Lint and Validate Skill

SkillAI & models

Lint-and-validate is a skill that gives an AI agent automatic quality control, linting, and static analysis procedures. After every code modification, the agent runs the appropriate linters, type checks, and security audits for the project's ecosystem and keeps fixing issues until the code passes. This ensures syntax correctness and project standards before a task is reported as done.

Use Lint and Validate Skill in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Lint and Validate Skill and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Lint and Validate Skill skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Have a project with linting or type checking configured, such as an .eslintrc, tsconfig.json, or pyproject.toml file.

Lint and Validate SkillStart free

What your AI can do with it

  • Runs ESLint or npm run lint with auto-fix on Node.js and TypeScript changes
  • Checks types with tsc --noEmit and MyPy for Python projects
  • Runs security audits with npm audit and Bandit
  • Lints Python code with Ruff and applies fixes
  • Follows a quality loop that repeats audit and fix until checks pass
  • Includes lint_runner.py and type_coverage.py scripts for unified checks

Getting started

  1. Have a project with linting or type checking configured, such as an .eslintrc, tsconfig.json, or pyproject.toml file.
  2. Add the lint-and-validate skill to your agent so it can use the Read, Glob, Grep, and Bash tools.
  3. Ask the agent to lint, format, check, validate, or run static analysis, or let it trigger automatically after code changes.
  4. Review the FINAL AUDIT REPORT the agent produces and have it fix any failures before finishing.

What this skill tells your AI

The instructions your AI receives, as published by davila7/claude-code-templates in cli-tool/components/skills/development/lint-and-validate/SKILL.md and read by ahel’s review.

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
  1. Lint/Fix: npm run lint or npx eslint "path" --fix
  2. Types: npx tsc --noEmit
  3. Security: npm audit --audit-level=high
Python
  1. Linter (Ruff): ruff check "path" --fix (Fast & Modern)
  2. Security (Bandit): bandit -r "path" -ll
  3. Types (MyPy): mypy "path"

The Quality Loop

  1. Write/Edit Code
  2. Run Audit: npm run lint && npx tsc --noEmit
  3. Analyze Report: Check the "FINAL AUDIT REPORT" section.
  4. 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.


Scripts

ScriptPurposeCommand
scripts/lint_runner.pyUnified lint checkpython scripts/lint_runner.py <project_path>
scripts/type_coverage.pyType coverage analysispython scripts/type_coverage.py <project_path>

Signals

GitHub stars
32k
Forks
4k
Last commit
Oct 2026

Others that do the same job

Questions

When should the skill run?
After every code modification. The skill treats validation as mandatory and instructs the agent not to finish a task until the code is error-free.
What does it do for Python projects?
It runs Ruff for linting with fixes, Bandit for security checks, and MyPy for type checking on the given path.
What does it do for Node.js and TypeScript projects?
It runs npm run lint or ESLint with --fix, checks types with tsc --noEmit, and runs npm audit at the high severity level.
Advanced
Item type
skill
Key
lint-and-validate-davila7
Source
github.com/davila7/claude-code-templates