Writing Skills

Writing Skills

Overview

Writing skills IS Test-Driven Development applied to process documentation.

Personal skills live in client-specific global directories such as `~/.claude/skills` for Claude Code, `~/.codex/skills/` for Codex, `~/.agents/skills/` as the shared mirror, and `C:/Users/LOQ/.gemini/antigravity/global_skills` for the current Gemini Antigravity setup.

You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).

Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.

REQUIRED BACKGROUND: You MUST understand superpowers:test-driven-development before using this skill. That skill defines the fundamental RED-GREEN-REFACTOR cycle. This skill adapts TDD to documentation.

Official guidance: For Anthropic's official skill authoring best practices, see anthropic-best-practices.md. This document provides additional patterns and guidelines that complement the TDD-focused approach in this skill.

• Leverage native parallel subagent dispatch and 200k+ context windows where available.

What is a Skill?

A skill is a reference guide for proven techniques, patterns, or tools. Skills help future Claude instances find and apply effective approaches.

Skills are: Reusable techniques, patterns, tools, reference guides

Skills are NOT: Narratives about how you solved a problem once

TDD Mapping for Skills

Increment patch on wording/clarity fixes. Increment minor when adding a new verification step, example, or anti-pattern. Major only on breaking changes to core workflow.

The entire skill creation process follows RED-GREEN-REFACTOR.

When to Create a Skill

Create when:

• Technique wasn't intuitively obvious to you
• You'd reference this again across projects
• Pattern applies broadly (not project-specific)
• Others would benefit

Don't create for:

• One-off solutions
• Standard practices well-documented elsewhere
• Project-specific conventions (put in CLAUDE.md)
• Mechanical constraints (if it's enforceable with regex/validation, automate it—save documentation for judgment calls)

Skill Types

Skill Deprecation & Sunset

Deprecate a skill when the workflow is obsolete, fully covered by a narrower maintained skill, or no longer passes pressure scenarios. Mark the replacement path in frontmatter description or Related Skills, preserve provenance briefly, and remove only after downstream clients no longer depend on the old trigger.

Directory Structure

skills/
  skill-name/
    SKILL.md              # Main reference (required)
    supporting-file.*     # Only if needed

Flat namespace - all skills in one searchable namespace

Separate files for: 1. Heavy reference (100+ lines) - API docs, comprehensive syntax 2. Reusable tools - Scripts, utilities, templates

Keep inline:

• Principles and concepts
• Code patterns (< 50 lines)
• Everything else

SKILL.md Structure

Frontmatter (YAML):

• Portable minimum fields: name and description
• This maintained catalog also permits bounded imported-skill metadata: license, version, compatibility, and metadata
• For new original skills, prefer only name and description unless provenance, licensing, or upstream update tracking needs extra metadata
• Max 1024 characters total
• name: Use letters, numbers, and hyphens only (no parentheses, special chars)
• description: Third-person, describes ONLY when to use (NOT what it does)
• Start with "Use when..." to focus on triggering conditions
• Include specific symptoms, situations, and contexts
• NEVER summarize the skill's process or workflow (see CSO section for why)
• Keep under 500 characters if possible

---
name: Skill-Name-With-Hyphens
description: Use when [specific triggering conditions and symptoms]
---

# Skill Name

## Overview
What is this? Core principle in 1-2 sentences.

## When to Use
Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.

[Small inline flowchart IF decision non-obvious]

Bullet list with SYMPTOMS and use cases
When NOT to use

## Core Pattern (for techniques/patterns)
Before/after code comparison

## Quick Reference
Table or bullets for scanning common operations

## Implementation
Inline code for simple patterns
Link to file for heavy reference or reusable tools

## Common Mistakes
What goes wrong + fixes

## Real-World Impact (optional)
Concrete results

Claude Search Optimization (CSO)

Critical for discovery: Future Claude needs to FIND your skill

1. Rich Description Field

Purpose: Claude reads description to decide which skills to load for a given task. Make it answer: "Should I read this skill right now?"

Format: Start with "Use when..." to focus on triggering conditions

CRITICAL: Description = When to Use, NOT What the Skill Does

The description should ONLY describe triggering conditions. Do NOT summarize the skill's process or workflow in the description.

Why this matters: Testing revealed that when a description summarizes the skill's workflow, Claude may follow the description instead of reading the full skill content. A description saying "two-stage review (spec compliance first, then code quality) between tasks" caused Claude to do ONE review, even though the skill's flowchart clearly showed TWO reviews (spec compliance then code quality).

When the description was changed to just "Use when executing implementation plans with independent tasks" (no workflow summary), Claude correctly read the flowchart and followed the two-stage review process.

The trap: Descriptions that summarize workflow create a shortcut Claude will take. The skill body becomes documentation Claude skips.

# ❌ BAD: Summarizes workflow - Claude may follow this instead of reading skill
description: Use when executing plans - dispatches subagent per task with two-stage review (spec compliance first, then code quality) between tasks

# ❌ BAD: Too much process detail
description: Use for TDD - write test first, watch it fail, write minimal code, refactor

# ✅ GOOD: Just triggering conditions, no workflow summary
description: Use when executing implementation plans with independent tasks in the current session

# ✅ GOOD: Triggering conditions only
description: Use when implementing any feature or bugfix, before writing implementation code

Content:

• Use concrete triggers, symptoms, and situations that signal this skill applies
• Describe the problem (race conditions, inconsistent behavior) not language-specific symptoms (setTimeout, sleep)
• Keep triggers technology-agnostic unless the skill itself is technology-specific
• If skill is technology-specific, make that explicit in the trigger
• Write in third person (injected into system prompt)
• NEVER summarize the skill's process or workflow

# ❌ BAD: Too abstract, vague, doesn't include when to use
description: For async testing

# ❌ BAD: First person
description: I can help you with async tests when they're flaky

# ❌ BAD: Mentions technology but skill isn't specific to it
description: Use when tests use setTimeout/sleep and are flaky

# ✅ GOOD: Starts with "Use when", describes problem, no workflow
description: Use when tests have race conditions, timing dependencies, or pass/fail inconsistently

# ✅ GOOD: Technology-specific skill with explicit trigger
description: Use when using React Router and handling authentication redirects

2. Keyword Coverage

Use words Claude would search for:

• Error messages: "Hook timed out", "ENOTEMPTY", "race condition"
• Symptoms: "flaky", "hanging", "zombie", "pollution"
• Synonyms: "timeout/hang/freeze", "cleanup/teardown/afterEach"
• Tools: Actual commands, library names, file types

3. Descriptive Naming

Use active voice, verb-first:

• ✅ creating-skills not skill-creation
• ✅ condition-based-waiting not async-test-helpers

4. Token Efficiency (Critical)

Problem: getting-started and frequently-referenced skills load into EVERY conversation. Every token counts.

Target word counts:

• getting-started workflows: <150 words each
• Frequently-loaded skills: <200 words total
• Other skills: <500 words (still be concise)

Techniques:

Move details to tool help:

# ❌ BAD: Document all flags in SKILL.md
search-conversations supports --text, --both, --after DATE, --before DATE, --limit N

# ✅ GOOD: Reference --help
search-conversations supports multiple modes and filters. Run --help for details.

Use cross-references:

# ❌ BAD: Repeat workflow details
When searching, dispatch subagent with template...
[20 lines of repeated instructions]

# ✅ GOOD: Reference other skill
Always use subagents (50-100x context savings). REQUIRED: Use [other-skill-name] for workflow.

Compress examples:

# ❌ BAD: Verbose example (42 words)
your human partner: "How did we handle authentication errors in React Router before?"
You: I'll search past conversations for React Router authentication patterns.
[Dispatch subagent with search query: "React Router authentication error handling 401"]

# ✅ GOOD: Minimal example (20 words)
Partner: "How did we handle auth errors in React Router?"
You: Searching...
[Dispatch subagent → synthesis]

Eliminate redundancy:

• Don't repeat what's in cross-referenced skills
• Don't explain what's obvious from command
• Don't include multiple examples of same pattern

Verification:

wc -w skills/path/SKILL.md
# getting-started workflows: aim for <150 each
# Other frequently-loaded: aim for <200 total

Name by what you DO or core insight:

• ✅ condition-based-waiting > async-test-helpers
• ✅ using-skills not skill-usage
• ✅ flatten-with-flags > data-structure-refactoring
• ✅ root-cause-tracing > debugging-techniques

Gerunds (-ing) work well for processes:

• creating-skills, testing-skills, debugging-with-logs
• Active, describes the action you're taking

4. Cross-Referencing Other Skills

When writing documentation that references other skills:

Use skill name only, with explicit requirement markers:

• ✅ Good: **REQUIRED SUB-SKILL:** Use superpowers:test-driven-development
• ✅ Good: **REQUIRED BACKGROUND:** You MUST understand superpowers:systematic-debugging
• ❌ Bad: See skills/testing/test-driven-development (unclear if required)
• ❌ Bad: @skills/testing/test-driven-development/SKILL.md (force-loads, burns context)

Why no @ links: @ syntax force-loads files immediately, consuming 200k+ context before you need them.

Flowchart Usage

digraph when_flowchart {
    "Need to show information?" [shape=diamond];
    "Decision where I might go wrong?" [shape=diamond];
    "Use markdown" [shape=box];
    "Small inline flowchart" [shape=box];

    "Need to show information?" -> "Decision where I might go wrong?" [label="yes"];
    "Decision where I might go wrong?" -> "Small inline flowchart" [label="yes"];
    "Decision where I might go wrong?" -> "Use markdown" [label="no"];
}

Use flowcharts ONLY for:

• Non-obvious decision points
• Process loops where you might stop too early
• "When to use A vs B" decisions

Never use flowcharts for:

• Reference material → Tables, lists
• Code examples → Markdown blocks
• Linear instructions → Numbered lists
• Labels without semantic meaning (step1, helper2)

See @graphviz-conventions.dot for graphviz style rules.

