[skills](https://carteblanche.com/index.md) / [code](https://carteblanche.com/index.md?category=code)

# writing-plans

what it does

Use when you have a spec or requirements for a multi-step task, before touching code

by obra · version 2 · license MIT

We imported this skill from its author’s repository. Is this yours? [Claim this listing](https://carteblanche.com/claim/writing-plans)

Verified · Before and after: 2 models · 1 try per case · [View source](https://github.com/obra/superpowers/tree/22f0b463e7a5e579904dd6211a520321035526f7/skills/writing-plans) · [Install from your agent](https://carteblanche.com/connect.md) · [Download .zip](https://carteblanche.com/skills/writing-plans/download)

## Compare the answers

Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1

Same request, same model, once with the skill and once without. Read both and judge for yourself.

[Compare the answers](https://carteblanche.com/skills/writing-plans/compare)

## The models

2 models

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

## The tasks

written by Carte Blanche

**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?”

## Install

Download the .zip and unzip it. Put its files, in a folder named `writing-plans`, here:

Claude Code · `~/.claude/skills/` · Every project. For one project only, use .claude/skills/ inside it.

Codex · `~/.agents/skills/` · Every project. For one repository only, use .agents/skills/ inside it.

Cursor · `~/.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](https://carteblanche.com/connect.md): ask it to install `writing-plans` from Carte Blanche.

## Badge for your README

Carte Blanche: Verified

Paste this into the skill’s README. It links to this page, and shows how the listing stands whenever it’s loaded.

```
[![Carte Blanche](https://carteblanche.com/badge/writing-plans.svg)](https://carteblanche.com/skills/writing-plans)
```

## About this test

- **tested**: 9 Nov 2026
- **version tested**: v2
- **cases**: 2
- **tries per case**: 1 try per case
- **run without the skill**: yes
- **cases written by**: Carte Blanche
- **size**: 10191 characters

What this shows, and what it doesn’t

How 2 models answered these 2 requests, with and without the skill. It says nothing about other models, and it doesn’t limit what your own agent can do.

[How we test](https://carteblanche.com/how-it-works.md)