Skill Creator
Install when you want to author or refine agent skills with concise procedural knowledge, bundled resources, and workflows that extend Claude-style agents.
Overview
Skill Creator is an agent skill most often used in Build (also Ship, Operate) that guides you through creating and updating effective modular skills with workflows, integrations, and bundled resources.
Install
npx skills add https://github.com/supabase/agent-skills --skill skill-creatorWhat is this skill?
- Frames skills as modular onboarding guides with workflows, integrations, domain expertise, and bundled scripts or refere
- Teaches a concise-context discipline—only add knowledge the model likely lacks
- Covers four capability layers: specialized workflows, tool integrations, domain expertise, and bundled resources
- Applicable when creating a new skill or updating an existing SKILL.md package
- Positions procedural knowledge as the bridge from general chat agent to specialized task agent
- Four documented capability layers: workflows, tool integrations, domain expertise, and bundled resources
Adoption & trust: 693 installs on skills.sh; 2.2k GitHub stars; 2/2 security scanners passed (skills.sh audits).
What problem does it solve?
You know agents can do more with procedural packages, but your SKILL.md drafts are bloated, unstructured, or missing the workflows and assets that make a skill trustworthy to invoke.
Who is it for?
Solo builders authoring their first custom skill, tightening a community skill fork, or standardizing how your indie team documents agent workflows in git.
Skip if: Builders who only need a one-off prompt with no reuse, or those looking for runtime MCP server setup rather than SKILL.md authoring guidance.
When should I use this skill?
Users want to create a new skill or update an existing skill that extends the agent with specialized knowledge, workflows, or tool integrations.
What do I get? / Deliverables
You leave with a tighter skill design—clear scope, concise instructions, and optional bundled resources—ready to commit and invoke from your agent without wasting context on redundant explanation.
- Structured SKILL.md draft or revision plan
- Concise workflow and reference outline for the new skill
- Checklist of bundled scripts or assets to add
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build because new skills are created while assembling agent capabilities, though teams also revise skills during Ship review and Operate iteration. Agent-tooling is the right primary subphase: skill packages are modular extensions to the agent itself, not one-off app features.
Where it fits
Draft a SKILL.md that encodes your SaaS billing edge cases so the agent stops hallucinating Stripe flows.
Turn your repeatable PR review checklist into a concise checker skill before launch week.
Trim an overgrown internal skill after users complain it eats half the context window each invoke.
How it compares
Use as structured skill authoring guidance instead of dumping long system prompts into every chat session.
Common Questions / FAQ
Who is skill-creator for?
It is for indie and solo developers who extend Claude Code, Cursor, or Codex with reusable SKILL.md packages and want principled structure rather than ad-hoc prompt files.
When should I use skill-creator?
Invoke during Build when adding agent-tooling, during Ship when documenting review or release rituals as skills, and during Operate when iterating skills after production feedback.
Is skill-creator safe to install?
Review the Security Audits panel on this Prism page for ingest-time signals; the skill is instructional meta-content—verify bundled scripts and LICENSE.txt in the repo before running anything locally.
SKILL.md
READMESKILL.md - Skill Creator
# Skill Creator This skill provides guidance for creating effective skills. ## About Skills Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess. ### What Skills Provide 1. Specialized workflows - Multi-step procedures for specific domains 2. Tool integrations - Instructions for working with specific file formats or APIs 3. Domain expertise - Company-specific knowledge, schemas, business logic 4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks ## Core Principles ### Concise is Key The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request. **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?" and "Does this paragraph justify its token cost?" Prefer concise examples over verbose explanations. ### 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, or heuristics guide the approach. **Medium freedom (pseudocode or scripts with parameters)**: Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior. **Low freedom (specific scripts, few parameters)**: Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed. Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom). ### Anatomy of a Skill Every skill consists of a required SKILL.md file and optional bundled resources: ``` skill-name/ ├── SKILL.md (required) │ ├── YAML frontmatter metadata (required) │ │ ├── name: (required) │ │ └── description: (required) │ └── Markdown instructions (required) └── Bundled Resources (optional) ├── scripts/ - Executable code (Python/Bash/etc.) ├── references/ - Documentation intended to be loaded into context as needed └── assets/ - Files used in output (templates, icons, fonts, etc.) ``` #### SKILL.md (required) Every SKILL.md consists of: - **Frontmatter** (YAML): Contains `name` and `description` fields. These are the only fields that Claude reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used. - **Body** (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all). #### Bundled Resources (optional) ##### Scripts (`scripts/`) Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten. - **When to include**: When the same code is being rewritten repeatedly or deterministic reliability is needed - **Example**: `scripts/rotate_pdf.py` for PDF rotation tasks - **Benefits**: Token efficient, deterministic, may be executed without loading into context - **Note**: Scripts may still need to be read by Claude for patching or environment-specific adjustments ##### References (`references/`) Documentation and reference material inten