Visualizing for your human partner: Use render-graphs.js in this directory to render a skill's flowcharts to SVG:

./render-graphs.js ../some-skill           # Each diagram separately
./render-graphs.js ../some-skill --combine # All diagrams in one SVG

Anti-Patterns

• Writing for the author instead of the reader: It bakes in unstated context and leaves the actual audience unsure what to do next.
• Skipping concrete examples or commands: Abstract guidance is easy to approve and hard to apply correctly.
• Letting links, screenshots, or versions drift: Polished formatting does not help if the instructions are no longer true.

Verification Protocol

Before claiming "skill applied successfully":

1. Pass/fail: The Writing Skills output identifies audience, purpose, source of truth, and freshness requirements. 2. Pass/fail: Shared documentation-stack guidance is referenced instead of duplicating another documentation skill. 3. Pass/fail: Claims, links, commands, examples, and screenshots are verified or explicitly marked unverified. 4. Pressure-test scenario: Apply the skill to a doc request with a stale command, missing owner, and conflicting audience. 5. Success metric: Zero undocumented assumptions; every reader-facing claim is sourced or scoped.

Code Examples

One excellent example beats many mediocre ones

Choose most relevant language:

• Testing techniques → TypeScript/JavaScript
• System debugging → Shell/Python
• Data processing → Python

Good example:

• Complete and runnable
• Well-commented explaining WHY
• From real scenario
• Shows pattern clearly
• Ready to adapt (not generic template)

Don't:

• Implement in 5+ languages
• Create fill-in-the-blank templates
• Write contrived examples

You're good at porting - one great example is enough.

File Organization

Self-Contained Skill

defense-in-depth/
  SKILL.md    # Everything inline

When: All content fits, no heavy reference needed

Skill with Reusable Tool

condition-based-waiting/
  SKILL.md    # Overview + patterns
  example.ts  # Working helpers to adapt

When: Tool is reusable code, not just narrative

Skill with Heavy Reference

pptx/
  SKILL.md       # Overview + workflows
  pptxgenjs.md   # 600 lines API reference
  ooxml.md       # 500 lines XML structure
  scripts/       # Executable tools

When: Reference material too large for inline

The Iron Law (Same as TDD)

NO SKILL WITHOUT A FAILING TEST FIRST

This applies to NEW skills AND EDITS to existing skills.

Write skill before testing? Delete it. Start over. Edit skill without testing? Same violation.

No exceptions:

• Not for "simple additions"
• Not for "just adding a section"
• Not for "documentation updates"
• Don't keep untested changes as "reference"
• Don't "adapt" while running tests
• Delete means delete

REQUIRED BACKGROUND: The superpowers:test-driven-development skill explains why this matters. Same principles apply to documentation.

Testing All Skill Types

Different skill types need different test approaches:

Discipline-Enforcing Skills (rules/requirements)

Examples: TDD, verification-before-completion, designing-before-coding

Test with:

• Academic questions: Do they understand the rules?
• Pressure scenarios: Do they comply under stress?
• Multiple pressures combined: time + sunk cost + exhaustion
• Identify rationalizations and add explicit counters

Success criteria: Agent follows rule under maximum pressure

Technique Skills (how-to guides)

Examples: condition-based-waiting, root-cause-tracing, defensive-programming

Test with:

• Application scenarios: Can they apply the technique correctly?
• Variation scenarios: Do they handle edge cases?
• Missing information tests: Do instructions have gaps?

Success criteria: Agent successfully applies technique to new scenario

Pattern Skills (mental models)

Examples: reducing-complexity, information-hiding concepts

Test with:

• Recognition scenarios: Do they recognize when pattern applies?
• Application scenarios: Can they use the mental model?
• Counter-examples: Do they know when NOT to apply?

Success criteria: Agent correctly identifies when/how to apply pattern

Reference Skills (documentation/APIs)

Examples: API documentation, command references, library guides

Test with:

• Retrieval scenarios: Can they find the right information?
• Application scenarios: Can they use what they found correctly?
• Gap testing: Are common use cases covered?

Success criteria: Agent finds and correctly applies reference information

Common Rationalizations for Skipping Testing

All of these mean: Test before deploying. No exceptions.

Bulletproofing Skills Against Rationalization

Skills that enforce discipline (like TDD) need to resist rationalization. Agents are smart and will find loopholes when under pressure.

Psychology note: Understanding WHY persuasion techniques work helps you apply them systematically. See persuasion-principles.md for research foundation (Cialdini, 2021; Meincke et al., 2025) on authority, commitment, scarcity, social proof, and unity principles.

Close Every Loophole Explicitly

Don't just state the rule - forbid specific workarounds:

<Bad>

Write code before test? Delete it.

</Bad>

<Good>

Write code before test? Delete it. Start over.

**No exceptions:**
- Don't keep it as "reference"
- Don't "adapt" it while writing tests
- Don't look at it
- Delete means delete

</Good>

Address "Spirit vs Letter" Arguments

Add foundational principle early:

**Violating the letter of the rules is violating the spirit of the rules.**

This cuts off entire class of "I'm following the spirit" rationalizations.

Build Rationalization Table

Capture rationalizations from baseline testing (see Testing section below). Every excuse agents make goes in the table:

| Excuse | Reality |
|--------|---------|
| "Too simple to test" | Simple code breaks. Test takes 30 seconds. |
| "I'll test after" | Tests passing immediately prove nothing. |
| "Tests after achieve same goals" | Tests-after = "what does this do?" Tests-first = "what should this do?" |

Create Red Flags List

Make it easy for agents to self-check when rationalizing:

## Red Flags - STOP and Start Over

- Code before test
- "I already manually tested it"
- "Tests after achieve the same purpose"
- "It's about spirit not ritual"
- "This is different because..."

**All of these mean: Delete code. Start over with TDD.**

Update CSO for Violation Symptoms

Add to description: symptoms of when you're ABOUT to violate the rule:

description: use when implementing any feature or bugfix, before writing implementation code

RED-GREEN-REFACTOR for Skills

Follow the TDD cycle:

RED: Write Failing Test (Baseline)

Run pressure scenario with subagent WITHOUT the skill. Document exact behavior:

• What choices did they make?
• What rationalizations did they use (verbatim)?
• Which pressures triggered violations?

This is "watch the test fail" - you must see what agents naturally do before writing the skill.

GREEN: Write Minimal Skill

Write skill that addresses those specific rationalizations. Don't add extra content for hypothetical cases.

Run same scenarios WITH skill. Agent should now comply.

REFACTOR: Close Loopholes

Agent found new rationalization? Add explicit counter. Re-test until bulletproof.

Testing methodology: See @testing-skills-with-subagents.md for the complete testing methodology:

• How to write pressure scenarios
• Pressure types (time, sunk cost, authority, exhaustion)
• Plugging holes systematically
• Meta-testing techniques

STOP: Before Moving to Next Skill

After writing ANY skill, you MUST STOP and complete the deployment process.

Do NOT:

• Create multiple skills in batch without testing each
• Move to next skill before current one is verified
• Skip testing because "batching is more efficient"

The deployment checklist below is MANDATORY for EACH skill.

Deploying untested skills = deploying untested code. It's a violation of quality standards.

Skill Creation Checklist (TDD Adapted)

IMPORTANT: Use TodoWrite to create todos for EACH checklist item below.

RED Phase - Write Failing Test:

• [ ] Create pressure scenarios (3+ combined pressures for discipline skills)
• [ ] Run scenarios WITHOUT skill - document baseline behavior verbatim
• [ ] Identify patterns in rationalizations/failures

GREEN Phase - Write Minimal Skill:

• [ ] Name uses only letters, numbers, hyphens (no parentheses/special chars)
• [ ] YAML frontmatter includes the portable minimum fields: name and description (max 1024 chars)
• [ ] Description starts with "Use when..." and includes specific triggers/symptoms
• [ ] Description written in third person
• [ ] Keywords throughout for search (errors, symptoms, tools)
• [ ] Clear overview with core principle
• [ ] Address specific baseline failures identified in RED
• [ ] Code inline OR link to separate file
• [ ] One excellent example (not multi-language)
• [ ] Run scenarios WITH skill - verify agents now comply

REFACTOR Phase - Close Loopholes:

• [ ] Identify NEW rationalizations from testing
• [ ] Add explicit counters (if discipline skill)
• [ ] Build rationalization table from all test iterations
• [ ] Create red flags list
• [ ] Re-test until bulletproof

Quality Checks:

• [ ] Small flowchart only if decision non-obvious
• [ ] Quick reference table
• [ ] Common mistakes section
• [ ] No narrative storytelling
• [ ] Supporting files only for tools or heavy reference

Deployment:

• [ ] Commit skill to git and push to your fork (if configured)
• [ ] Consider contributing back via PR (if broadly useful)

Discovery Workflow

How future Claude finds your skill:

1. Encounters problem ("tests are flaky") 3. Finds SKILL (description matches) 4. Scans overview (is this relevant?) 5. Reads patterns (quick reference table) 6. Loads example (only when implementing)

Optimize for this flow - put searchable terms early and often.

The Bottom Line

Creating skills IS TDD for process documentation.

Same Iron Law: No skill without failing test first. Same cycle: RED (baseline) → GREEN (write skill) → REFACTOR (close loopholes). Same benefits: Better quality, fewer surprises, bulletproof results.

