Code change verification

Skill Komluc/agent-skills-production/skills/code-change-verification

Production-grade agent skills for Claude Code, OpenAI Codex, Gemini CLI, and every platform implementing the Agent Skills open standard

Install

npx -y skills add Komluc/agent-skills-production --skill code-change-verification

Assembled 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

Runs the full verification stack (format, lint, typecheck, tests) when changes affect runtime code, tests, or build behavior. Use before committing or opening a PR. Do not trigger for documentation-only changes, config comments, or README edits.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.1 KB, 416 tokens by cl100k_base, as published. Nobody here has run it

Step 1 — Detect the project type

Check which config files exist at the repo root:

scripts/detect-stack.sh

The script outputs one of: python, typescript, python+typescript, unknown.

If output is unknown: ask the user which stack to verify before continuing.

Step 2 — Run verification

Run the appropriate commands based on detected stack.

Python stack

scripts/verify-python.sh

Expected output on success:

[format]    ✅ passed
[lint]      ✅ passed
[typecheck] ✅ passed
[tests]     ✅ passed (N tests, 0 failed)

TypeScript stack

scripts/verify-typescript.sh

Expected output on success:

[install]   ✅ passed
[build]     ✅ passed
[lint]      ✅ passed
[tests]     ✅ passed (N tests, 0 failed)

Both stacks

Run Python script first, then TypeScript. Both must pass before proceeding.

Step 3 — Handle results

If all checks pass: Report: Verification complete — all checks passed. Safe to commit. No further action required.

If any check fails:

Read the script output in full
Identify the failing check (format / lint / typecheck / tests)
Report in this exact format:

Verification failed — [N] check(s) failed:

❌ [check name]: [error summary in one line]
   Fix: [specific action to take]

❌ [check name]: [error summary in one line]
   Fix: [specific action to take]

Do not commit until all checks pass.

Do NOT attempt to auto-fix errors unless the user explicitly asks
Do NOT skip a failing check and proceed — report it and stop

Error reference

See references/common-errors.md for known error patterns and their fixes.