writing-plans
what it does
Use when you have a spec or requirements for a multi-step task, before touching code
Same request, same model, once with the skill and once without. Read both and judge for yourself.
Claude Sonnet 5.5
made by Anthropic
claude-sonnet-5-5 · revision not reported by the provider
1 try per case · tested 9 Nov 2026
GPT-6.1 Sol
made by OpenAI
gpt-6.1-sol · revision not reported by the provider
1 try per case · tested 9 Nov 2026
example-1
“I need to add rate limiting to our Express API. Requirements: 100 requests per minute per API key, 429 response with a Retry-After header, limits stored in Redis, and a config flag to disable it in local dev. Admin routes are exempt. Please write an implementation plan before we touch any code, with ordered steps, files likely affected, and how we'll test each piece.”
example-2
“Here's the spec for migrating our user profile page from class components to React hooks: keep the existing behavior, split the 600-line ProfilePage into smaller components, move data fetching into a custom useProfile hook, and keep the Jest tests passing throughout. Can you break this into a step-by-step plan with small, safe commits before I start coding?”
Download the .zip and unzip it. Put its files, in a folder named writing-plans, here:
~/.claude/skills/Every project. For one project only, use .claude/skills/ inside it.~/.agents/skills/Every project. For one repository only, use .agents/skills/ inside it.~/.cursor/skills/Cursor also reads the Claude Code and Codex folders above.Then start a new session and ask for what the skill does. Other agents that read SKILL.md have their own skills folder; check their docs.
Or install from your agent: ask it to install writing-plans from Carte Blanche.