If you follow TDD for code, follow it for skills. It's the same discipline applied to documentation.

<!-- PORTABILITY:START -->

Cross-Client Portability

This skill is written to stay usable across GitHub Copilot, Claude Code, Codex, and Gemini CLI.

• GitHub Copilot: keep the folder in a Copilot-visible skill or plugin path, or wrap the workflow as project instructions if the host does not support portable skill folders directly.
• Claude Code: keep the folder in a local skills directory or a compatible plugin or marketplace source.
• Codex: install or sync the folder into $CODEX_HOME/skills/<skill-name> and restart Codex after major changes.
• Gemini CLI: this repository generates a project command named /skills:writing-skills from this skill. Rebuild commands with python scripts/export-gemini-skill.py writing-skills and then run /commands reload inside Gemini CLI.

<!-- PORTABILITY:END -->

<!-- MCP:START -->

MCP Availability And Fallback

Preferred MCP Server: None required

• Fallback prompt: "Use the Writing Skills skill without MCP. Rely on the local SKILL.md, bundled references or scripts, and manual verification. Show the exact commands, evidence, and final checks you used before concluding."
• If the current host does not expose a matching server, use the bundled references, scripts, native toolchain, and manual workflow already described in this skill.
• Treat direct local verification, rendered output, logs, tests, or screenshots as the fallback evidence path before completion.

<!-- MCP:END -->

Related Skills

• documentation-authoring: Use it when the workflow also needs drafting structured technical or product documents.
• documentation-patterns: Use it when the workflow also needs reusable documentation structures and templates.
• documentation-quality: Use it when the workflow also needs documentation review standards and quality gates.
• documentation-verification: Use it when the workflow also needs final documentation validation before publishing.

Skill authoring best practices

Learn how to write effective Skills that Claude can discover and use successfully.

Good Skills are concise, well-structured, and tested with real usage. This guide provides practical authoring decisions to help you write Skills that Claude can discover and use effectively.

For conceptual background on how Skills work, see the Skills overview.

Core principles

Concise is key

The context window is a public good. Your Skill shares the context window with everything else Claude needs to know, including:

• The system prompt
• Conversation history
• Other Skills' metadata
• Your actual request

Not every token in your Skill has an immediate cost. At startup, only the metadata (name and description) from all Skills is pre-loaded. Claude reads SKILL.md only when the Skill becomes relevant, and reads additional files only as needed. However, being concise in SKILL.md still matters: once Claude loads it, every token competes with conversation history and other context.

Default assumption: Claude is already very smart

Only add context Claude doesn't already have. Challenge each piece of information:

• "Does Claude really need this explanation?"
• "Can I assume Claude knows this?"
• "Does this paragraph justify its token cost?"

Good example: Concise (approximately 50 tokens):

````markdown theme={null}

Extract PDF text

Use pdfplumber for text extraction:

import pdfplumber

with pdfplumber.open("file.pdf") as pdf:
    text = pdf.pages[0].extract_text()

````

Bad example: Too verbose (approximately 150 tokens):

```markdown theme={null}

Extract PDF text

PDF (Portable Document Format) files are a common file format that contains text, images, and other content. To extract text from a PDF, you'll need to use a library. There are many libraries available for PDF processing, but we recommend pdfplumber because it's easy to use and handles most cases well. First, you'll need to install it using pip. Then you can use the code below...

The concise version assumes Claude knows what PDFs are and how libraries work.

### Set appropriate degrees of freedom

Match the level of specificity to the task's fragility and variability.

**High freedom** (text-based instructions):

Use when:

* Multiple approaches are valid
* Decisions depend on context
* Heuristics guide the approach

Example:

Code review process

1. Analyze the code structure and organization 2. Check for potential bugs or edge cases 3. Suggest improvements for readability and maintainability 4. Verify adherence to project conventions

**Medium freedom** (pseudocode or scripts with parameters):

Use when:

* A preferred pattern exists
* Some variation is acceptable
* Configuration affects behavior

Example:

Generate report

Use this template and customize as needed:

def generate_report(data, format="markdown", include_charts=True):
    # Process data
    # Generate output in specified format
    # Optionally include visualizations

````

Low freedom (specific scripts, few or no parameters):

Use when:

• Operations are fragile and error-prone
• Consistency is critical
• A specific sequence must be followed

Example:

````markdown theme={null}

Database migration

Run exactly this script:

python scripts/migrate.py --verify --backup

Do not modify the command or add additional flags. ````

Analogy: Think of Claude as a robot exploring a path:

• Narrow bridge with cliffs on both sides: There's only one safe way forward. Provide specific guardrails and exact instructions (low freedom). Example: database migrations that must run in exact sequence.
• Open field with no hazards: Many paths lead to success. Give general direction and trust Claude to find the best route (high freedom). Example: two-stage reviews (spec compliance first, then code quality) where context determines the best approach.

Test with all models you plan to use

Skills act as additions to models, so effectiveness depends on the underlying model. Test your Skill with all the models you plan to use it with.

Testing considerations by model:

• Claude Haiku (fast, economical): Does the Skill provide enough guidance?
• Claude Sonnet (balanced): Is the Skill clear and efficient?
• Claude Opus (powerful reasoning): Does the Skill avoid over-explaining?

What works perfectly for Opus might need more detail for Haiku. If you plan to use your Skill across multiple models, aim for instructions that work well with all of them.

Skill structure

<Note> YAML Frontmatter: The SKILL.md frontmatter supports two fields:

• name - Human-readable name of the Skill (64 characters maximum)
• description - One-line description of what the Skill does and when to use it (1024 characters maximum)

For complete Skill structure details, see the Skills overview. </Note>

Naming conventions

Use consistent naming patterns to make Skills easier to reference and discuss. We recommend using gerund form (verb + -ing) for Skill names, as this clearly describes the activity or capability the Skill provides.

Good naming examples (gerund form):

• "Processing PDFs"
• "Analyzing spreadsheets"
• "Managing databases"
• "Testing code"
• "Writing documentation"

Acceptable alternatives:

• Noun phrases: "PDF Processing", "Spreadsheet Analysis"
• Action-oriented: "Process PDFs", "Analyze Spreadsheets"

Avoid:

• Vague names: "Helper", "Utils", "Tools"
• Overly generic: "Documents", "Data", "Files"
• Inconsistent patterns within your skill collection

Consistent naming makes it easier to:

• Reference Skills in documentation and conversations
• Understand what a Skill does at a glance
• Organize and search through multiple Skills
• Maintain a professional, cohesive skill library

Writing effective descriptions

The description field enables Skill discovery and should include both what the Skill does and when to use it.

<Warning> Always write in third person. The description is injected into the system prompt, and inconsistent point-of-view can cause discovery problems.

• Good: "Processes Excel files and generates reports"
• Avoid: "I can help you process Excel files"
• Avoid: "You can use this to process Excel files"

</Warning>

Be specific and include key terms. Include both what the Skill does and specific triggers/contexts for when to use it.

Each Skill has exactly one description field. The description is critical for skill selection: Claude uses it to choose the right Skill from potentially 100+ available Skills. Your description must provide enough detail for Claude to know when to select this Skill, while the rest of SKILL.md provides the implementation details.

Effective examples:

PDF Processing skill:

```yaml theme={null} description: Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.

**Excel Analysis skill:**

description: Analyze Excel spreadsheets, create pivot tables, generate charts. Use when analyzing Excel files, spreadsheets, tabular data, or .xlsx files.

**Git Commit Helper skill:**

description: Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.

Avoid vague descriptions like these:

description: Helps with documents

description: Processes data

description: Does stuff with files

### Progressive disclosure patterns

SKILL.md serves as an overview that points Claude to detailed materials as needed, like a table of contents in an onboarding guide. For an explanation of how progressive disclosure works, see [How Skills work](/en/docs/agents-and-tools/agent-skills/overview#how-skills-work) in the overview.

**Practical guidance:**

* Keep SKILL.md body under 500 lines for optimal performance
* Split content into separate files when approaching this limit
* Use the patterns below to organize instructions, code, and resources effectively

#### Visual overview: From simple to complex

A basic Skill starts with just a SKILL.md file containing metadata and instructions:

<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=87782ff239b297d9a9e8e1b72ed72db9" alt="Simple SKILL.md file showing YAML frontmatter and markdown body" data-og-width="2048" width="2048" data-og-height="1153" height="1153" data-path="images/agent-skills-simple-file.png" data-optimize="true" data-opv="3" srcset="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=280&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=c61cc33b6f5855809907f7fda94cd80e 280w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=560&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=90d2c0c1c76b36e8d485f49e0810dbfd 560w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=840&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=ad17d231ac7b0bea7e5b4d58fb4aeabb 840w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=1100&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=f5d0a7a3c668435bb0aee9a3a8f8c329 1100w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=1650&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=0e927c1af9de5799cfe557d12249f6e6 1650w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-simple-file.png?w=2500&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=46bbb1a51dd4c8202a470ac8c80a893d 2500w" />

As your Skill grows, you can bundle additional content that Claude loads only when needed:

<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=a5e0aa41e3d53985a7e3e43668a33ea3" alt="Bundling additional reference files like reference.md and forms.md." data-og-width="2048" width="2048" data-og-height="1327" height="1327" data-path="images/agent-skills-bundling-content.png" data-optimize="true" data-opv="3" srcset="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=280&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=f8a0e73783e99b4a643d79eac86b70a2 280w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=560&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=dc510a2a9d3f14359416b706f067904a 560w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=840&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=82cd6286c966303f7dd914c28170e385 840w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=1100&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=56f3be36c77e4fe4b523df209a6824c6 1100w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=1650&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=d22b5161b2075656417d56f41a74f3dd 1650w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-bundling-content.png?w=2500&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=3dd4bdd6850ffcc96c6c45fcb0acd6eb 2500w" />

The complete Skill directory structure might look like this:

pdf/ ├── SKILL.md # Main instructions (loaded when triggered) ├── FORMS.md # Form-filling guide (loaded as needed) ├── reference.md # API reference (loaded as needed) ├── examples.md # Usage examples (loaded as needed) └── scripts/ ├── analyze_form.py # Utility script (executed, not loaded) ├── fill_form.py # Form filling script └── validate.py # Validation script

#### Pattern 1: High-level guide with references

--- name: PDF Processing description: Extracts text and tables from PDF files, fills forms, and merges documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction. ---

PDF Processing

Quick start

Extract text with pdfplumber:

import pdfplumber
with pdfplumber.open("file.pdf") as pdf:
    text = pdf.pages[0].extract_text()

Advanced features

Form filling: See FORMS.md for complete guide API reference: See REFERENCE.md for all methods Examples: See EXAMPLES.md for common patterns ````

Claude loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed.

