Writing Plans

What it does

The skill focuses on a plan another engineer could execute without needing the original conversation. It connects the requirement to files, responsibilities, steps and acceptance evidence. This can reveal missing decisions before implementation begins, particularly when storage, background jobs, user interfaces and deployment all participate in one feature.

Best for

A feature with several dependent stages, an unfamiliar repository, or a handoff where the next contributor needs enough context to make consistent decisions. It is most useful when a vague checklist would leave important questions about data flow, integration points or test expectations unanswered.

Tradeoffs and requirements

A detailed plan can become stale as new evidence arrives. Keep it close to the code and revise decisions that no longer match the implementation. Routine one-file edits rarely need the same planning overhead as a new subsystem. A plan also cannot establish that an integration works; its acceptance steps still have to be executed.

Unknown; inspect source requirements and supporting scripts.

Install from the source

Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.

npx skills add https://github.com/obra/superpowers/tree/2ce8aa15d05bd57213e6f746f953aafb7ded7a8b/skills/writing-plans --skill writing-plans

Review pinned skill folder ↗ · CLI documentation ↗

After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.

Safety & review signals

Static review only. This is not a security audit or a guarantee of safety.

SKILL.md text only; scripts, dependencies and runtime behavior not audited.

• Shell Or Package Install — review the source context.

Allowed tools declaration: Unknown. Runtime permissions and network behavior: Unknown.

AI Craft Pad Skill Score

88/100 · Metadata coverage 100% · Model 1.0

Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.

Documentation

100/100

100

Maintenance

100/100

100

License Clarity

100/100

100

Repository Health

100/100

100

Compatibility Evidence

80/100

80

Popularity

99/100

99

Originality

80/100

80

Static Safety

60/100

60

Suggested workflow

Start from the user's observable outcome, identify the participating components and dependencies, then break the change into reviewable steps. Attach an appropriate check to each important boundary and reserve public deployment verification for the final stage.

How to judge the result

Ask whether another contributor could identify what to change, why it belongs in scope, how to check it and what evidence is still required before calling the feature complete.