Skill Claude CodeCodex
Read PR review feedback, fix or reject each requested change, reply per thread, resolve every thread, and verify zero threads remain.
5 1mo ago A 30 tokens
original MIT
5Stars on the repository
27Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
fix-ci
02Skill Claude CodeCodex
Diagnose and fix a failing CI run for the current branch, then re-verify.
5 1mo ago A 21 tokens
original MIT
harness-eval
03Skill Claude CodeCodex
Evaluate THIS repository's agent harness — a deterministic structure audit (A1) plus content quality probes (A2), plus an isolated producer/judge dynamic eval (B) with paired sign-test A/B variant comparison.
5 1mo ago A 48 tokens
original MIT
log-gotcha
04Skill Claude CodeCodex
Record a newly-discovered gotcha to .agents/wiki/ BEFORE handoff — the harness's feedback loop. The wiki is how the next agent doesn't repeat your discovery.
5 1mo ago A 40 tokens
original MIT
Skill Claude CodeCodex
Never cast an approving review on a PR your own (shared) agent identity authored — approval must come from an independent reviewer.
5 1mo ago A 30 tokens
original MIT
Skill Claude CodeCodex
Rebase the PR branch onto the default branch, resolve conflicts keeping both intents, and verify mergeability before pushing.
5 1mo ago A 27 tokens
original MIT
self-verify
07Skill Claude CodeCodex
Run the project's own build/test/lint and converge before handing work to a reviewer. Requires explicit baseline → after evidence — the suite must be shown to change state, not just be "green at the end".
5 1mo ago A 46 tokens
original MIT
Skill Claude CodeCodex
Admission bar and structure for writing a new skill, so the skill library stays lean and discoverable.
5 1mo ago A 24 tokens
original MIT
Skill Claude CodeCodex
Turn a reviewer/judge failure into an instruction-surface change that passes a prevention test.
5 1mo ago A 23 tokens
original MIT
verify-loop
10Skill Claude CodeCodex
General wait → inspect → fix (max 3) → self-park loop for any post-action verification (build, tests, CI, visual, lint).
5 1mo ago A 35 tokens
original MIT