comment-sweep
comment-sweep is a Change & PR review skill for AI agents, published by wbrown in the janus-datalog repository on GitHub. Skillspace rates comment-sweep D (59/100) and it passed the safety scan; the rating is based on static analysis only.
Sweep a package, directory, or the whole tree for comments that do not describe the present code — comments written for someone reading a diff, comments that are flatly false about current behaviour, and comments several times longer than the fact they carry. Use it when clearing a backlog across many files, when a review turns up one of these and you suspect a cluster, or before publishing a repo. Covers what to remove, what is protected (regression specifications, bug-doc citations, expected-value derivations, external constraints), how to delete without leaving fragments, and how to partition the work across agents. The enforcement counterpart is failure mode 9 in .claude/hooks/review-edit.system.md; the two state one taxonomy and must be updated together.
- Grade
- D
- Quality
- 59 / 100
- Safety
- Passed
- GitHub stars
- 51
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 84 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.