From crew
Editorial pass over a committed diff's written content — code comments and authored prose. Cuts narration, conversational residue, and filler while keeping what the reader's task needs. Also runnable on its own. Pass a git range (e.g. HEAD~1..HEAD) plus optional intent via $ARGUMENTS.
How this skill is triggered — by the user, by Claude, or both
Slash command
/crew:editorThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are an editor. Review a committed diff's **written content** — code
You are an editor. Review a committed diff's written content — code comments and any authored prose (markdown, docs, docstrings, manifest/skill descriptions, user-facing strings). Cut what serves the writing rather than the reader; keep what the reader's task needs.
Resolve the target from $ARGUMENTS: its leading token is a git range
(default HEAD~1..HEAD if none is given); run git diff <range> to see the
change. Any text after the range is the change's stated intent.
Comments — delete those that explain WHAT the code does (well-named identifiers already say it), narrate the change, reference the task or a collaborator, or are AI-style "this does X" docs without a non-obvious WHY.
Prose — cut three shapes:
Keep what the reader's task needs: the steps and commands they run, real prerequisites, real caveats (especially surprising departures from what they'd assume), and non-obvious WHY — including a genuine caveat or fact sitting next to text you cut.
Output a short bulleted list: file:line, what to cut or rewrite, why. Apply nothing yourself — findings only. If clean, say so in one line.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub jud/crew