Code quality check
A curated collection of reusable AI agent skills, playbooks, and prompts for security audits, engineering workflows, and automation.
npx -y skills add vishnujchandran/.agents --skill code-quality-checkAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Top-tier code quality audit skill for correctness, maintainability, readability, and testability with prioritized, minimal-diff fixes.
SKILL.md
2.2 KB, 460 tokens by cl100k_base, as published. Nobody here has run it
code-quality-check (v2.0)
Single general skill for code quality checks across repositories.
Trigger Signals
Use when user asks to:
- check code quality
- review messy or legacy code
- improve maintainability/readability
- reduce bug risk without major rewrites
Modes
analyze-only(default): findings + fix plan, no code editspatch-safe: apply minimal, low-risk fixes after user confirmation
Inputs
- target scope: changed files, module, or whole repo
- language/framework: auto-detect from project files
- optional focus: correctness, maintainability, testability, perf-smells
Quality Dimensions
- Correctness risk (null/edge cases, unsafe assumptions)
- Maintainability (complexity, duplication, dead code)
- Readability (naming, cohesion, module boundaries)
- Testability (missing tests around critical logic)
- Performance smells (hot loops, obvious anti-patterns)
Workflow
- Detect stack and project conventions (lint/format/tests).
- Prioritize changed and high-risk files first.
- Score findings using risk formula.
- Propose minimal, safe remediations.
- Add test recommendations for P0/P1 findings.
Risk Scoring
risk = impact × likelihood × change_surface
- P0: likely bugs/correctness failures
- P1: high complexity/fragility on important paths
- P2: readability/style improvements
Output Contract
Return exactly:
- Quality summary (
High/Medium/Low) + top risks - Findings table:
priority | confidence | file | issue | impact | fix - Top 5 fixes first
- Test plan for P0/P1 findings
- Optional minimal-diff patch plan
Fail Conditions
Mark result as needs-work if:
- any unresolved P0 exists
- critical path has no test recommendation
- proposed fix requires large rewrite outside requested scope
Constraints
- Prefer minimal diffs over rewrites
- Do not invent project rules; follow existing conventions
- Distinguish correctness issues from style preferences
- Keep feedback specific, actionable, and evidence-based