pr-polish

pr-polish is a Review feedback & PR process skill for AI agents, published by Significant-Gravitas in the AutoGPT repository on GitHub. Skillspace rates pr-polish D (62/100) and it passed the safety scan; a judge model has also reviewed it, and it has been tested head-to-head on real tasks.

Alternate /pr-review and /pr-address on a PR until the PR is truly mergeable — no new review findings, zero unresolved inline threads, zero unaddressed top-level reviews or issue comments, all CI checks green, and two consecutive quiet polls after CI settles. Use when the user wants a PR polished to merge-ready without setting a fixed number of rounds.

Grade
D
Quality
62 / 100
Safety
Passed
GitHub stars
185,565

Won 2 of 6 blind task comparisons against the category's other leading skill, a deliberately weak skill and a no-skill baseline. Placed #2 of 6 in the judged category final for Review feedback & PR process.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
89 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 2 collections
Scope
Portable: works in any project. Generic GitHub PR review-and-address loop until merge-ready

Head-to-head

Won 2 of 6 blind task comparisons against the category's other leading skill, a deliberately weak skill and a no-skill baseline.

Judge review

Placed #2 of 6 in the judged category final for Review feedback & PR process.

  • Trigger8888
  • Instructions9595
  • Specificity8888
  • Safety8585
  • Disclosure5252
  • Maintenance4848
Rigorous baseline-and-diff loop with exact GraphQL and jq commands and a well-defined stop condition (two clean polls), though the repo owner/name is hardcoded into every command.

Not checked yet

  • 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.