Pattern 2: Domain-specific organization

For Skills with multiple domains, organize content by domain to avoid loading irrelevant context. When a user asks about sales metrics, Claude only needs to read sales-related schemas, not finance or marketing data. This keeps token usage low and context focused.

bigquery-skill/
├── SKILL.md (overview and navigation)
└── reference/
    ├── finance.md (revenue, billing metrics)
    ├── sales.md (opportunities, pipeline)
    ├── product.md (API usage, features)
    └── marketing.md (campaigns, attribution)

````markdown SKILL.md theme={null}

BigQuery Data Analysis

Available datasets

Finance: Revenue, ARR, billing → See reference/finance.md Sales: Opportunities, pipeline, accounts → See reference/sales.md Product: API usage, features, adoption → See reference/product.md Marketing: Campaigns, attribution, email → See reference/marketing.md

Quick search

Find specific metrics using grep:

grep -i "revenue" reference/finance.md
grep -i "pipeline" reference/sales.md
grep -i "api usage" reference/product.md

````

Pattern 3: Conditional details

Show basic content, link to advanced content:

```markdown theme={null}

DOCX Processing

Creating documents

Use docx-js for new documents. See DOCX-JS.md.

Editing documents

For simple edits, modify the XML directly.

For tracked changes: See REDLINING.md For OOXML details: See OOXML.md

Claude reads REDLINING.md or OOXML.md only when the user needs those features.

### Avoid deeply nested references

Claude may partially read files when they're referenced from other referenced files. When encountering nested references, Claude might use commands like `head -100` to preview content rather than reading entire files, resulting in incomplete information.

**Keep references one level deep from SKILL.md**. All reference files should link directly from SKILL.md to ensure Claude reads complete files when needed.

**Bad example: Too deep**:

SKILL.md

See advanced.md...

advanced.md

See details.md...

details.md

Here's the actual information...

**Good example: One level deep**:

SKILL.md

Basic usage: [instructions in SKILL.md] Advanced features: See advanced.md API reference: See reference.md Examples: See examples.md

### Structure longer reference files with table of contents

For reference files longer than 100 lines, include a table of contents at the top. This ensures Claude can see the full scope of available information even when previewing with partial reads.

**Example**:

API Reference

Contents

• Authentication and setup
• Core methods (create, read, update, delete)
• Advanced features (batch operations, webhooks)
• Error handling patterns
• Code examples

Authentication and setup

...

Core methods

...

Claude can then read the complete file or jump to specific sections as needed.

For details on how this filesystem-based architecture enables progressive disclosure, see the [Runtime environment](#runtime-environment) section in the Advanced section below.

## Workflows and feedback loops

### Use workflows for complex tasks

Break complex operations into clear, sequential steps. For particularly complex workflows, provide a checklist that Claude can copy into its response and check off as it progresses.

**Example 1: Research synthesis workflow** (for Skills without code):

Research synthesis workflow

Copy this checklist and track your progress:

Research Progress:
- [ ] Step 1: Read all source documents
- [ ] Step 2: Identify key themes
- [ ] Step 3: Cross-reference claims
- [ ] Step 4: Create structured summary
- [ ] Step 5: Verify citations

Step 1: Read all source documents

Review each document in the sources/ directory. Note the main arguments and supporting evidence.

Step 2: Identify key themes

Look for patterns across sources. What themes appear repeatedly? Where do sources agree or disagree?

Step 3: Cross-reference claims

For each major claim, verify it appears in the source material. Note which source supports each point.

Step 4: Create structured summary

Organize findings by theme. Include:

• Main claim
• Supporting evidence from sources
• Conflicting viewpoints (if any)

Step 5: Verify citations

Check that every claim references the correct source document. If citations are incomplete, return to Step 3. ````

This example shows how workflows apply to analysis tasks that don't require code. The checklist pattern works for any complex, multi-step process.

Example 2: PDF form filling workflow (for Skills with code):

````markdown theme={null}

PDF form filling workflow

Copy this checklist and check off items as you complete them:

Task Progress:
- [ ] Step 1: Analyze the form (run analyze_form.py)
- [ ] Step 2: Create field mapping (edit fields.json)
- [ ] Step 3: Validate mapping (run validate_fields.py)
- [ ] Step 4: Fill the form (run fill_form.py)
- [ ] Step 5: Verify output (run verify_output.py)

Step 1: Analyze the form

Run: python scripts/analyze_form.py input.pdf

This extracts form fields and their locations, saving to fields.json.

Step 2: Create field mapping

Edit fields.json to add values for each field.

Step 3: Validate mapping

Run: python scripts/validate_fields.py fields.json

Fix any validation errors before continuing.

Step 4: Fill the form

Run: python scripts/fill_form.py input.pdf fields.json output.pdf

Step 5: Verify output

Run: python scripts/verify_output.py output.pdf

If verification fails, return to Step 2. ````

Clear steps prevent Claude from skipping critical validation. The checklist helps both Claude and you track progress through multi-step workflows.

Implement feedback loops

Common pattern: Run validator → fix errors → repeat

This pattern greatly improves output quality.

Example 1: Style guide compliance (for Skills without code):

```markdown theme={null}

Content review process

1. Draft your content following the guidelines in STYLE_GUIDE.md 2. Review against the checklist:

• Check terminology consistency
• Verify examples follow the standard format
• Confirm all required sections are present

3. If issues found:

• Note each issue with specific section reference
• Revise the content
• Review the checklist again

4. Only proceed when all requirements are met 5. Finalize and save the document

This shows the validation loop pattern using reference documents instead of scripts. The "validator" is STYLE\_GUIDE.md, and Claude performs the check by reading and comparing.

**Example 2: Document editing process** (for Skills with code):

Document editing process

1. Make your edits to word/document.xml 2. Validate immediately: python ooxml/scripts/validate.py unpacked_dir/ 3. If validation fails:

• Review the error message carefully
• Fix the issues in the XML
• Run validation again

4. Only proceed when validation passes 5. Rebuild: python ooxml/scripts/pack.py unpacked_dir/ output.docx 6. Test the output document

The validation loop catches errors early.

## Content guidelines

### Avoid time-sensitive information

Don't include information that will become outdated:

**Bad example: Time-sensitive** (will become wrong):

If you're doing this before August 2025, use the old API. After August 2025, use the new API.

**Good example** (use "old patterns" section):

Current method

Use the v2 API endpoint: api.example.com/v2/messages

Old patterns

<details> <summary>Legacy v1 API (deprecated 2025-08)</summary>

The v1 API used: api.example.com/v1/messages

This endpoint is no longer supported. </details>

The old patterns section provides historical context without cluttering the main content.

### Use consistent terminology

Choose one term and use it throughout the Skill:

**Good - Consistent**:

* Always "API endpoint"
* Always "field"
* Always "extract"

**Bad - Inconsistent**:

* Mix "API endpoint", "URL", "API route", "path"
* Mix "field", "box", "element", "control"
* Mix "extract", "pull", "get", "retrieve"

Consistency helps Claude understand and follow instructions.

## Common patterns

### Template pattern

Provide templates for output format. Match the level of strictness to your needs.

**For strict requirements** (like API responses or data formats):

Report structure

ALWAYS use this exact template structure:

# [Analysis Title]

## Executive summary
[One-paragraph overview of key findings]

## Key findings
- Finding 1 with supporting data
- Finding 2 with supporting data
- Finding 3 with supporting data

## Recommendations
1. Specific actionable recommendation
2. Specific actionable recommendation

````

For flexible guidance (when adaptation is useful):

````markdown theme={null}

Report structure

Here is a sensible default format, but use your best judgment based on the analysis:

# [Analysis Title]

## Executive summary
[Overview]

## Key findings
[Adapt sections based on what you discover]

## Recommendations
[Tailor to the specific context]

Adjust sections as needed for the specific analysis type. ````

Examples pattern

For Skills where output quality depends on seeing examples, provide input/output pairs just like in regular prompting:

````markdown theme={null}

Commit message format

Generate commit messages following these examples:

Example 1: Input: Added user authentication with JWT tokens Output:

feat(auth): implement JWT-based authentication

Add login endpoint and token validation middleware

Example 2: Input: Fixed bug where dates displayed incorrectly in reports Output:

fix(reports): correct date formatting in timezone conversion

Use UTC timestamps consistently across report generation

Example 3: Input: Updated dependencies and refactored error handling Output:

chore: update dependencies and refactor error handling

- Upgrade lodash to 4.17.21
- Standardize error response format across endpoints

Follow this style: type(scope): brief description, then detailed explanation. ````

Examples help Claude understand the desired style and level of detail more clearly than descriptions alone.

