Agent skill
code-linting
Run linters according to repository guidelines. Use immediately after creating or modifying code, or before committing changes.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/code-linting
SKILL.md
Code Linting
Run all appropriate linters according to repository guidelines.
When to Use This Skill
Use this skill:
- Immediately after creating new source code files
- Immediately after modifying existing code (functions, classes, imports, etc.)
- Immediately after completing a feature, refactor, or bug fix
- Before staging files for commit
- When build/compilation succeeds but linting hasn't been checked
- Proactively, whenever code changes are made
Don't use:
- When you've already run linting and it passed
Linter Discovery
First look for linting commands in the following order:
- Directives to AI agents (
CLAUDE.md,.cursorrules,.ai-rules,AGENTS.md,AGENT.md,GEMINI.md, and similar) - Repository documentation (
README.md,docs/, etc.) - Package configuration (
package.json,Makefile,pyproject.toml, etc.) - Standard linter patterns for the project type
If no linting guidelines are found or they are unclear, ask the user for clarification.
Common Linter Commands
# JavaScript/TypeScript
npm run lint
yarn run lint
pnpm run lint
npx eslint .
# Python
ruff check .
pylint .
flake8 .
black --check .
make lint
# Shell
shellcheck .
# Multiple/Generic
npm run format
yarn run format
pnpm run format
Linting Process
For each linter found:
- If it has an auto-fix mode (e.g.,
prettier,eslint --fix,black,ruff check --fix), run that first - Run the linter in check mode to see if there are any remaining issues
- If issues can't be fixed automatically, report them clearly
Important Rules
CRITICAL: Do NOT ignore unfixed issues!
- All linting issues MUST be resolved before considering the task complete
- The only exception is if the user explicitly gives permission to defer resolution
- Document any issues that couldn't be auto-fixed for the user to review
Output
Report results organized by:
- Auto-fixed issues: What was automatically corrected
- Remaining issues: Issues requiring manual attention (list each with file, line, and description)
- Recommendation: What the developer should do next
If all linting passes, simply confirm: "All linters passed."
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?