
Prose Review
Check that added comments, docstrings, and changelog entries document the code rather...
Install
npx skills add pipecat-ai/pipecat --skill prose-review -g -a claude-code -y- Repository
- pipecat-ai/pipecat17k
- Category
- Git and review
- Updated
- 3d ago
- License
- BSD-2-Clause
- Context cost
- Lightabout 1,077 tokens
- Runs scripts
- No, instructions only
What it does
Check that added comments, docstrings, and changelog entries document the code rather than narrate the change that produced it
Review the prose this work adds, comments, docstrings, changelog entries, against
the "Writing for Future Readers" section of AGENTS.md, which is the authority.
This skill is the operational check.
The reader you are writing for has never seen this change. They open the file months from now and see only the code as it stands. Detail that feels important while making a change, what the code used to do, why an alternative was rejected, that the fix was verified, is invisible context to them, and often actively misleading.
Scope
| Argument | Diff to review |
|---|---|
staged | git diff --cached -U0 |
branch (default) | git diff $(git merge-base main HEAD) -U0 |
<path> | git diff $(git merge-base main HEAD) -U0 -- <path> |
The branch and <path> scopes diff against the merge base, so they cover
committed and uncommitted work, prose written moments ago still needs review.
Review added lines only (^\+): comments, docstrings, and any
changelog/*.md content. Untouched prose is out of scope. Read the surrounding
code for each hit, the judgment depends on what the code already shows.
The Test
For each added line, ask: does this describe the code as it now stands, or does it narrate the change that produced it?
Rewrite or delete anything that:
- Describes what the code used to do, or contrasts old behavior with new
- Argues the change is correct, or records that it was tested or verified
- Names an alternative that was considered and rejected
- Only restates what the adjacent code already shows
- Uses shorthand that made sense mid-task but won't to someone reading cold
Rationale survives only when its absence would puzzle a future reader, a constraint or non-obvious decision the code itself cannot express. Keep those, and prefer stating the constraint over recounting the discovery.

