Code Quality
Code-quality review that MUST assess five quality axes and SHOULD apply the ReAct checklist with prioritized fixes.
Install
$ agentstack add skill-gc-victor-supersimple-code-quality ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-gc-victor-supersimple-code-quality) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Code Quality Skill
Purpose
This skill MUST assess code across correctness, readability, architecture, security, and performance, and it SHOULD approve changes only when they clearly improve the codebase. Judge the real maintenance cost of the change, not theoretical perfection.
ReAct Framework
REASON — Is the change justified and well scoped?
- Is the core problem clear?
- Does the change solve one problem?
- Is this the simplest solution that could work?
- Is added complexity justified?
- Was reuse considered?
ACT — Is the implementation high quality?
Review these five axes:
- Correctness
- Readability
- Architecture
- Security
- Performance
REFLECT — Is the system better after the change?
- Did complexity stay flat or decrease?
- Should any cleanup happen now instead of later?
- Is knowledge preserved in understandable code?
- Is the change easy to roll back or iterate on?
Severity Model
- Critical: blocks approval
- High: serious issue, must fix
- Medium: should fix, but may not block
- Low / Nit: optional improvement
- FYI: context only
Only Critical and High issues block approval.
Change Size Guidance
- ~100 lines: good
- ~300 lines: acceptable if focused
- ~1000 lines: too large; split it
Separate refactoring from feature work when possible.
Verification
Run the relevant checks before reporting:
- lint,
- type check,
- tests,
- dependency audit,
- build.
Mark unavailable checks as N/A.
Red Flags
Treat AI-generated code as untrusted until verified; check edge cases, tests, and hidden assumptions carefully.
- speculative abstractions,
- opaque cleverness,
- missing validation,
- secrets in code,
- N+1 or unbounded work,
- oversized changes with weak justification.
Follow the ReAct framework above.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: gc-victor
- Source: gc-victor/supersimple
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.