At a glance
- Best for
- Assign responsibilities to files and tasks
- Works with
- Requirements or design documents · Project file structure and constraints
- Outcome
- An actionable, reviewable implementation plan · Task interfaces, tests, and acceptance criteria
- Source
- obra/superpowers
01 / Understand the skill
About writing-plans
Map designs and requirements to implementation tasks with files, interfaces, tests, and acceptance criteria. Check coverage and consistency before handing off to the user's chosen execution workflow. Takes requirement documents and project structure and produces task dependencies, interfaces, tests, and acceptance checklists, so implementers need not guess at omitted decisions.
Requirements
- Confirmed requirements or a design document
- The complete companion Superpowers workflow
- Use subagent-driven-development or executing-plans for the selected execution approach; use using-git-worktrees when worktrees are needed
Inputs
- Requirements or design documents
- Project file structure and constraints
Outputs
- An actionable, reviewable implementation plan
- Task interfaces, tests, and acceptance criteria
02 / Confirm the fit
Use writing-plans when you need to
- Assign responsibilities to files and tasks
- Make interfaces and test conditions explicit
- Check requirement coverage and review the plan
03 / See the workflow
How writing-plans works
- 01Read confirmed requirements and divide responsibilities
- 02Document task dependencies and verification conditions
- 03Review the plan and hand off to the selected execution workflow
Check before installing
Compatible platforms
Cursor · GitHub Copilot · OpenAI Codex · Claude Code
Best fit
Assign responsibilities to files and tasks
Review the source instructions if the required output differs from the formats described above.
Install and use
Compatible with Cursor and GitHub Copilot and OpenAI Codex and Claude Code · Published by obra
Ready to add writing-plans?
Use the published instructions below, then provide the required input and describe the result you need.
General instructions · Cursor · GitHub Copilot · OpenAI Codex · Claude Code
/plugin install superpowers@claude-plugins-official Install the complete Claude Code plugin as described in the upstream README. For other hosts, follow their dedicated installation sections in the same README.
Review the source repository and license before installing third-party skills.
Continue exploring
Similar skills
Authoritative reference for the Claude API and Anthropic SDKs: model IDs, pricing, thinking/effort params, streaming, tool use, caching, managed agents, and model migration.
Read, edit, create, and fix Excel/CSV files — formulas, formatting, charts, and clean financial models with zero formula errors.
Generate distinctive, production-grade frontend UI that avoids generic AI aesthetics — pages, components, dashboards, and landing pages.
Build high-quality MCP (Model Context Protocol) servers in Python (FastMCP) or Node/TypeScript that let LLMs use external services through well-designed tools.