Code preflight
Run build, typecheck, lint, tests, and security checks for the current project. Auto-detects Python vs Node/Next.js.From its SKILL.md
npx -y skills add GRIDLOCK-NYC/claude-skills --skill code-preflightAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 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.
SKILL.md
2.6 KB, 716 tokens by cl100k_base, as published. Nobody here has run it
Verification Skill
Run a complete pre-PR check suite for the current project.
Step 1: Detect Project Type
Check the current directory for:
- Python:
pyproject.tomlorrequirements.txtpresent - Next.js/Node:
package.jsonpresent, optionallynext.config.* - If both exist, run both suites
Step 2: Run Checks
Python Projects
Run sequentially, capture exit codes:
- Tests:
python -m pytest -x --tb=short -q(FAIL if exit != 0) - Lint:
ruff check .(FAIL if exit != 0) - Format:
ruff format --check .(FAIL if exit != 0) - Type Check:
mypy . --ignore-missing-imports(WARN only — never FAIL on mypy) - Secrets Scan:
grep -rn "sk-\|API_KEY\s*=\|SECRET\s*=\|TOKEN\s*=" --include="*.py" . | grep -v ".env" | grep -v "__pycache__"(FAIL if matches found)
Next.js/Node Projects
Run sequentially, capture exit codes:
- Build:
npm run build(FAIL if exit != 0) - Type Check:
npx tsc --noEmit(FAIL if exit != 0) - Lint:
npm run lint(FAIL if exit != 0) - Tests:
npm run test -- --run(FAIL if exit != 0, SKIP if no test script) - Secrets Scan:
grep -rn "sk-\|API_KEY\s*=" --include="*.ts" --include="*.tsx" . | grep -v "node_modules" | grep -v ".env"(FAIL if matches found)
Step 3: Format Report
Output exactly this format:
=== VERIFICATION REPORT ===
Project: [name] ([Python|Next.js|Both])
Directory: [cwd]
Branch: [git branch --show-current]
[PASS|FAIL|WARN|SKIP] Tests [1-line summary]
[PASS|FAIL|WARN|SKIP] Lint [1-line summary]
[PASS|FAIL|WARN|SKIP] Format [1-line summary]
[PASS|FAIL|WARN|SKIP] Type Check [1-line summary]
[PASS|FAIL|WARN|SKIP] Secrets Scan [1-line summary]
[PASS|FAIL|WARN|SKIP] Build [1-line summary, Node only]
VERDICT: [READY | NOT READY] ([N failures, M warnings])
===========================
Step 4: Verdict Rules
- READY: Zero FAILs (WARNs and SKIPs are OK)
- NOT READY: One or more FAILs
- For each FAIL, suggest the specific fix but do NOT auto-fix
- If the user passed an argument (e.g.,
/code-preflight tests), only run that specific check
Important
- Do NOT modify any files. This is read-only + run checks.
- If a tool is missing (ruff, mypy, eslint), mark that check as SKIP with reason.
- Respect the 3-file rule: if the user needs fixes, list them but let the user decide scope.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.