Lint
Run linting and formatting checks. Use when user asks to "run linter", "/lint", "check linting", "fix lint errors", or requests code linting/formatting. Don't use for running tests or type-checking only.From its SKILL.md
npx -y skills add helderberto/agent-skills --skill lintAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 12 stars12 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.
- runs commandsInstructs the agent to run 8 commands, including `package.json lint` and 7 more.
SKILL.md
1.3 KB, 310 tokens by cl100k_base, as published. Nobody here has run it
Linting
Run the project's linter/formatter — detect it, don't assume a toolchain.
Detection
Prefer a task the project already defines, then fall back to the ecosystem tool:
| Ecosystem | Check | Fix |
|---|---|---|
| Node | package.json lint (eslint/biome) | lint:fix |
| Python | ruff check / flake8 | ruff check --fix |
| Go | golangci-lint run / gofmt -l | gofmt -w |
| Rust | cargo clippy / cargo fmt --check | cargo fmt |
| else | Makefile / CI lint target | — |
Workflow
- Detect the linter (project task first, then ecosystem default)
- Run the check command
- For fixes: run the fix variant (only when requested)
- Report
file:linereferences for all errors
Rules
- Prefer the project's defined task over a raw tool call
- Never invent a linter the project doesn't use
Error Handling
- If no linter or task found → report which config/task is expected and stop
- If the linter exits with parse errors → report each file-level parse error separately with
file:line - If the linter config is missing → report which config is expected and stop
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most quality gates skills give in 310 tokens
Counted across 1,524 of the 2,830 authors here whose files we hold, read 2026-09-06
- Read full output and check exit codein 45 of 1524, across 40 files
- Verify output confirms the claimin 44 of 1524, across 39 files
- Identify the command that proves the claimin 43 of 1524, across 39 files
- Execute the full verification commandin 36 of 1524, across 30 files
- Produce a verification reportin 34 of 1524, across 18 files
- Review git diff changesin 30 of 1524, across 16 files
- Fix build failures immediatelyin 29 of 1524, across 9 files
- Group findings by severityin 28 of 1524
- State claim only with evidencein 27 of 1524, across 22 files
- Verify regression tests with red-green cyclein 26 of 1524, across 22 files
- Run the full test suitein 26 of 1524, across 25 files
- Run test suite with coveragein 25 of 1524, across 10 files
Said here and by no other author read
- Detect the project linter first
- Prefer project defined tasks
- Run fix variant only when requested
- Report missing config or tasks
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.