Skip to content

Writing Plans skill

Convert an approved design into reviewable engineering tasks with interfaces and verification.

Community · Jesse Vincent / Prime Radiant
AuthorJesse Vincent / Prime Radiant
LicenceMIT
Sourceobra/superpowers · SKILL.md on GitHub
Project websiteprimeradiant.com/superpowers
Works inClaude Code · Codex, Gemini CLI, Cursor, Copilot
Read from the source on

The writing-plans skill turns an approved specification into an implementation plan for an engineer with fresh context. It records exact paths, interfaces, constraints and verification commands.

The plan is a handoff artifact, not a completed implementation. Tasks are grouped by coherent work, with explicit inputs and outputs so separate builders can coordinate.

From the skill's SKILL.md: writing-plans

This is a community skill by Jesse Vincent / Prime Radiant, not checked by us or by Anthropic. Skills can tell the agent to run code, read files or call the network. Before installing, read its SKILL.md and every script in the folder, and look for anything that does not match what it says it does.

What it does

  1. Read the approved specification and inspect relevant code.
  2. Define global constraints, interfaces and reviewable tasks.
  3. Self-review the plan and agree how execution will proceed.

What you get

  • A plan under docs/superpowers/plans/YYYY-MM-DD-<feature>.md with task steps and verification.

When to use it

  • Hand a multi-step change to an engineer who has not read this conversation.

When not to use it

  • Requirements are still unsettled; use brainstorming first.

What it needs

  • An approved specification, a file-capable coding agent and access to the project.
  • Execution, testing and commits require the project’s own tools and permissions.

Files in the skill

File or folderWhat it is for
SKILL.mdPlan structure, task granularity and handoff requirements.

Licence as found in the repository on 2026-11-19: MIT.

Example prompts

Type one of these after installing; naming the skill makes sure it is used.

  • Turn this approved design into a plan with explicit interfaces and verification commands.
  • Review whether these tasks are coherent changes rather than one task per file.
  • Plan this migration for a fresh engineer and state the global constraints.

How to install writing-plans

Installation and permissions

The complete Superpowers plugin preserves links to brainstorming and execution skills. The planning folder itself contains only its SKILL.md.

The source includes test-first steps and commits in task plans. Adapt execution to your repository rules; creating a plan does not run those steps.

A skill is a folder with a SKILL.md file. You install it once; the agent reads its short description at the start of each session and loads the full instructions only when a request matches. Pick the place you use:

Claude Code: from the plugin marketplace

  1. Start Claude Code in a terminal with claude.
  2. This plugin is in Anthropic's official marketplace, which Claude Code adds for you the first time you start it.
  3. Install the plugin. Claude Code opens its details first: check what it will add (skills, hooks, MCP servers), then choose whether it is for you, for everyone on this repository, or for you in this repository only.
    /plugin install superpowers@claude-plugins-official
  4. Type / and look for /superpowers:writing-plans, or simply ask for the task.

From your shell instead of a session:

claude plugin install superpowers@claude-plugins-official

Claude Code: copy the folder into your skills folder

Put the skill's folder in ~/.claude/skills/ to use it in every project on this computer, or in .claude/skills/ inside a repository to share it with everyone who works there (commit it).

git clone --depth 1 https://github.com/obra/superpowers.git
mkdir -p ~/.claude/skills
cp -R superpowers/skills/writing-plans ~/.claude/skills/

Claude Code notices new or changed skills in these folders during the session. If the skills folder did not exist when the session started, run /reload-skills once. Then type /writing-plans or just describe the task.

On Windows, run the commands in Git Bash or WSL, or copy the folder into the same place with File Explorer.

Codex, Gemini CLI, Cursor and GitHub Copilot

These agents read the same SKILL.md folders. The one folder all four accept inside a project is .agents/skills/, so this copies the skill there:

git clone --depth 1 https://github.com/obra/superpowers.git
mkdir -p .agents/skills
cp -R superpowers/skills/writing-plans .agents/skills/
AgentProject folderYour user folderNotes
OpenAI Codex
.agents/skills/
~/.agents/skills/
Type $ or run /skills to pick a skill; Codex also chooses one when your task matches.
Gemini CLI
.agents/skills/
.gemini/skills/
~/.agents/skills/
~/.gemini/skills/
Or install from Git with gemini skills install <git URL> --path <folder> --consent. Google replaced Gemini CLI with Antigravity CLI for free-tier and Google One users on 18 June 2026; Antigravity uses .agents/skills/ in a project and ~/.gemini/config/skills/ for you.
Cursor
.agents/skills/
.cursor/skills/
~/.agents/skills/
~/.cursor/skills/
Type / in Agent chat to pick a skill. Cursor also reads Claude Code's .claude/skills/ folders.
GitHub Copilot
.github/skills/
.agents/skills/
.claude/skills/
~/.copilot/skills/
~/.agents/skills/
Works in Copilot CLI, the cloud agent, and agent mode in VS Code, Visual Studio and JetBrains (IDE support depends on the version). Or run gh skill install OWNER/REPOSITORY SKILL (public preview, GitHub CLI 2.90.0 or later).
Only install skills you trust. Anthropic's advice is to use skills only from trusted sources, and to read every file of any other skill before using it: a skill can direct the agent to run commands, read files or send data in ways its description does not mention.

Sources for these steps

Checked against each vendor's documentation on 2026-11-14:

A plan that survives context changes

Global constraints apply across tasks; task interfaces identify what each step consumes and produces. This reduces hidden assumptions during handoff.

Review the plan before execution. A detailed command is still a proposal until it is run and its result checked.

Questions about writing-plans

Does it run the plan?

No. It writes and reviews the plan, then hands execution to an agreed method.

What context should a task contain?

Exact paths, interfaces, relevant constraints, implementation steps and concrete verification commands.

Is each file a separate task?

No. Tasks should be coherent, reviewable changes; file boundaries alone are not enough.

Does it need a paid service?

No separate service is specified by the skill. Your agent subscription or API usage may still cost money.

More AI skills

Related skills

Skill categories