check
Check code quality without making changes — lint, format, type, and security checks. Use when you want to inspect issues before fixing them.
Best use case
check is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Check code quality without making changes — lint, format, type, and security checks. Use when you want to inspect issues before fixing them.
Teams using check should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/check/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How check Compares
| Feature / Agent | check | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Check code quality without making changes — lint, format, type, and security checks. Use when you want to inspect issues before fixing them.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Code Quality Check (Read-Only) Run all quality checks and report results. Do not auto-fix anything. ## Tools This project uses the following hooks in `.pre-commit-config.yaml`: 1. **ruff** — Python lint 2. **ruff-format** — Code formatting 3. **pyright** — Static type checking 4. **bandit** — Security vulnerability scan ## Execution Run in order: ```bash # 1. Lint (no fix) uv run ruff check src/ tests/ # 2. Format check (no fix) uv run ruff format --check src/ tests/ # 3. Type check uv run pyright # 4. Security scan uv run bandit -c pyproject.toml -r src/ ``` ## Output Format ``` ## Code Quality Report ### Ruff Lint - Status: [pass/fail] - Issues found: [count] - Key issues: - [file:line] [rule-id] [description] ### Ruff Format - Status: [pass/fail] - Files needing formatting: [count] ### Pyright - Status: [pass/fail] - Type errors: [count] - Key errors: - [file:line] [error message] ### Bandit - Status: [pass/fail] - Security issues: [count] - By severity: High [n] / Medium [n] / Low [n] ``` On failures: - Lint/format issues → "Auto-fixable with the `auto-fix` skill" - Type errors → "Requires manual fix — locations listed above" - Security issues → "Review High severity first" If all pass: output `Code quality checks passed ✓` only.