
Writing Plans
- 789 installs
- 44k repo stars
- Updated July 27, 2026
- sickn33/antigravity-awesome-skills
writing-plans is a productivity agent skill that turns a high-level spec into a complete, bite-sized, executable implementation plan an agent can follow without additional context for developers starting multi-step featu
About
writing-plans is a Productivity & Planning agent skill from sickn33/antigravity-awesome-skills that converts specs or requirements into comprehensive implementation plans before any code changes. The skill assumes the executing engineer has zero codebase context and documents every file to touch, code snippets, testing steps, docs to consult, and verification criteria as bite-sized tasks following DRY, YAGNI, TDD, and frequent commits. Developers reach for writing-plans when a multi-step feature needs a structured execution roadmap an agent or engineer can follow without follow-up questions. The skill is marked critical risk and triggers before touching code when requirements already exist. Plans break work into discrete commits-friendly tasks covering implementation, tests, and documentation checks so downstream agents execute sequentially with full context.
- Creates comprehensive implementation plans assuming zero codebase familiarity and questionable taste
- Enforces DRY, YAGNI, TDD, and frequent commits as core principles
- Delivers bite-sized tasks each scoped to one 2-5 minute action with explicit test-commit loops
- Every plan includes the required header directing the use of executing-plans sub-skill
- Saves standardized plans to docs/plans/YYYY-MM-DD-<feature-name>.md in a dedicated worktree
Writing Plans by the numbers
- 789 all-time installs (skills.sh)
- +33 installs in the week ending Jul 25, 2026 (Skillselion tracking)
- Ranked #575 of 3,301 Productivity & Planning skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill writing-plansAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 789 |
|---|---|
| repo stars | ★ 44k |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 27, 2026 |
| Repository | sickn33/antigravity-awesome-skills ↗ |
How do you turn a spec into an implementation plan?
Turn a high-level spec into a complete, bite-sized, executable implementation plan that an agent can follow without any additional context.
Who is it for?
Developers or agents starting a multi-step feature who have a written spec and need a self-contained, executable task plan before editing code.
Skip if: Single-line bug fixes or exploratory spikes where a formal multi-task implementation plan would add unnecessary overhead.
When should I use this skill?
A developer has a spec or requirements for a multi-step task and needs a detailed implementation plan before any code, test, or doc edits begin.
What you get
Bite-sized implementation plan with per-task file paths, code guidance, test steps, and commit checkpoints.
- implementation plan document
- per-task file and test checklist
By the numbers
- Skill risk level is marked critical in the manifest metadata
Files
Writing Plans
Overview
Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Context: This should be run in a dedicated worktree (created by brainstorming skill).
Save plans to: docs/plans/YYYY-MM-DD-<feature-name>.md
Bite-Sized Task Granularity
Each step is one action (2-5 minutes):
- "Write the failing test" - step
- "Run it to make sure it fails" - step
- "Implement the minimal code to make the test pass" - step
- "Run the tests and make sure they pass" - step
- "Commit" - step
Plan Document Header
Every plan MUST start with this header:
# [Feature Name] Implementation Plan
> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
**Goal:** [One sentence describing what this builds]
**Architecture:** [2-3 sentences about approach]
**Tech Stack:** [Key technologies/libraries]
---Task Structure
### Task N: [Component Name]
**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py`
**Step 1: Write the failing test**
def test_specific_behavior(): result = function(input) assert result == expected
**Step 2: Run test to verify it fails**
Run: `pytest tests/path/test.py::test_name -v`
Expected: FAIL with "function not defined"
**Step 3: Write minimal implementation**
def function(input): return expected
**Step 4: Run test to verify it passes**
Run: `pytest tests/path/test.py::test_name -v`
Expected: PASS
**Step 5: Commit**
git add tests/path/test.py src/path/file.py git commit -m "feat: add specific feature"
Remember
- Exact file paths always
- Complete code in plan (not "add validation")
- Exact commands with expected output
- Reference relevant skills with @ syntax
- DRY, YAGNI, TDD, frequent commits
Execution Handoff
After saving the plan, offer execution choice:
"Plan complete and saved to `docs/plans/<filename>.md`. Two execution options:
1. Subagent-Driven (this session) - I dispatch fresh subagent per task, review between tasks, fast iteration
2. Parallel Session (separate) - Open new session with executing-plans, batch execution with checkpoints
Which approach?"
If Subagent-Driven chosen:
- REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development
- Stay in this session
- Fresh subagent per task + code review
If Parallel Session chosen:
- Guide them to open new session in worktree
- REQUIRED SUB-SKILL: New session uses superpowers:executing-plans
When to Use
This skill is applicable to execute the workflow or actions described in the overview.
Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Related skills
How it compares
Pick writing-plans over ad-hoc task lists when a multi-step spec needs file-level detail, TDD steps, and commit-sized tasks for agent execution.
FAQ
When should writing-plans run in a workflow?
writing-plans should run when a developer has a spec or requirements for a multi-step task and needs a complete implementation plan before modifying any code, tests, or documentation.
What principles does writing-plans embed in each plan?
writing-plans instructs agents to follow DRY, YAGNI, TDD, and frequent commits while listing files, code, testing steps, and docs needed for each bite-sized task.
Does writing-plans assume familiarity with the codebase?
writing-plans explicitly assumes the executing engineer has zero context for the codebase and documents everything needed including file paths, tests, and verification criteria.
Is Writing Plans safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.