MiniMax-AI/mcode-stack / stacks/jiachen/skills/pr-review-tuning
pr-review-tuning
VerifiedThe weekly self-tuning loop for the MCode Review bot on GitHub or GitLab. Measures the bot on a repository's recent PRs (threads per PR, which kinds people answer or dismiss, what was unanswered at merge, cost per round, time to merge, follow-up fixes), finds noise and misses, proposes at most three rule changes with their expected effect on each goal, backtests them on past PRs with known outcomes within an agreed token budget, has an independent check recompute the numbers, and changes rules only after a person approves. The first run only measures. Use for requests to run pr-review-tuning or to measure or tune the review bot, for the weekly scheduled run, and for settling a proposal (approve or reject P1).
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 247 B |
| SKILL.md | skill md | 10.6 KB |
| references/backtest.md | markdown | 4.4 KB |
| references/metrics.md | markdown | 9.5 KB |
| references/proposals.md | markdown | 3.5 KB |
| references/report-template.md | markdown | 2.2 KB |
| references/scheduling.md | markdown | 7.0 KB |
| scripts/backtest.mjs | script | 16.0 KB |
| scripts/collect.mjs | script | 13.2 KB |
| scripts/lib/common.mjs | script | 5.6 KB |
| scripts/lib/guard.mjs | script | 1.2 KB |
| scripts/metrics.mjs | script | 33.8 KB |
| scripts/test/backtest.test.mjs | script | 8.4 KB |
| scripts/test/collect.test.mjs | script | 11.4 KB |
| scripts/test/fixtures/backtest/fake-review.mjs | script | 2.8 KB |
| scripts/test/fixtures/metrics/previous-metrics.json | config | 333 B |
| scripts/test/fixtures/metrics/prs.jsonl | other | 10.4 KB |
| scripts/test/metrics.test.mjs | script | 12.7 KB |
references/report-template.md
View on GitHub# Weekly report template
Write `report.md` in the user's language, conclusion first. Every number comes from `metrics.json` or from a judgment recorded in `data/judgments.json`. Keep verified, inferred and unverified claims apart. Leave out a section that has nothing to say, except Conclusion, Headline and Verification.
```markdown
# <week> MCode Review tuning: <project>
Window: <since> to <until>, <time zone>. <First run: measure only. | Proposals wait for a decision.>
## Conclusion
<Two to five sentences: what moved since last week, the largest source of noise, the most costly miss, and what you recommend.>
## Headline
<The headline table of metrics.md: metric, this week, last week, change, direction.>
## Last week's changes
<For each change merged since the last report: what its proposal predicted and what the numbers show.>
## Noise
<Groups, question kinds and PRs that produce threads nobody uses, with numbers and two or three example threads. The agreement of the outcome classifier with your own judgment on the sample.>
## Misses
<Follow-up pairs by judgment: missed, ignored, not visible in review, unrelated. Every miss: the PR, the fix, and what the review should have seen.>
## Speed and cost
<Rounds per PR, tokens per round by tier, time to merge.>
## Maintainability
<Maintainability and duplication threads fixed against deferred; the deferred backlog.>
## Author quiz
<Answer rate, when the quiz is on.>
## Proposals
<Numbered: the change, the measured problem, the expected effect on each goal, the risk, how next week shows it, other tools, the backtest, the file. A table of options where there is a choice, with your recommendation. On the first run: the candidate problems for next week, ranked.>
## Verification
<From verify.md: which numbers were recomputed and how, which judgments were re-judged, the agreement, and what was fixed or taken out.>
## Verified, inferred, not verified
- Verified: <counted by a script and recomputed independently>
- Inferred: <estimates, replays, judgments>
- Not verified: <claims nobody checked, such as "fixed" in a reply>
## Open items from last week
## Files
<Paths of the data, the proposals, the backtest output and verify.md.>
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |