Menu
Composite code quality score from linter, types, tests, and optional dead-code checks.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Code review and cleanup across reuse, quality, and efficiency dimensions. Launches three parallel review agents against the current diff, then aggregates findings and applies fixes.
Red-team the agent's own output against OWASP Top 10 for LLM Applications and Agentic AI. Self-inject, test boundaries, check exfiltration paths. If you can't attack your own output, someone else will.
Mandatory verification of every factual claim before emission. API contracts, dependency versions, file existence, behavior promises — claims about code are hypotheses until verified against the actual source. Based on Dhuliawala et al. (Meta FAIR, ACL 2024).
Disciplined 6-step diagnosis loop with strict evidence gates between stages. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Cannot advance without the required artifact per step.
Split the workflow into Evaluator and Optimizer personas. Evaluator scores output 1–10 on correctness, completeness, safety, and simplicity. Optimizer rewrites to address critiques. Loop until score ≥9 or 3 iterations. Self-improvement without measurement is guessing.
Detect fail-open security patterns: debug mode in production, permissive CORS, disabled CSRF, default admin credentials, verbose error messages, unauthenticated health endpoints. Configuration is code — review it with the same rigor.
| name | health-check |
| description | Composite code quality score from linter, types, tests, and optional dead-code checks. |
/retro to attach metrics to trends.Related: /regression-check for deep test interpretation; /dependency-audit for supply chain; /skills-doctor for incident-driven "won't run" triage and deep debug (not baseline scoring).
Do not use this skill for security review or production monitoring substitution.
package.json scripts, Makefile, CI config, pyproject.toml, etc.--changed if time-bound)knip, ts-prune), shell lintCI=true).bun test, bun run per workspace rules.Return a markdown report with these exact sections:
| Dimension | Score | Evidence |
|---|---|---|
| Tests | 8/10 | 142/145 pass, 3 flaky skipped |
| Types | 10/10 | tsc --noEmit clean |
| Lint | 7/10 | 12 warnings |
8.2 / 10