review-defect-first
Skill1 starsChanged 54 days agoMITView on GitHub
Independent review of a diff, PR, or file that hunts concrete defects introduced by the change: correctness, security, data loss, authorization or tenant escape, production failure, broken contracts, performance regressions, missing critical tests. Severity-ordered findings citing a real code path; no style inflation; "no qualifying defect" is valid. Use for code review and as the independent gate at high risk.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- AL-JANEF/janefskillsword for word, first seen Sep 19, 2026
Other versions1 project uses a version of this.
Word for word · 1
- AL-JANEF/janefskills★ 1100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository25 other files it gives its agents.
- janefSkill
- forgeSkill
- accessibility-qualitySkill
- api-contractsSkill
- architecture-integritySkill
- context-efficiencySkill
- database-integritySkill
- delegation-disciplineSkill
- devops-reliabilitySkill
- documentation-integritySkill
- frontend-design-qualitySkill
- git-disciplineSkill
- implementation-qualitySkill
- performance-scalabilitySkill
- root-cause-debuggingSkill
- testing-verificationSkill
- ui-ux-qualitySkill
- auth-hardeningSkill
- secrets-guardSkill
- security-auditSkill
- security-loggingSkill
- skill-security-auditSkill
- threat-modelSkill
- variant-huntSkill
- vuln-auditSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 19
Read applicable repository instructions and the complete relevant diff, plus enough surrounding code to trace behavior end to end.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Defect-First Review
A review exists to find concrete, actionable defects introduced by the change. Style preferences, speculative concerns, and unsupported findings are noise; "no qualifying defect found" is a valid, honest result.
Method
- Read applicable repository instructions and the complete relevant diff, plus enough surrounding code to trace behavior end to end.
- Continue through the whole diff; do not stop at the first finding.
- Prioritize: correctness, security, data loss, authorization or tenant escape, production failure, broken contracts, performance regressions, missing critical tests. Then maintainability issues that will cause defects.
- Confirm each finding from a real code path, call site, invariant, or test gap. If you cannot point at it, it is not a finding.
- Order by severity and cite the smallest useful path and line range.
- End with residual risks and material verification gaps only.
The dimension checklist and the forbidden-pattern scan are in references/review-checklist.md.
Severity
- Blocking: correctness or security defect, data loss, authorization escape, broken contract.
- Should fix: real issue that is not blocking merge.
- Consider: hardening or improvement with a concrete benefit.
- Verified good: what is demonstrably correct; say so.
Output
## Review: <target>
### Blocking
- <file:line> — <defect> → <fix> (evidence: <path/test/invariant>)
### Should fix
### Consider
### Verified good
### Residual risk / not verifiedReviewers report; they do not edit. Route security-class findings to vuln-audit for remediation and to variant-hunt to sweep for siblings.
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.