task-pr-review-judgment — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited task-pr-review-judgment (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Main agent judges PR review without reading operations skills (skills/operations-on-pr-review/SKILL.md, skills/operations-on-merge/SKILL.md, etc.) directly. Judgment basis = issue body + PR diff + CI result.
if execution_mode == auto: Self-review (after CI pass): Main agent reviews PR diff against issue requirements. Subagent-created PR = separate perspective verification. Especially valuable. Self-created PR = diff re-check before merge. pass → proceed to merge. fail → fix and recommit (restart CI loop).
if execution_mode == trigger: External review judgment: APPROVED → proceed (delegate merge execution to subagent if available). CHANGES_REQUESTED → read review comments, judge against issue requirements, delegate fix to subagent.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.