receiving-code-review
Skill0 starsChanged 28 days agoMITView on GitHub
Turns review feedback into per-item verdicts backed by evidence from the codebase, before any fix is written. Use when review comments are in hand — fetched from a pull request, pasted into the conversation, or left by an automated reviewer such as Copilot code review, CodeRabbit, or another agent — and before acting on any of them, including when asked to just apply them, and when a suggestion looks unclear, wrong, or larger than the problem it solves.
187 other projects use a version of this.
Adopted by
Most recently taken up by
- DemonDamon/AgenticXtheir own version, first seen Nov 9, 2026
- roundpilot/superpowers-antigravitytheir own version, first seen Nov 8, 2026
- REPOZY/superpowers-optimizedtheir own version, first seen Nov 8, 2026
- lingyired/status-triotheir own version, first seen Nov 8, 2026
- afawfawffaf/my-skillstheir own version, first seen Nov 8, 2026
- supermorkat/qawa-arenatheir own version, first seen Nov 8, 2026
Used with
Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Leodorareluctant259Skillchinese-code-review
中文代码审查规范——在保持专业严谨的同时，用符合国内团队文化的方式给出有效反馈
Also in 8 projects that use this
- Leodorareluctant259Skill
chinese-commit-conventions
中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化
Also in 8 projects that use this
obraSkilldiagnosing-superpowers
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
Also in 20 projects that use this
OpenAISkillrequesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Also in 200 projects that use this
- OpenAISkill
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Also in 154 projects that use this
- +3 more from Leodorareluctant259
- +4 more from openai
Other versions187 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 187
- obra/superpowers★ 314ksame name
- cloudflare/workerd★ 9.1ksame name
- jnMetaCode/superpowers-zh★ 8.4ksame name
- openai/plugins★ 7.8ksame name
- farm-fe/farm★ 5.6ksame name
- microsoft/FluidFramework★ 4.9ksame name
- lingyired/status-trio★ 1.8ksame name
- GanyuanRan/Aegis★ 1.4ksame name
- pcvelz/superpowers★ 1.3ksame name
- DemonDamon/AgenticX★ 1ksame name
177 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- writing-skillsSkill
- building-wikiSkill
- compressing-knowledgeSkill
- creating-issuesSkill
- designing-cliSkill
- fuckSkill
- functional-domain-modelingSkill
- git-shippingSkill
- no-commentsSkill
- orchestratingSkill
- tracking-tasksSkill
- writing-japaneseSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 179 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 37
When the reviewer is an AI such as Copilot code review, or no user can answer mid-run, read AI reviewers and unattended runs.
“Common” is measured: kept by at least 6 in 10 of the 179 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Receiving Code Review
A review comment is a hypothesis about the code, not a fact about it. Settle every item against the codebase first; fixes come after.
Verdicts
Assign one verdict per item before editing anything. The evidence column is what makes the verdict reportable — without it, the item is still unsettled.
| Verdict | Evidence required | Next action |
| accept | The reported behavior reproduced, or the cited code read and confirmed | Fix, then verify the fix |
| clarify | — | Ask what the item means before touching the code |
| push back | Code, test, or constraint that contradicts the suggestion | Reply with that evidence and a question |
| drop | No caller or usage found for the code the suggestion would grow | Propose deleting it instead |
| unverifiable | — | Report what you checked, and what would settle it |
The item is clear but nothing in reach proves or disproves it — a production-only failure, an external system's behavior — so it is unverifiable, not a push back: absence of supporting code is not contradicting evidence. Never quietly accept one either.
A suggestion that contradicts a decision the user already made outranks the table: it goes back to the user, not into the code.
Confidence in a reviewer is not evidence. Bots and agent reviewers report findings about code paths they never read, and a human may be reading an older revision; check either, and accept what holds up. Judge an outdated thread against the current code, not the hunk it was left on.
Clarify All Items First
Assign verdicts across every item before implementing any of them, and ask about all the unclear ones in a single reply. Hold any item sharing an assumption with an unclear one — fixing item 3 under a wrong reading of item 5 produces work that must be undone. Independent accepted items can proceed while you wait.
When the reviewer is an AI such as Copilot code review, or no user can answer mid-run, read AI reviewers and unattended runs.
Implement and Verify
Order accepted items: breakage and security first, then mechanical fixes, then the ones that need design. Verify each fix on its own before starting the next, and re-run the wider tests once the batch is done.
Replying
Report the verdict and what settled it — "Reproduced, fixed in parser.ts", "Checked: no caller reaches this branch". Accepting is silent work; pushing back needs the contradicting evidence quoted. If you pushed back and were wrong, say what you checked, what it showed, and that you are fixing it.
On GitHub, reply inside the comment's own thread and resolve the thread once handled, so the next pass sees only new items.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.