qa-review
Skill1 starsChanged yesterdayMITView on GitHub
Run an extremely strict maintainability review of the author's own changes: abstraction quality, giant files, and spaghetti-condition growth. Use for a deep code quality audit, a strict QA review, or a harsh maintainability review of a diff or PR. Never reviews code the author did not touch.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- nshopik/dream-teamtheir own version, first seen Nov 16, 2026
- bcvk/support-lead-kittheir own version, first seen Nov 15, 2026
- drosam/agentstheir own version, first seen Nov 15, 2026
- fushinoryuu/claude_skillstheir own version, first seen Nov 1, 2026
- drvoss/everything-copilot-clitheir own version, first seen Oct 26, 2026
- TzolkinB/skillstheir own version, first seen Oct 22, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- nearai/ironclaw★ 13ksame name
- arjun988/blender-skills★ 2.2ksame name
- hellowind777/helloagents★ 704same name
- PackmindHub/packmind★ 323same name
- shuotao/REVIT_MCP_study★ 110same name
- drvoss/everything-copilot-cli★ 49same name
- nimadorostkar/Claude-Skills-collection★ 37same name
- ieuanign/skills★ 2same name
- nshopik/dream-team★ 2same name
- TzolkinB/skills★ 2same name
4 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 repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- vercel-react-best-practices/AGENTS.mdAGENTS.md
- architecture-reviewSkill
- awsSkill
- code-review-frontendSkill
- comment-sickoSkill
- demo-scriptSkill
- documentation-writerSkill
- dotnetSkill
- factory-reviewSkill
- factorySkill
- lets-talk-about-itSkill
- nextjs-proxy-csp-hardeningSkill
- performance-review-humanizerSkill
- pr-body-styleSkill
- prd-modeSkill
- prove-it-worksSkill
- pythonSkill
- reconcile-reviewsSkill
- security-reviewSkill
- simplifySkill
- spikeSkill
- sweSkill
- test-reviewSkill
- typescript-strict-styleSkill
- unslopSkill
- vercel-react-best-practicesSkill
- whats-going-onSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
4
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 21
If a pre-existing problem blocks a clean implementation, say so in one sentence tied to the author's change and recommend the smallest …
- Distinctive: line 22
If the diff cannot be obtained, stop and ask.
- Distinctive: line 26
Read the reference for each step when you reach it.
- Distinctive: line 40
No findings about code the author did not change.
“Common” is measured: kept by at least 6 in 10 of the 11 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
QA Review
An unusually strict review of the quality and maintainability of the code the author changed. Be ambitious about how the author's change is structured: look for "code judo" moves that keep behavior and make the change dramatically simpler, smaller, and more direct.
Scope: the author's changes only
Review what the author wrote or modified in this change. Nothing else.
- Get the change set from the diff against the base branch. Every finding must point to a line the diff adds or modifies, or to code whose behavior the diff directly changes.
- Never report a problem that already existed in code the author did not touch. This includes old spaghetti, oversized files, missing types, duplicated helpers, and outdated patterns. Do not mention them as "side notes", "while I was here", or "for a follow-up". Unbounded scope is the failure this rule prevents.
- Touching a file does not put the whole file in scope. Only the changed lines, and what those lines do to their immediate surroundings, are in scope.
- Read untouched code only to judge the author's change: to check whether a canonical helper already exists, whether a layer boundary is respected, or how the new code interacts with its callers. What you learn there is evidence for a finding about the author's code, never a finding in itself.
- Suggested fixes must be edits to the author's own changes: simplify them, move them, split them, or replace them with an existing helper. Do not ask the author to refactor, rename, or clean up code they did not write in this change.
- A change counts as making the surrounding code worse only when the diff itself introduced the problem, for example a new branch added to an existing function, or a file pushed over the size limit by the new lines.
- If a pre-existing problem blocks a clean implementation, say so in one sentence tied to the author's change and recommend the smallest local workaround. Do not recommend fixing the pre-existing problem in this change.
- If the diff cannot be obtained, stop and ask. Do not fall back to reviewing the whole codebase.
Steps
Read the reference for each step when you reach it. Do not load them all up front.
| Step | What you do | Read |
| 1. Scope | Get the diff against the base branch. Fix the set of changed lines. | this file |
| 2. Standards | Apply the baseline prompt and the eight rules to the changed code. | references/standards.md |
| 3. Inspect | Go through the diff with the review questions. Flag what matches. | references/flags.md |
| 4. Write | Turn findings into direct, actionable comments with a remedy each. | references/feedback.md |
| 5. Decide | Approve or block against the approval bar. | references/approval.md |
Output
- Findings ordered by severity, each tied to a line the diff changed, with a concrete remedy.
- A verdict: approve, or block with the presumptive blockers that apply.
- No findings about code the author did not change.
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.

