Use when you have a spec or requirements for a multi-step task, before touching code.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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:** Plans live inside a work project. Determine the project slug from `$CLAUDE_PROJECT` when present; otherwise ask which project this plan belongs to. If working in an isolated worktree, it should have been created via the `using-git-worktrees` skill at execution time.
**Save plans to:** `~/stripe/work/projects/<slug>/YYYY-MM-DD-<feature-name>.md`
- (User preferences for plan location override this default)
Every plan file starts with:
```yaml
---
status: active
project: "[[projects/<slug>/project]]"
---
```
…
The line at the top of this page pins the label v1.0.1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_cqj67l6vjvo3intt
GET https://markdownregistry.com/api/v1/resolve?ref=sodiumjoe/dotfiles/writing-plans
GET https://markdownregistry.com/api/v1/blob/75745a1bc96fd6d7b56369aa35aec8bd14557e9511b7006053f34a9f5c0c4b80
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
sodiumjoe/dotfiles · home/.agents/skills/brainstorming/SKILL.md · You MUST use this before any creative work - creating features, building components, adding functionality, or modifying…
sodiumjoe/dotfiles · home/.agents/skills/dispatching-parallel-agents/SKILL.md · Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
sodiumjoe/dotfiles · home/.agents/skills/executing-plans/SKILL.md · Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose…
sodiumjoe/dotfiles · home/.agents/skills/finishing-a-development-branch/SKILL.md · Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
sodiumjoe/dotfiles · home/.agents/skills/neovim-review/SKILL.md · Use when the user invokes /neovim-review for a pull request or a local :Review session in Neovim.
sodiumjoe/dotfiles · home/.agents/skills/neovim/SKILL.md · Interact with a running neovim instance over RPC — open files, show diffs, execute Lua. Use when you need to open a…
sodiumjoe/dotfiles · home/.agents/skills/receiving-code-review/SKILL.md · Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or…
sodiumjoe/dotfiles · home/.agents/skills/requesting-code-review/SKILL.md · Use when completing tasks, implementing major features, or before merging to verify work meets requirements
sodiumjoe/dotfiles · home/.agents/skills/subagent-driven-development/SKILL.md · Use when executing implementation plans with independent tasks in the current session
sodiumjoe/dotfiles · home/.agents/skills/systematic-debugging/SKILL.md · Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
sodiumjoe/dotfiles · home/.agents/skills/test-driven-development/SKILL.md · Use when implementing any feature or bugfix, before writing implementation code
a5c-ai/babysitter · library/methodologies/superpowers/skills/writing-plans/SKILL.md · Use when you have a spec or requirements for a multi-step task, before touching code. Creates bite-sized TDD…
ganyuanran/aegis · skills/writing-plans/SKILL.md · Use when you have an approved spec or written requirements for a multi-step task that needs a durable plan document…
optima-cityu/llm4ad_next · docker/knowledge-parser/skills/writing-plans/SKILL.md · Use before a multi-step document restructuring task to map the source, preserve important relationships, and decide…
xu123-bob/baize · agent/skills/superpowers/5.1.0/skills/writing-plans/SKILL.md · Use when you have a spec or requirements for a multi-step task, before touching code
