code-quality-gate
Skill1 starsChanged 3 months agoMITView on GitHub
This is a conformance and validation gate, not a substitute for code review. Determine the rules that apply to the change, run the project's authoritative checks, and report concrete pass/fail evidence. Apply guidance in this order: 1. Explicit user requirements for this change. 2. Repository and directory-scoped instructions (AGENTS.md, CLAUDE.md, contributor guides, and equivalent files). 3. Project configuration and canonical commands (formatter, linter, type checker, tests, build, CI configuration). 4. Relevant ADRs, domain references, and language-specific project guidance. 5. The…
2 other projects use a version of this.
Adopted by
Most recently taken up by
- kinhluan/skillstheir own version, first seen Nov 8, 2026
- AmitSinghOM/agent-skillstheir own version, first seen Sep 12, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- kinhluan/skills★ 6same name
- AmitSinghOM/agent-skills★ 0same name
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 repository14 other files it gives its agents.
- audit-pi-sessionSkill
- bash-scriptSkill
- cli-uxSkill
- docs-pesapSkill
- external-reviewSkill
- githubSkill
- gitlabSkill
- good-apiSkill
- prekSkill
- pythonSkill
- rust-pesapSkill
- tdd-pesapSkill
- torcSkill
- uvSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 32
If two authoritative sources conflict, report the conflict and do not silently choose a rule.
- Distinctive: line 40
Discover guidance: Read the applicable instruction files and identify the project's canonical validation commands.
- Distinctive: line 45
Run deterministic checks: Prefer the narrowest relevant formatter, linter, type checker, test, build, and generated-file checks.
- Distinctive: line 48
Inspect conformance: Check the changed code against the discovered rules, acceptance criteria, public contracts, and local patterns.
- Distinctive: line 57
Use the repository's separate review mechanism for correctness findings, severity, architecture, security review, and merge recommendations.
≈ “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
Code Quality Gate
This is a conformance and validation gate, not a substitute for code review. Determine the rules that apply to the change, run the project's authoritative checks, and report concrete pass/fail evidence.
Rule precedence
Apply guidance in this order:
- Explicit user requirements for this change.
- Repository and directory-scoped instructions (
AGENTS.md,CLAUDE.md, contributor guides, and equivalent files). - Project configuration and canonical commands (formatter, linter, type checker, tests, build, CI configuration).
- Relevant ADRs, domain references, and language-specific project guidance.
- The fallback baseline only where applicable project guidance is absent.
If two authoritative sources conflict, report the conflict and do not silently choose a rule. Treat missing guidance as a gap, not as permission to invent a project convention.
Workflow
- Scope the change. Inspect the diff, changed files, nearby tests, and the repository root. Check for nested instructions that govern touched paths.
- Discover guidance. Read the applicable instruction files and identify the project's canonical validation commands. Do not assume a generic command when the repository defines another one.
- Build a check matrix. Record each rule or command as
pass,fail,not-run, ornot-applicable, with its source. - Run deterministic checks. Prefer the narrowest relevant formatter, linter, type checker, test, build, and generated-file checks. Expand to the project-mandated suite when required.
- Inspect conformance. Check the changed code against the discovered rules, acceptance criteria, public contracts, and local patterns. Do not turn this into a broad search for unrelated bugs or design opinions.
- Report honestly. Distinguish a failed check, a skipped check, an unavailable tool, and an ambiguous or missing rule. Never claim a pass from an unrun command.
Boundary with review
- Use the repository's separate review mechanism for correctness findings, severity, architecture, security review, and merge recommendations.
- Apply comment-cleanup rules only for an explicit comment request or when they are a stated project requirement.
- Apply NASA/JPL rules only when safety-oriented discipline is explicitly requested.
Output
## Quality Gate: Pass | Needs fixes | Blocked
### Guidance applied
- Source: rule or convention
- Scope: files/directories covered
### Checks
- [pass|fail|not-run|not-applicable] Rule or command
Evidence: ...
### Unresolved guidance
- Missing, conflicting, or unavailable project information
### Validation
- Command: ...
- Result: ...Needs fixes means an applicable rule or required check failed. Blocked means
required guidance, tooling, credentials, or environment state prevented a
meaningful check. Do not use severity labels.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