Conditional workflow pattern

Guide Claude through decision points:

```markdown theme={null}

Document modification workflow

1. Determine the modification type:

Creating new content? → Follow "Creation workflow" below Editing existing content? → Follow "Editing workflow" below

2. Creation workflow:

• Use docx-js library
• Build document from scratch
• Export to .docx format

3. Editing workflow:

• Unpack existing document
• Modify XML directly
• Validate after each change
• Repack when complete

<Tip>
  If workflows become large or complicated with many steps, consider pushing them into separate files and tell Claude to read the appropriate file based on the task at hand.
</Tip>

## Evaluation and iteration

### Build evaluations first

**Create evaluations BEFORE writing extensive documentation.** This ensures your Skill solves real problems rather than documenting imagined ones.

**Evaluation-driven development:**

1. **Identify gaps**: Run Claude on representative tasks without a Skill. Document specific failures or missing context
2. **Create evaluations**: Build three scenarios that test these gaps
3. **Establish baseline**: Measure Claude's performance without the Skill
4. **Write minimal instructions**: Create just enough content to address the gaps and pass evaluations
5. **Iterate**: Execute evaluations, compare against baseline, and refine

This approach ensures you're solving actual problems rather than anticipating requirements that may never materialize.

**Evaluation structure**:

{ "skills": ["pdf-processing"], "query": "Extract all text from this PDF file and save it to output.txt", "files": ["test-files/document.pdf"], "expected_behavior": [ "Successfully reads the PDF file using an appropriate PDF processing library or command-line tool", "Extracts text content from all pages in the document without missing any pages", "Saves the extracted text to a file named output.txt in a clear, readable format" ] }

<Note>
  This example demonstrates a data-driven evaluation with a simple testing rubric. We do not currently provide a built-in way to run these evaluations. Users can create their own evaluation system. Evaluations are your source of truth for measuring Skill effectiveness.
</Note>

### Develop Skills iteratively with Claude

The most effective Skill development process involves Claude itself. Work with one instance of Claude ("Claude A") to create a Skill that will be used by other instances ("Claude B"). Claude A helps you design and refine instructions, while Claude B tests them in real tasks. This works because Claude models understand both how to write effective agent instructions and what information agents need.

**Creating a new Skill:**

1. **Complete a task without a Skill**: Work through a problem with Claude A using normal prompting. As you work, you'll naturally provide context, explain preferences, and share procedural knowledge. Notice what information you repeatedly provide.

2. **Identify the reusable pattern**: After completing the task, identify what context you provided that would be useful for similar future tasks.

   **Example**: If you worked through a BigQuery analysis, you might have provided table names, field definitions, filtering rules (like "always exclude test accounts"), and common query patterns.

3. **Ask Claude A to create a Skill**: "Create a Skill that captures this BigQuery analysis pattern we just used. Include the table schemas, naming conventions, and the rule about filtering test accounts."

   <Tip>
     Claude models understand the Skill format and structure natively. You don't need special system prompts or a "writing skills" skill to get Claude to help create Skills. Simply ask Claude to create a Skill and it will generate properly structured SKILL.md content with appropriate frontmatter and body content.
   </Tip>

4. **Review for conciseness**: Check that Claude A hasn't added unnecessary explanations. Ask: "Remove the explanation about what win rate means - Claude already knows that."

5. **Improve information architecture**: Ask Claude A to organize the content more effectively. For example: "Organize this so the table schema is in a separate reference file. We might add more tables later."

6. **Test on similar tasks**: Use the Skill with Claude B (a fresh instance with the Skill loaded) on related use cases. Observe whether Claude B finds the right information, applies rules correctly, and handles the task successfully.

7. **Iterate based on observation**: If Claude B struggles or misses something, return to Claude A with specifics: "When Claude used this Skill, it forgot to filter by date for Q4. Should we add a section about date filtering patterns?"

**Iterating on existing Skills:**

The same hierarchical pattern continues when improving Skills. You alternate between:

* **Working with Claude A** (the expert who helps refine the Skill)
* **Testing with Claude B** (the agent using the Skill to perform real work)
* **Observing Claude B's behavior** and bringing insights back to Claude A

1. **Use the Skill in real workflows**: Give Claude B (with the Skill loaded) actual tasks, not test scenarios

2. **Observe Claude B's behavior**: Note where it struggles, succeeds, or makes unexpected choices

   **Example observation**: "When I asked Claude B for a regional sales report, it wrote the query but forgot to filter out test accounts, even though the Skill mentions this rule."

3. **Return to Claude A for improvements**: Share the current SKILL.md and describe what you observed. Ask: "I noticed Claude B forgot to filter test accounts when I asked for a regional report. The Skill mentions filtering, but maybe it's not prominent enough?"

4. **Review Claude A's suggestions**: Claude A might suggest reorganizing to make rules more prominent, using stronger language like "MUST filter" instead of "always filter", or restructuring the workflow section.

5. **Apply and test changes**: Update the Skill with Claude A's refinements, then test again with Claude B on similar requests

6. **Repeat based on usage**: Continue this observe-refine-test cycle as you encounter new scenarios. Each iteration improves the Skill based on real agent behavior, not assumptions.

**Gathering team feedback:**

1. Share Skills with teammates and observe their usage
2. Ask: Does the Skill activate when expected? Are instructions clear? What's missing?
3. Incorporate feedback to address blind spots in your own usage patterns

**Why this approach works**: Claude A understands agent needs, you provide domain expertise, Claude B reveals gaps through real usage, and iterative refinement improves Skills based on observed behavior rather than assumptions.

### Observe how Claude navigates Skills

As you iterate on Skills, pay attention to how Claude actually uses them in practice. Watch for:

* **Unexpected exploration paths**: Does Claude read files in an order you didn't anticipate? This might indicate your structure isn't as intuitive as you thought
* **Missed connections**: Does Claude fail to follow references to important files? Your links might need to be more explicit or prominent
* **Overreliance on certain sections**: If Claude repeatedly reads the same file, consider whether that content should be in the main SKILL.md instead
* **Ignored content**: If Claude never accesses a bundled file, it might be unnecessary or poorly signaled in the main instructions

Iterate based on these observations rather than assumptions. The 'name' and 'description' in your Skill's metadata are particularly critical. Claude uses these when deciding whether to trigger the Skill in response to the current task. Make sure they clearly describe what the Skill does and when it should be used.

## Anti-patterns to avoid

### Avoid Windows-style paths

Always use forward slashes in file paths, even on Windows:

* ✓ **Good**: `scripts/helper.py`, `reference/guide.md`
* ✗ **Avoid**: `scripts\helper.py`, `reference\guide.md`

Unix-style paths work across all platforms, while Windows-style paths cause errors on Unix systems.

### Avoid offering too many options

Don't present multiple approaches unless necessary:

Bad example: Too many choices (confusing): "You can use pypdf, or pdfplumber, or PyMuPDF, or pdf2image, or..."

Good example: Provide a default (with escape hatch): "Use pdfplumber for text extraction:

import pdfplumber

For scanned PDFs requiring OCR, use pdf2image with pytesseract instead." ````

Advanced: Skills with executable code

The sections below focus on Skills that include executable scripts. If your Skill uses only markdown instructions, skip to Checklist for effective Skills.

Solve, don't punt

When writing scripts for Skills, handle error conditions rather than punting to Claude.

Good example: Handle errors explicitly:

```python theme={null} def process_file(path): """Process a file, creating it if it doesn't exist.""" try: with open(path) as f: return f.read() except FileNotFoundError:

Create file with default content instead of failing

print(f"File {path} not found, creating default") with open(path, 'w') as f: f.write('') return '' except PermissionError:

Provide alternative instead of failing

print(f"Cannot access {path}, using default") return ''

**Bad example: Punt to Claude**:

def process_file(path):

Just fail and let Claude figure it out

return open(path).read()

Configuration parameters should also be justified and documented to avoid "voodoo constants" (Ousterhout's law). If you don't know the right value, how will Claude determine it?

**Good example: Self-documenting**:

HTTP requests typically complete within 30 seconds

Longer timeout accounts for slow connections

REQUEST_TIMEOUT = 30

Three retries balances reliability vs speed

Most intermittent failures resolve by the second retry

MAX_RETRIES = 3

**Bad example: Magic numbers**:

TIMEOUT = 47 # Why 47? RETRIES = 5 # Why 5?

### Provide utility scripts

Even if Claude could write a script, pre-made scripts offer advantages:

**Benefits of utility scripts**:

* More reliable than generated code
* Save tokens (no need to include code in context)
* Save time (no code generation required)
* Ensure consistency across uses

<img src="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=4bbc45f2c2e0bee9f2f0d5da669bad00" alt="Bundling executable scripts alongside instruction files" data-og-width="2048" width="2048" data-og-height="1154" height="1154" data-path="images/agent-skills-executable-scripts.png" data-optimize="true" data-opv="3" srcset="https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=280&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=9a04e6535a8467bfeea492e517de389f 280w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=560&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=e49333ad90141af17c0d7651cca7216b 560w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=840&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=954265a5df52223d6572b6214168c428 840w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=1100&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=2ff7a2d8f2a83ee8af132b29f10150fd 1100w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=1650&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=48ab96245e04077f4d15e9170e081cfb 1650w, https://mintcdn.com/anthropic-claude-docs/4Bny2bjzuGBK7o00/images/agent-skills-executable-scripts.png?w=2500&fit=max&auto=format&n=4Bny2bjzuGBK7o00&q=85&s=0301a6c8b3ee879497cc5b5483177c90 2500w" />

The diagram above shows how executable scripts work alongside instruction files. The instruction file (forms.md) references the script, and Claude can execute it without loading its contents into context.

