Lint And Validate

This runs linting, type checking, and static analysis after every code change you make, supporting both Node.js/TypeScript (ESLint, tsc) and Python (Ruff, MyPy, Bandit) ecosystems. The skill enforces a strict quality loop where you can't mark work as done until all checks pass. It's opinionated about when to run (always) and what constitutes acceptable code (zero errors in the final audit). If you're the type who forgets to lint before committing or tends to skip type checks when in a hurry, this acts as an automatic guardrail. The approach is heavy handed but effective for maintaining standards.

skills.sh installs: 334
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill lint-and-validate --agent claude-code

Installs into .claude/skills of the current project.

Files

Lint and Validate Skill

MANDATORY: Run appropriate validation tools after EVERY code change. Do not finish a task until the code is error-free.

Procedures by Ecosystem

Node.js / TypeScript

Lint/Fix: npm run lint or npx eslint "path" --fix
Types: npx tsc --noEmit
Security: npm audit --audit-level=high

Python

Linter (Ruff): ruff check "path" --fix (Fast & Modern)
Security (Bandit): bandit -r "path" -ll
Types (MyPy): mypy "path"

The Quality Loop

Write/Edit Code
Run Audit: npm run lint && npx tsc --noEmit
Analyze Report: Check the "FINAL AUDIT REPORT" section.
Fix & Repeat: Submitting code with "FINAL AUDIT" failures is NOT allowed.

Error Handling

If lint fails: Fix the style or syntax issues immediately.
If tsc fails: Correct type mismatches before proceeding.
If no tool is configured: Check the project root for .eslintrc, tsconfig.json, pyproject.toml and suggest creating one.

Strict Rule: No code should be committed or reported as "done" without passing these checks.