Local qa

Run local QA including formatting, linting, and testing for the repository. Use whenever any file has been updated.From its SKILL.md

Install

npx -y skills add dceoy/ai-coding-agent-skills --skill local-qa

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

2 stars2 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.
runs commandsInstructs the agent to run 2 commands, including `scripts/qa.sh` and 1 more.

1.3 KB, 261 tokens by cl100k_base, as published. Nobody here has run it

Run the local QA script scripts/qa.sh in this skill.

Execute the script exactly as shown above when this skill is triggered.
Capture and summarize key output (success/failure, major warnings, and any files modified).
If the script fails due to missing tooling (command not found, missing executable, or equivalent), install the missing tool(s) and rerun ./scripts/qa.sh.
Install tools using this order of preference:
1. Use the project's package manager when applicable (uv/poetry for Python, package manager scripts/dependencies for Node.js).
2. Use a system package manager (brew on macOS, apt on Debian/Ubuntu) when project-local install is not applicable.
3. Use language-specific installers as fallback (pipx/pip, npm, go install, etc.).
If multiple tools are missing, repeat install -> rerun until QA completes or you hit a blocker.
If installation fails or requires unavailable privileges, report what was attempted, the exact failure, and stop.
Do not run unrelated commands; only run commands needed for QA and missing-tool installation.

537 B alongside SKILL.md, 1 of them executable