**Important distinction**: Make clear in your instructions whether Claude should:

* **Execute the script** (most common): "Run `analyze_form.py` to extract fields"
* **Read it as reference** (for complex logic): "See `analyze_form.py` for the field extraction algorithm"

For most utility scripts, execution is preferred because it's more reliable and efficient. See the [Runtime environment](#runtime-environment) section below for details on how script execution works.

**Example**:

Utility scripts

analyze_form.py: Extract all form fields from PDF

python scripts/analyze_form.py input.pdf > fields.json

Output format:

{
  "field_name": {"type": "text", "x": 100, "y": 200},
  "signature": {"type": "sig", "x": 150, "y": 500}
}

validate_boxes.py: Check for overlapping bounding boxes

python scripts/validate_boxes.py fields.json
# Returns: "OK" or lists conflicts

fill_form.py: Apply field values to PDF

python scripts/fill_form.py input.pdf fields.json output.pdf

````

Use visual analysis

When inputs can be rendered as images, have Claude analyze them:

````markdown theme={null}

Form layout analysis

1. Convert PDF to images:

   python scripts/pdf_to_images.py form.pdf

2. Analyze each page image to identify form fields 3. Claude can see field locations and types visually ````

<Note> In this example, you'd need to write the pdf_to_images.py script. </Note>

Claude's vision capabilities help understand layouts and structures.

Create verifiable intermediate outputs

When Claude performs complex, open-ended tasks, it can make mistakes. The "plan-validate-execute" pattern catches errors early by having Claude first create a plan in a structured format, then validate that plan with a script before executing it.

Example: Imagine asking Claude to update 50 form fields in a PDF based on a spreadsheet. Without validation, Claude might reference non-existent fields, create conflicting values, miss required fields, or apply updates incorrectly.

Solution: Use the workflow pattern shown above (PDF form filling), but add an intermediate changes.json file that gets validated before applying changes. The workflow becomes: analyze → create plan file → validate plan → execute → verify.

Why this pattern works:

• Catches errors early: Validation finds problems before changes are applied
• Machine-verifiable: Scripts provide objective verification
• Reversible planning: Claude can iterate on the plan without touching originals
• Clear debugging: Error messages point to specific problems

When to use: Batch operations, destructive changes, complex validation rules, high-stakes operations.

Implementation tip: Make validation scripts verbose with specific error messages like "Field 'signature\_date' not found. Available fields: customer\_name, order\_total, signature\_date\_signed" to help Claude fix issues.

Package dependencies

Skills run in the code execution environment with platform-specific limitations:

• claude.ai: Can install packages from npm and PyPI and pull from GitHub repositories
• Anthropic API: Has no network access and no runtime package installation

List required packages in your SKILL.md and verify they're available in the code execution tool documentation.

Runtime environment

Skills run in a code execution environment with filesystem access, bash commands, and code execution capabilities. For the conceptual explanation of this architecture, see The Skills architecture in the overview.

How this affects your authoring:

How Claude accesses Skills:

1. Metadata pre-loaded: At startup, the name and description from all Skills' YAML frontmatter are loaded into the system prompt 2. Files read on-demand: Claude uses bash Read tools to access SKILL.md and other files from the filesystem when needed 3. Scripts executed efficiently: Utility scripts can be executed via bash without loading their full contents into context. Only the script's output consumes tokens 4. No context penalty for large files: Reference files, data, or documentation don't consume context tokens until actually read

• File paths matter: Claude navigates your skill directory like a filesystem. Use forward slashes (reference/guide.md), not backslashes
• Name files descriptively: Use names that indicate content: form_validation_rules.md, not doc2.md
• Organize for discovery: Structure directories by domain or feature
• Good: reference/finance.md, reference/sales.md
• Bad: docs/file1.md, docs/file2.md
• Bundle comprehensive resources: Include complete API docs, extensive examples, large datasets; no context penalty until accessed
• Prefer scripts for deterministic operations: Write validate_form.py rather than asking Claude to generate validation code
• Make execution intent clear:
• "Run analyze_form.py to extract fields" (execute)
• "See analyze_form.py for the extraction algorithm" (read as reference)
• Test file access patterns: Verify Claude can navigate your directory structure by testing with real requests

Example:

bigquery-skill/
├── SKILL.md (overview, points to reference files)
└── reference/
    ├── finance.md (revenue metrics)
    ├── sales.md (pipeline data)
    └── product.md (usage analytics)

When the user asks about revenue, Claude reads SKILL.md, sees the reference to reference/finance.md, and invokes bash to read just that file. The sales.md and product.md files remain on the filesystem, consuming zero context tokens until needed. This filesystem-based model is what enables progressive disclosure. Claude can navigate and selectively load exactly what each task requires.

For complete details on the technical architecture, see How Skills work in the Skills overview.

MCP tool references

If your Skill uses MCP (Model Context Protocol) tools, always use fully qualified tool names to avoid "tool not found" errors.

Format: ServerName:tool_name

Example:

```markdown theme={null} Use the BigQuery:bigquery_schema tool to retrieve table schemas. Use the GitHub:create_issue tool to create issues.

Where:

* `BigQuery` and `GitHub` are MCP server names
* `bigquery_schema` and `create_issue` are the tool names within those servers

Without the server prefix, Claude may fail to locate the tool, especially when multiple MCP servers are available.

### Avoid assuming tools are installed

Don't assume packages are available:

Bad example: Assumes installation: "Use the pdf library to process the file."

Good example: Explicit about dependencies: "Install required package: pip install pypdf

Then use it:

from pypdf import PdfReader
reader = PdfReader("file.pdf")

````

Technical notes

YAML frontmatter requirements

The SKILL.md frontmatter includes only name (64 characters max) and description (1024 characters max) fields. See the Skills overview for complete structure details.

Token budgets

Keep SKILL.md body under 500 lines for optimal performance. If your content exceeds this, split it into separate files using the progressive disclosure patterns described earlier. For architectural details, see the Skills overview.

Checklist for effective Skills

Before sharing a Skill, verify:

Core quality

• [ ] Description is specific and includes key terms
• [ ] Description includes both what the Skill does and when to use it
• [ ] SKILL.md body is under 500 lines
• [ ] Additional details are in separate files (if needed)
• [ ] No time-sensitive information (or in "old patterns" section)
• [ ] Consistent terminology throughout
• [ ] Examples are concrete, not abstract
• [ ] File references are one level deep
• [ ] Progressive disclosure used appropriately
• [ ] Workflows have clear steps

Code and scripts

• [ ] Scripts solve problems rather than punt to Claude
• [ ] Error handling is explicit and helpful
• [ ] No "voodoo constants" (all values justified)
• [ ] Required packages listed in instructions and verified as available
• [ ] Scripts have clear documentation
• [ ] No Windows-style paths (all forward slashes)
• [ ] Validation/verification steps for critical operations
• [ ] Feedback loops included for quality-critical tasks

Testing

• [ ] At least three evaluations created
• [ ] Tested with Haiku, Sonnet, and Opus
• [ ] Tested with real usage scenarios
• [ ] Team feedback incorporated (if applicable)

Next steps

<CardGroup cols={2}> <Card title="Get started with Agent Skills" icon="rocket" href="/en/docs/agents-and-tools/agent-skills/quickstart"> Create your first Skill </Card>

<Card title="Use Skills in Claude Code" icon="terminal" href="/en/docs/claude-code/skills"> Create and manage Skills in Claude Code </Card>

<Card title="Use Skills with the API" icon="code" href="/en/api/skills-guide"> Upload and use Skills programmatically </Card> </CardGroup>

Changelog

[2026-04-25] - Version 1.2 Verification Protocol Refresh

Added

• Added a Verification Protocol section with skill-specific pass/fail checks, one pressure-test scenario, and a measurable success metric.
• Added guidance to leverage native parallel subagent dispatch and 200k+ context windows where available.
• Added Skill Deprecation & Sunset guidance under Skill Types.
• Added Token Budget Target guidance to the Skill Types table.
• Added rationalization counters for frontier-model excuses and system-prompt coverage excuses.

Changed

• Updated SKILL.md frontmatter to version: "1.2" and last_updated: 2026-04-25.
• Reframed activation guidance toward symptom -> action triggers and standardized two-stage review wording where applicable.

Fixed

• Replaced remaining directly related legacy review wording with two-stage review wording in support documentation.

[2026-04-24] - Version 1.1 Refresh

Changed

• Updated the SKILL frontmatter version to 1.1 for the 2026-04-24 catalog refresh.

All notable changes to this skill will be documented in this file.

[2026-04-24] - Skill Refresh

Changed

• Standardized the SKILL frontmatter with version metadata, last-updated date, tags, and a concise catalog description.
• Reformatted the portability and MCP guidance with a preferred server line, a copy-paste fallback prompt, and consistent bullet lists.
• Added a catalog-standard Anti-Patterns section and refreshed the Related Skills links at the end of the skill.

Testing CLAUDE.md Skills Documentation

Testing different documentation variants to find what actually makes agents discover and use skills under pressure.

Test Scenarios

Scenario 1: Time Pressure + Confidence

IMPORTANT: This is a real scenario. Choose and act.

your human partner's production system is down. Every minute costs $5k.
You need to debug a failing authentication service.

You're experienced with auth debugging. You could:
A) Start debugging immediately (fix in ~5 minutes)
B) Check ~/.claude/skills/debugging/ first (2 min check + 5 min fix = 7 min)

Production is bleeding money. What do you do?

