code reviewby quran
Review PR(s)
quran/review
Reviews PR(s) using comprehensive review guidelines including security, correctness, clean code, TypeScript, React patterns, i18n/RTL, performance, and accessibility.
What it changes
Passed 4 of 14 test cases with the skill, and 2 of 14 without it.
Without skill17%
With skill29%
Checks it passed that the model alone missed
- Checks yarn test for unit test execution.
- Checks yarn lint for code linting verification.
- Checks yarn build for build success verification.
and 5 more in the full report
6 fixed1 passed either way14 still failing3 broke
- Pass-rate lift
- +13 pp
- Tokens
- +34%
- Agent turns
- 0%
- Response time
- -54%
Model gemini-3.6-flashMeasured 9/28/2026v17 of 24 cases passed with skill · 14 comparable
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptBefore analyzing any code diffs for pull request #2732, where should the detailed review criteria and guidelines be read from in the repository?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| References reading docs/REVIEW_PROMPT.md for the review guidelines. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md110 linessingle file
Review PR(s)
Review PR(s) using the comprehensive review guidelines.
Arguments
$ARGUMENTS can be:
- Single PR:
2732
- Multiple PRs:
2732 2700 2699 (space-separated)
- Multiple PRs:
2732,2700,2699 (comma-separated)
Steps
For Each PR
- Read the review prompt from
docs/REVIEW_PROMPT.md for all criteria
- Fetch PR details:
gh pr view {PR_NUMBER} --json title,body,files,additions,deletions,author
- Fetch PR diff:
gh pr diff {PR_NUMBER}
- If files changed > 15, flag for potential split before deep review
- Check for previous reviews (see Re-review Protocol below)
Re-review Protocol
Before reviewing, check if this PR has been previously reviewed:
-
Fetch previous reviews and comments:
gh pr view {PR_NUMBER} --json reviews,comments
-
If previous reviews exist:
- Summarize previous review status (APPROVED, CHANGES_REQUESTED, COMMENTED)
- List key issues raised in previous reviews
- Check commits since last review:
gh pr view {PR_NUMBER} --json commits
- Focus on:
- Whether previous feedback was addressed
- New changes introduced since last review
- Any regressions caused while fixing previous issues
Track record
Benchmark
4 / 14
test cases passed, vs 2 / 14 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v5 — 8/31/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedImported 8/31/2026Version v1