Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lgtm-hq-lint
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/lint
What's inside
- Skill name
lint- Description
- Run linting and formatting. Prefer `uv run lintro chk` for checks and `uv run lintro fmt` for formatting when lintro is available; fall back to native tools only when lintro is unavailable or another skill documents a follow-up pass (e.g. raycast).
- License
- MIT
- Instructions
- 54 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Lint
## Tooling
Prefer [lintro](https://github.com/lgtm-hq/py-lintro) for linting and formatting.
When available, use `uv run lintro chk` and `uv run lintro fmt`.
If lintro is unavailable, fall back to the language's native bundled tools (ruff,
black, clippy, rustfmt, eslint, bandit, etc.). Another skill may document an
additional pass after lintro (for example, `raycast` runs `npm run lint` after
lintro — Raycast rules take precedence for extension-specific checks).
## Commands
- `uv run lintro fmt` — format code
- `uv run lintro chk` — check code for issues
- `uv run lintro tst` — run tests
## Rules
- **CRITICAL: NEVER run `lintro chk --tools ...` (targeted/filtered checks).** Always run
the full `uv run lintro chk` without `--tools`. Filtered runs silently skip tools and
miss issues.
- **Exception:** single-tool runs (`--tools <tool>`) are permitted only when
developing or verifying that specific lintro tool (the `/lintro-add` and
`/lintro-verify` workflows). Even then, a full `uv run lintro chk` is still
required before committing.
- Linting must produce **zero issues** before proceeding
- **Fix ALL issues** — whether introduced in the current session or pre-existing
- **Ignore policy** — suppressing a finding is not a fix:
1. **Fix the root cause first.** `# noqa`, `# type: ignore`, `# nosec`,
`# nosemgrep`, `# yamllint disable-line`, etc. are a LAST resort, only
when there is no reasonable fix.
2. **If suppression is genuinely required**, use the narrowest possible
ignore — specific rule code, single line — WITH an inline justification
comment (`# nosec B603 - fixed argv list, no shell`). Unjustified
ignores are rejected.
3. **Blanket or file-level ignores** (whole-file disables, config-wide
excludes) require a documented exception (e.g. in `CONTRIBUTING.md`).
## Usage
When asked to lint or format code:
1. Run `uv run lintro fmt` FIRST to auto-fix formatting issues across the ENTIRE
codebase (when lintro is available)
2. Run `uv run lintro chk` to check for remaining issues (when lintro is available)
3. If lintro is unavailable, use native tooling for the language and still aim for
zero issues
4. Manually fix any issues found — do not leave issues unfixed
5. Re-run the check command to verify all fixes
6. Only as a last resort, add ignore comments WITH justificationFrom lgtm-hq/ai-skills, MIT.
More from lgtm-hq/ai-skills
- 0.587score
analyze-project
lgtm-hq
High-level project analysis.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
analyze-tests
lgtm-hq
Test suite analysis.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
audit-merges
lgtm-hq
Deep retrospective audit of everything merged to main over a window - code quality against the stand-* skills, introduced bugs, unsafe changes, merges over…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
babysit-pr
lgtm-hq
Autonomously drive an open PR to merge-ready state by triaging Greptile and CodeRabbit review comments, fixing CI failures, handling CodeRabbit rate limits…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
implement-issues
lgtm-hq
Implement a set of GitHub issues in parallel - triage or take an explicit issue list, group by file-conflict, create a worktree per lane, delegate to…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
lintro-review
lgtm-hq
AI branch review using lintro's own `lintro review` — a standard local pre-push pass alongside the coderabbit and greptile CLIs, and the review of record when…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
greptile
lgtm-hq
Run Greptile CLI for pre-push AI branch review.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
issue
lgtm-hq
Create GitHub issues with proper formatting, labels, and AI implementation prompts.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
pr
lgtm-hq
Create pull requests with proper templates and metadata.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
pr-raycast
lgtm-hq
Prepare and open a pull request to raycast/extensions.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
analyze-code
lgtm-hq
Code-level quality analysis.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
backlog
lgtm-hq
Interactive dispatcher for backlog work.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 15
- Last commit (this folder)
- Jul 9, 2026 (3 months ago)
- Last release
- Oct 22, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/lgtm-hq/ai-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lgtm-hq
- 0.587score
analyze-tests
lgtm-hq
Test suite analysis.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
audit-merges
lgtm-hq
Deep retrospective audit of everything merged to main over a window - code quality against the stand-* skills, introduced bugs, unsafe changes, merges over…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
babysit-pr
lgtm-hq
Autonomously drive an open PR to merge-ready state by triaging Greptile and CodeRabbit review comments, fixing CI failures, handling CodeRabbit rate limits…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
implement-issues
lgtm-hq
Implement a set of GitHub issues in parallel - triage or take an explicit issue list, group by file-conflict, create a worktree per lane, delegate to…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
lintro-review
lgtm-hq
AI branch review using lintro's own `lintro review` — a standard local pre-push pass alongside the coderabbit and greptile CLIs, and the review of record when…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
analyze-project
lgtm-hq
High-level project analysis.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
lint skill. Agent Mart. https://agentmart.dev/skills/lgtm-hq-lint (last updated 2026-10-24)