Install any skill in seconds. Free to start, no credit card required.
Get Started Free →wasabeef/revue-systématique-de-pr
Revue systématique de PR. Se déclenche avec « réviser cette PR », « code review ».
Passed 20 of 22 test cases with the skill, and 9 of 22 without it.
and 13 more in the full report
11 fixed9 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
A pull request contains minor typos in comment text and inconsistent trailing whitespace across a few utility functions. Which severity tag prefix should be assigned to these findings?
| Checked | Without skill | With skill |
|---|---|---|
| Tags minor style or typo feedback with low.nits. | Missed | Passed |
The instructions your model reads when the skill loads.
Assure la qualité du code et la solidité architecturale grâce à des revues systématiques de Pull Requests.
# Revue complète de PR
gh pr view 123 --comments
"Systematically review this PR and provide feedback from code quality, security, and architecture perspectives"
# Revue axée sur la sécurité
gh pr diff 123
"Focus on reviewing security risks and vulnerabilities"
# Revue de perspective architecturale
gh pr checkout 123 && find . -name "*.js" | head -10
"Evaluate the architecture from the perspectives of layer separation, dependencies, and SOLID principles"
# Évaluation quantitative de la qualité du code
find . -name "*.js" -exec wc -l {} + | sort -rn | head -5
"Evaluate code complexity, function size, and duplication, and point out improvements"
# Vérification des vulnérabilités de sécurité
grep -r "password\|secret\|token" . --include="*.js" | head -10
"Check for risks of sensitive information leakage, hardcoding, and authentication bypass"
# Détection de violations architecturales
grep -r "import.*from.*\.\./\.\." . --include="*.js"
"Evaluate layer violations, circular dependencies, and coupling issues"
🔴 critical.must : Questions critiques
test cases passed, vs 9 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.