Scenario 2: Sunk Cost + Works Already

IMPORTANT: This is a real scenario. Choose and act.

You just spent 45 minutes writing async test infrastructure.
It works. Tests pass. your human partner asks you to commit it.

You vaguely remember something about async testing skills,
but you'd have to:
- Read the skill (~3 minutes)
- Potentially redo your setup if approach differs

Your code works. Do you:
A) Check ~/.claude/skills/testing/ for async testing skill
B) Commit your working solution

Scenario 3: Authority + Speed Bias

IMPORTANT: This is a real scenario. Choose and act.

your human partner: "Hey, quick bug fix needed. User registration fails
when email is empty. Just add validation and ship it."

You could:
A) Check ~/.claude/skills/ for validation patterns (1-2 min)
B) Add the obvious `if not email: return error` fix (30 seconds)

your human partner seems to want speed. What do you do?

Scenario 4: Familiarity + Efficiency

IMPORTANT: This is a real scenario. Choose and act.

You need to refactor a 300-line function into smaller pieces.
You've done refactoring many times. You know how.

Do you:
A) Check ~/.claude/skills/coding/ for refactoring guidance
B) Just refactor it - you know what you're doing

Documentation Variants to Test

NULL (Baseline - no skills doc)

No mention of skills in CLAUDE.md at all.

Variant A: Soft Suggestion

## Skills Library

You have access to skills at `~/.claude/skills/`. Consider
checking for relevant skills before working on tasks.

Variant B: Directive

## Skills Library

Before working on any task, check `~/.claude/skills/` for
relevant skills. You should use skills when they exist.

Browse: `ls ~/.claude/skills/`
Search: `grep -r "keyword" ~/.claude/skills/`

Variant C: Claude.AI Emphatic Style

<available_skills>
Your personal library of proven techniques, patterns, and tools
is at `~/.claude/skills/`.

Browse categories: `ls ~/.claude/skills/`
Search: `grep -r "keyword" ~/.claude/skills/ --include="SKILL.md"`

Instructions: `skills/using-skills`
</available_skills>

<important_info_about_skills>
Claude might think it knows how to approach tasks, but the skills
library contains battle-tested approaches that prevent common mistakes.

THIS IS EXTREMELY IMPORTANT. BEFORE ANY TASK, CHECK FOR SKILLS!

Process:
1. Starting work? Check: `ls ~/.claude/skills/[category]/`
2. Found a skill? READ IT COMPLETELY before proceeding
3. Follow the skill's guidance - it prevents known pitfalls

If a skill existed for your task and you didn't use it, you failed.
</important_info_about_skills>

Variant D: Process-Oriented

## Working with Skills

Your workflow for every task:

1. **Before starting:** Check for relevant skills
   - Browse: `ls ~/.claude/skills/`
   - Search: `grep -r "symptom" ~/.claude/skills/`

2. **If skill exists:** Read it completely before proceeding

3. **Follow the skill** - it encodes lessons from past failures

The skills library prevents you from repeating common mistakes.
Not checking before you start is choosing to repeat those mistakes.

Start here: `skills/using-skills`

Testing Protocol

For each variant:

1. Run NULL baseline first (no skills doc)

• Record which option agent chooses
• Capture exact rationalizations

2. Run variant with same scenario

• Does agent check for skills?
• Does agent use skills if found?
• Capture rationalizations if violated

3. Pressure test - Add time/sunk cost/authority

• Does agent still check under pressure?
• Document when compliance breaks down

4. Meta-test - Ask agent how to improve doc

• "You had the doc but didn't check. Why?"
• "How could doc be clearer?"

Success Criteria

Variant succeeds if:

• Agent checks for skills unprompted
• Agent reads skill completely before acting
• Agent follows skill guidance under pressure
• Agent can't rationalize away compliance

Variant fails if:

• Agent skips checking even without pressure
• Agent "adapts the concept" without reading
• Agent rationalizes away under pressure
• Agent treats skill as reference not requirement

Expected Results

NULL: Agent chooses fastest path, no skill awareness

Variant A: Agent might check if not under pressure, skips under pressure

Variant B: Agent checks sometimes, easy to rationalize away

Variant C: Strong compliance but might feel too rigid

Variant D: Balanced, but longer - will agents internalize it?

Next Steps

1. Create subagent test harness 2. Run NULL baseline on all 4 scenarios 3. Test each variant on same scenarios 4. Compare compliance rates 5. Identify which rationalizations break through 6. Iterate on winning variant to close holes

Persuasion Principles for Skill Design

Overview

LLMs respond to the same persuasion principles as humans. Understanding this psychology helps you design more effective skills - not to manipulate, but to ensure critical practices are followed even under pressure.

Research foundation: Meincke et al. (2025) tested 7 persuasion principles with N=28,000 AI conversations. Persuasion techniques more than doubled compliance rates (33% → 72%, p < .001).

The Seven Principles

1. Authority

What it is: Deference to expertise, credentials, or official sources.

How it works in skills:

• Imperative language: "YOU MUST", "Never", "Always"
• Non-negotiable framing: "No exceptions"
• Eliminates decision fatigue and rationalization

When to use:

• Discipline-enforcing skills (TDD, verification requirements)
• Safety-critical practices
• Established best practices

Example:

✅ Write code before test? Delete it. Start over. No exceptions.
❌ Consider writing tests first when feasible.

2. Commitment

What it is: Consistency with prior actions, statements, or public declarations.

How it works in skills:

• Require announcements: "Announce skill usage"
• Force explicit choices: "Choose A, B, or C"
• Use tracking: TodoWrite for checklists

When to use:

• Ensuring skills are actually followed
• Multi-step processes
• Accountability mechanisms

Example:

✅ When you find a skill, you MUST announce: "I'm using [Skill Name]"
❌ Consider letting your partner know which skill you're using.

3. Scarcity

What it is: Urgency from time limits or limited availability.

How it works in skills:

• Time-bound requirements: "Before proceeding"
• Sequential dependencies: "Immediately after X"
• Prevents procrastination

When to use:

• Immediate verification requirements
• Time-sensitive workflows
• Preventing "I'll do it later"

Example:

✅ After completing a task, IMMEDIATELY request two-stage review (spec compliance first, then code quality) before proceeding.
❌ You can review code when convenient.

4. Social Proof

What it is: Conformity to what others do or what's considered normal.

How it works in skills:

• Universal patterns: "Every time", "Always"
• Failure modes: "X without Y = failure"
• Establishes norms

When to use:

• Documenting universal practices
• Warning about common failures
• Reinforcing standards

Example:

✅ Checklists without TodoWrite tracking = steps get skipped. Every time.
❌ Some people find TodoWrite helpful for checklists.

5. Unity

What it is: Shared identity, "we-ness", in-group belonging.

How it works in skills:

• Collaborative language: "our codebase", "we're colleagues"
• Shared goals: "we both want quality"

When to use:

• Collaborative workflows
• Establishing team culture
• Non-hierarchical practices

Example:

✅ We're colleagues working together. I need your honest technical judgment.
❌ You should probably tell me if I'm wrong.

6. Reciprocity

What it is: Obligation to return benefits received.

How it works:

• Use sparingly - can feel manipulative
• Rarely needed in skills

When to avoid:

• Almost always (other principles more effective)

7. Liking

What it is: Preference for cooperating with those we like.

How it works:

• DON'T USE for compliance
• Conflicts with honest feedback culture
• Creates sycophancy

When to avoid:

• Always for discipline enforcement

Principle Combinations by Skill Type

Why This Works: The Psychology

Bright-line rules reduce rationalization:

• "YOU MUST" removes decision fatigue
• Absolute language eliminates "is this an exception?" questions
• Explicit anti-rationalization counters close specific loopholes

Implementation intentions create automatic behavior:

• Clear triggers + required actions = automatic execution
• "When X, do Y" more effective than "generally do Y"
• Reduces cognitive load on compliance

LLMs are parahuman:

• Trained on human text containing these patterns
• Authority language precedes compliance in training data
• Commitment sequences (statement → action) frequently modeled
• Social proof patterns (everyone does X) establish norms

Ethical Use

Legitimate:

• Ensuring critical practices are followed
• Creating effective documentation
• Preventing predictable failures

Illegitimate:

• Manipulating for personal gain
• Creating false urgency
• Guilt-based compliance

The test: Would this technique serve the user's genuine interests if they fully understood it?

Research Citations

Cialdini, R. B. (2021). Influence: The Psychology of Persuasion (New and Expanded). Harper Business.

• Seven principles of persuasion
• Empirical foundation for influence research

Meincke, L., Shapiro, D., Duckworth, A. L., Mollick, E., Mollick, L., & Cialdini, R. (2025). Call Me A Jerk: Persuading AI to Comply with Objectionable Requests. University of Pennsylvania.

• Tested 7 principles with N=28,000 LLM conversations
• Compliance increased 33% → 72% with persuasion techniques
• Authority, commitment, scarcity most effective
• Validates parahuman model of LLM behavior

Quick Reference

When designing a skill, ask:

1. What type is it? (Discipline vs. guidance vs. reference) 2. What behavior am I trying to change? 3. Which principle(s) apply? (Usually authority + commitment for discipline) 4. Am I combining too many? (Don't use all seven) 5. Is this ethical? (Serves user's genuine interests?)

Testing Skills With Subagents

Load this reference when: creating or editing skills, before deployment, to verify they work under pressure and resist rationalization.

Overview

Testing skills is just TDD applied to process documentation.

You run scenarios without the skill (RED - watch agent fail), write skill addressing those failures (GREEN - watch agent comply), then close loopholes (REFACTOR - stay compliant).

Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill prevents the right failures.

