skill

lint-and-validate · davila7 — Claude Code skill: linting and setup

Q: How do I install lint-and-validate in Claude Code?

Run `npx skills add davila7/claude-code-templates --skill lint-and-validate -a claude-code`. The skill will then be available in Claude Code.

Q: What happens when a project has no configured lint tool?

The skill checks the project root for `.eslintrc`, `tsconfig.json`, and `pyproject.toml`, then suggests creating a configuration.

This skill runs linting, type checks, and security audits after code changes. Use it to keep project checks in the editing loop.

Install into Claude Code · claude-code-templates All methods and platforms ↓

npx claude-code-templates@latest --skill development/lint-and-validate

Open on GitHub

What lint-and-validate does

The skill sets up a repeatable check cycle after each code edit: run the relevant tools, inspect the report, fix failures, and run the checks again. For Node.js and TypeScript, it can use npm run lint or npx eslint "path" --fix, followed by npx tsc --noEmit and npm audit --audit-level=high. Python projects use ruff check "path" --fix, bandit -r "path" -ll, and mypy "path".

It also includes scripts/lint_runner.py for a unified lint check and scripts/type_coverage.py for type coverage analysis. When the project has no configured checker, the skill looks for .eslintrc, tsconfig.json, and pyproject.toml, then suggests creating a configuration. A failed check means the code should not be reported as done.

What it helps with

catch style and syntax issues after edits
check TypeScript and Python type errors
run a Node.js dependency security audit
scan Python code with Bandit
measure type coverage for a project

Example prompts for the agent

Run the relevant checks on the code I just changed and fix every failure.
Check the project types and dependency security before marking the task done.
Run python scripts/lint_runner.py <project_path> and explain the audit results.

How to install lint-and-validate

1claude-code-templates

npx claude-code-templates@latest --skill development/lint-and-validate

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill lint-and-validate -a claude-code

3Manually: put the files in place

~/.claude/skills/lint-and-validate/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/lint-and-validate/

Manually: put the files in place

.agents/skills/lint-and-validate/SKILL.md

For all projects use ~/.agents/skills/

Manually: put the files in place

.cursor/skills/lint-and-validate/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install davila7/claude-code-templates lint-and-validate

2Manually: put the files in place

.github/skills/lint-and-validate/SKILL.md

Platform CLI

gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/development/lint-and-validate

Manually: put the files in place

.devin/skills/lint-and-validate/SKILL.md

The legacy .windsurf/skills/ path still works

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about lint-and-validate

How do I install lint-and-validate in Claude Code?

Run npx skills add davila7/claude-code-templates --skill lint-and-validate -a claude-code. The skill will then be available in Claude Code.

What does lint-and-validate do?

It runs linting, type checks, and security audits after code changes. The commands vary for Node.js, TypeScript, and Python projects.

What happens when a project has no configured lint tool?

The skill checks the project root for .eslintrc, tsconfig.json, and pyproject.toml, then suggests creating a configuration.

Similar skills

All skills for Testing and QA →

lint-and-validate by other authors comes first.

lint-and-validate sickn33 Runs configured linters and type checkers after code changes, telling actual failures apart from tools that never ran. CX Codex +1 1,300installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. CX Codex +1 678,700installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. 1,141,062installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs agent-browser vercel-labs A CLI skill for browser control: it opens pages, fills forms, clicks buttons, and tests web apps. Use it when an agent needs to act inside a website. CX Codex +1 1,200,000installs prototype Matt Pocock Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase. 986,201installs

From the same set495

The whole set →

doc A skill for reading, creating and editing .docx files when layout matters — tables, page breaks, fonts. Useful when the document goes to a client. 99installs electron-development A Claude skill for building Electron desktop apps: context isolation, safe IPC through preload, electron-builder packaging and auto-update. 98installs statsmodels A skill for regressions, GLM, time series and hypothesis tests inside Claude. Useful when you need inference on coefficients, not just predictions. 97installs screenshot-feature-extractor Turns interface screenshots into a feature and task checklist. Use it to plan work from UI designs or visual references. 97installs commit This skill formats commit messages using Sentry conventions, including issue references. Use it when you want a consistent Git history for a Sentry project. 94installs worktree-init Turns a list of tasks into separate git worktrees, each ready for its own Claude session in a Ghostty panel. 94installs observability-engineer Walks you through monitoring, logging and tracing design, SLI/SLO targets and incident response. Useful when you run many services and alert noise gets out of hand. 93installs domain-driven-design Decides whether a project needs full DDD, then lays out the work from strategic modeling to evented architecture. 93installs