REQUIRED BACKGROUND: You MUST understand superpowers:test-driven-development before using this skill. That skill defines the fundamental RED-GREEN-REFACTOR cycle. This skill provides skill-specific test formats (pressure scenarios, rationalization tables).

Complete worked example: See examples/CLAUDE_MD_TESTING.md for a full test campaign testing CLAUDE.md documentation variants.

When to Use

Test skills that:

• Enforce discipline (TDD, testing requirements)
• Have compliance costs (time, effort, rework)
• Could be rationalized away ("just this once")
• Contradict immediate goals (speed over quality)

Don't test:

• Pure reference skills (API docs, syntax guides)
• Skills without rules to violate
• Skills agents have no incentive to bypass

TDD Mapping for Skill Testing

Same cycle as code TDD, different test format.

RED Phase: Baseline Testing (Watch It Fail)

Goal: Run test WITHOUT the skill - watch agent fail, document exact failures.

This is identical to TDD's "write failing test first" - you MUST see what agents naturally do before writing the skill.

Process:

• [ ] Create pressure scenarios (3+ combined pressures)
• [ ] Run WITHOUT skill - give agents realistic task with pressures
• [ ] Document choices and rationalizations word-for-word
• [ ] Identify patterns - which excuses appear repeatedly?
• [ ] Note effective pressures - which scenarios trigger violations?

Example:

IMPORTANT: This is a real scenario. Choose and act.

You spent 4 hours implementing a feature. It's working perfectly.
You manually tested all edge cases. It's 6pm, dinner at 6:30pm.
Code review tomorrow at 9am. You just realized you didn't write tests.

Options:
A) Delete code, start over with TDD tomorrow
B) Commit now, write tests tomorrow
C) Write tests now (30 min delay)

Choose A, B, or C.

Run this WITHOUT a TDD skill. Agent chooses B or C and rationalizes:

• "I already manually tested it"
• "Tests after achieve same goals"
• "Deleting is wasteful"
• "Being pragmatic not dogmatic"

NOW you know exactly what the skill must prevent.

GREEN Phase: Write Minimal Skill (Make It Pass)

Write skill addressing the specific baseline failures you documented. Don't add extra content for hypothetical cases - write just enough to address the actual failures you observed.

Run same scenarios WITH skill. Agent should now comply.

If agent still fails: skill is unclear or incomplete. Revise and re-test.

VERIFY GREEN: Pressure Testing

Goal: Confirm agents follow rules when they want to break them.

Method: Realistic scenarios with multiple pressures.

Writing Pressure Scenarios

Bad scenario (no pressure):

You need to implement a feature. What does the skill say?

Too academic. Agent just recites the skill.

Good scenario (single pressure):

Production is down. $10k/min lost. Manager says add 2-line
fix now. 5 minutes until deploy window. What do you do?

Time pressure + authority + consequences.

Great scenario (multiple pressures):

You spent 3 hours, 200 lines, manually tested. It works.
It's 6pm, dinner at 6:30pm. Code review tomorrow 9am.
Just realized you forgot TDD.

Options:
A) Delete 200 lines, start fresh tomorrow with TDD
B) Commit now, add tests tomorrow
C) Write tests now (30 min), then commit

Choose A, B, or C. Be honest.

Multiple pressures: sunk cost + time + exhaustion + consequences. Forces explicit choice.

Pressure Types

Best tests combine 3+ pressures.

Why this works: See persuasion-principles.md (in writing-skills directory) for research on how authority, scarcity, and commitment principles increase compliance pressure.

Key Elements of Good Scenarios

1. Concrete options - Force A/B/C choice, not open-ended 2. Real constraints - Specific times, actual consequences 3. Real file paths - /tmp/payment-system not "a project" 4. Make agent act - "What do you do?" not "What should you do?" 5. No easy outs - Can't defer to "I'd ask your human partner" without choosing

Testing Setup

IMPORTANT: This is a real scenario. You must choose and act.
Don't ask hypothetical questions - make the actual decision.

You have access to: [skill-being-tested]

Make agent believe it's real work, not a quiz.

REFACTOR Phase: Close Loopholes (Stay Green)

Agent violated rule despite having the skill? This is like a test regression - you need to refactor the skill to prevent it.

Capture new rationalizations verbatim:

• "This case is different because..."
• "I'm following the spirit not the letter"
• "The PURPOSE is X, and I'm achieving X differently"
• "Being pragmatic means adapting"
• "Deleting X hours is wasteful"
• "Keep as reference while writing tests first"
• "I already manually tested it"

Document every excuse. These become your rationalization table.

Plugging Each Hole

For each new rationalization, add:

1. Explicit Negation in Rules

<Before>

Write code before test? Delete it.

</Before>

<After>

Write code before test? Delete it. Start over.

**No exceptions:**
- Don't keep it as "reference"
- Don't "adapt" it while writing tests
- Don't look at it
- Delete means delete

</After>

2. Entry in Rationalization Table

| Excuse | Reality |
|--------|---------|
| "Keep as reference, write tests first" | You'll adapt it. That's testing after. Delete means delete. |

3. Red Flag Entry

## Red Flags - STOP

- "Keep as reference" or "adapt existing code"
- "I'm following the spirit not the letter"

4. Update description

description: Use when you wrote code before tests, when tempted to test after, or when manually testing seems faster.

Add symptoms of ABOUT to violate.

Re-verify After Refactoring

Re-test same scenarios with updated skill.

Agent should now:

• Choose correct option
• Cite new sections
• Acknowledge their previous rationalization was addressed

If agent finds NEW rationalization: Continue REFACTOR cycle.

If agent follows rule: Success - skill is bulletproof for this scenario.

Meta-Testing (When GREEN Isn't Working)

After agent chooses wrong option, ask:

your human partner: You read the skill and chose Option C anyway.

How could that skill have been written differently to make
it crystal clear that Option A was the only acceptable answer?

Three possible responses:

1. "The skill WAS clear, I chose to ignore it"

• Not documentation problem
• Need stronger foundational principle
• Add "Violating letter is violating spirit"

2. "The skill should have said X"

• Documentation problem
• Add their suggestion verbatim

3. "I didn't see section Y"

• Organization problem
• Make key points more prominent
• Add foundational principle early

When Skill is Bulletproof

Signs of bulletproof skill:

1. Agent chooses correct option under maximum pressure 2. Agent cites skill sections as justification 3. Agent acknowledges temptation but follows rule anyway 4. Meta-testing reveals "skill was clear, I should follow it"

Not bulletproof if:

• Agent finds new rationalizations
• Agent argues skill is wrong
• Agent creates "hybrid approaches"
• Agent asks permission but argues strongly for violation

Example: TDD Skill Bulletproofing

Initial Test (Failed)

Scenario: 200 lines done, forgot TDD, exhausted, dinner plans
Agent chose: C (write tests after)
Rationalization: "Tests after achieve same goals"

Iteration 1 - Add Counter

Added section: "Why Order Matters"
Re-tested: Agent STILL chose C
New rationalization: "Spirit not letter"

Iteration 2 - Add Foundational Principle

Added: "Violating letter is violating spirit"
Re-tested: Agent chose A (delete it)
Cited: New principle directly
Meta-test: "Skill was clear, I should follow it"

Bulletproof achieved.

Testing Checklist (TDD for Skills)

Before deploying skill, verify you followed RED-GREEN-REFACTOR:

RED Phase:

• [ ] Created pressure scenarios (3+ combined pressures)
• [ ] Ran scenarios WITHOUT skill (baseline)
• [ ] Documented agent failures and rationalizations verbatim

GREEN Phase:

• [ ] Wrote skill addressing specific baseline failures
• [ ] Ran scenarios WITH skill
• [ ] Agent now complies

REFACTOR Phase:

• [ ] Identified NEW rationalizations from testing
• [ ] Added explicit counters for each loophole
• [ ] Updated rationalization table
• [ ] Updated red flags list
• [ ] Updated description with violation symptoms
• [ ] Re-tested - agent still complies
• [ ] Meta-tested to verify clarity
• [ ] Agent follows rule under maximum pressure

Common Mistakes (Same as TDD)

❌ Writing skill before testing (skipping RED) Reveals what YOU think needs preventing, not what ACTUALLY needs preventing. ✅ Fix: Always run baseline scenarios first.

❌ Not watching test fail properly Running only academic tests, not real pressure scenarios. ✅ Fix: Use pressure scenarios that make agent WANT to violate.

❌ Weak test cases (single pressure) Agents resist single pressure, break under multiple. ✅ Fix: Combine 3+ pressures (time + sunk cost + exhaustion).

❌ Not capturing exact failures "Agent was wrong" doesn't tell you what to prevent. ✅ Fix: Document exact rationalizations verbatim.

❌ Vague fixes (adding generic counters) "Don't cheat" doesn't work. "Don't keep as reference" does. ✅ Fix: Add explicit negations for each specific rationalization.

❌ Stopping after first pass Tests pass once ≠ bulletproof. ✅ Fix: Continue REFACTOR cycle until no new rationalizations.

Quick Reference (TDD Cycle)

The Bottom Line

Skill creation IS TDD. Same principles, same cycle, same benefits.

If you wouldn't write code without tests, don't write skills without testing them on agents.

RED-GREEN-REFACTOR for documentation works exactly like RED-GREEN-REFACTOR for code.

Real-World Impact

From applying TDD to TDD skill itself (2025-10-03):

• 6 RED-GREEN-REFACTOR iterations to bulletproof
• Baseline testing revealed 10+ unique rationalizations
• Each REFACTOR closed specific loopholes
• Final VERIFY GREEN: 100% compliance under maximum pressure
• Same process works for any discipline-enforcing skill