lgtm-hq
OrganizationCanonical Agent Skills library for Claude Code, Cursor, Codex, and other agents.
Categories
Indexed Skills (38)
implement-issues
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 sub-agents, open a PR per lane; never merges. Use when asked to implement issues, work the backlog, or pick up multiple issues in parallel.
backlog
Interactive dispatcher for backlog work. Asks one routing question — drive PRs to merge, or implement issues to open-PR state — then follow-ups based on the answer, and hands off to implement-issues / babysit-pr with standing policy applied. Use when asked to work the backlog or run /backlog.
babysit-pr
Autonomously drive an open PR to merge-ready state by triaging Greptile and CodeRabbit review comments, fixing CI failures, handling CodeRabbit rate limits, and looping until checks are green with no unresolved actionable threads. With the --merge flag, also merge the PR(s) once binding merge-queue conditions are met. Use when asked to babysit a PR, shepherd a PR, or keep a PR merge-ready until review/CI cycles complete.
sweep-prs
Retrospective audit of recently merged/closed PRs for anomalies that slipped through - merges without green builds, merges onto red main, unresolved or post-merge review threads, hollow resolutions. Read-only sweep, then confirmed remediation (issues, disposition replies). Use when asked to sweep PRs, audit merged PRs, or check what slipped through.
jira
Generate Jira-style ticket descriptions. Use when the user says "/jira", "jira ticket", or "give me a Jira ticket".
analyze-code
Code-level quality analysis. Use when asked to review code for smells, security issues, implementation quality, or test coverage.
analyze-project
High-level project analysis. Use when asked to analyze, review, or evaluate a project's architecture, structure, and overall health.
analyze-tests
Test suite analysis. Use when asked to analyze, review, or evaluate a project's tests for quality, coverage gaps, and best practices.
branch
Start work on a new branch or worktree. Use when asked to start a new branch, new worktree, begin work on a feature/fix, or start fresh. Supports issue numbers and plain descriptions.
commit
Pre-commit workflow and commit guidelines. Use when asked to commit changes. Requires passing lint and tests, signed commits, semantic prefixes, imperative mood.
issue
Create GitHub issues with proper formatting, labels, and AI implementation prompts. Use when asked to create an issue, report a bug, or request a feature.
lint
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).
pr-raycast
Prepare and open a pull request to raycast/extensions. Use when the user asks to open, submit, or get ready for a Raycast Store extension PR �� not for general extension coding.
pr
Create pull requests with proper templates and metadata. Use when asked to create a PR, open a pull request, or submit changes for review. Auto-assign and auto-labeling handled by CI.
properize
Promote a quick-and-dirty prototype to an lgtm-hq-standard repo - commit WIP lint-clean, grill the design, spec the backlog as milestone/epic/issue tree, then implement issue by issue. Use when asked to properize, productionize, or turn a prototype into a proper project.
raycast
Raycast extension development standards. Use when writing or modifying Raycast extensions. Run lintro first, then Raycast's toolchain (npm run lint) which takes precedence for extension-specific rules.
reconcile
Consolidate worktrees and clean up stale branches. Use when asked to reconcile, clean up worktrees, consolidate branches, or tidy up a project's git state.
scorecard
Audit the OpenSSF Scorecard rating for py-lintro. Use when asked to check the scorecard, understand the rating, or find what's missing. Specific to github.com/lgtm-hq/py-lintro.
stand-ci
CI/CD and GitHub Actions guidelines. Use when writing workflows or Actions. Shell script code must be in dedicated .sh or .py files. Actions must be pinned to SHAs, not versions.
stand-odin
Odin coding standards. Use when writing Odin code. Covers idiomatic error handling with or_else and or_return, memory/allocator patterns, attributes, naming and API conventions, and testing with core:testing.
stand-py
Python >= 3.11 coding standards. Use when writing Python code. Requires type hints, return types, Google-style docstrings, trailing commas, explicit kwargs, StrEnum with auto(), dataclasses, pytest-style tests.
stand-rust
Rust coding standards. Use when writing Rust code. Covers edition, error handling with thiserror/anyhow, unsafe policy, type patterns, testing, documentation, and dependency management.
stand-ts
TypeScript and JavaScript standards. Use when writing TS/JS code. Covers strict mode, type patterns, error handling, imports, naming, testing, React conventions, and package management with bun.
test-api
Playwright API testing best practices. Use when writing REST API tests with Playwright. Enforces Zod schema validation, client/fixture separation, and contract testing.
test-shell
BATS shell script testing. Use when writing or running shell script tests. Covers setup/teardown, assertions, mocking, helper patterns, and coverage with kcov.
test-ui-qsf
QSF project conventions for the Playwright E2E suite. Use when working in the QSF playwright-tests directory (authFixtures, ___ping-* handles, data-test-label test IDs, .auth storage states) — not for generic Playwright advice.
test-ui
Playwright E2E testing best practices. Use when writing browser tests, visual regression, or accessibility tests in any project. Enforces user-facing locators, auto-waiting, web-first assertions, and Page Object Model.
turbo-add
Guide for adding a new theme family to turbo-themes. Use when implementing Nord, Solarized, Gruvbox, Tokyo Night, One Dark, Ayu, Kanagawa, Everforest, Radix, or any new theme.
turbo-test
Run the full turbo-themes build and test pipeline. Use when asked to build, test, lint, or validate the turbo-themes project. Includes example projects by default.
turbo-verify
Verify that a theme implementation is complete and follows all project standards. Use after adding a new theme to turbo-themes.
coderabbit
Run CodeRabbit CLI for pre-push AI diff review. Use when asked for CodeRabbit, cr review, or as part of the default pre-push review set with greptile and lintro-review. Max 2-3 runs per change set.
greptile
Run Greptile CLI for pre-push AI branch review. Use when asked for Greptile review, raycast/extensions pre-PR checks, or as part of the default pre-push review set with coderabbit and lintro-review. Max 2 runs per change set.
lintro-add
Guide for adding new linting/formatting tools to lintro. Use when implementing shellcheck, shfmt, sqlfluff, taplo, semgrep, gitleaks, or any new tool plugin.
lintro-verify
Verify that a lintro tool implementation is complete and follows all project standards. Use after adding a new tool to lintro.
stand-general
Global coding standards for all projects and languages. Use when writing any code. Covers linting with lintro, testing with coverage, semantic commits, PR creation, and pre-push AI review with coderabbit, greptile, and lintro review CLIs.
lintro-review
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 those are rate-limited or unavailable. Use when asked for a lintro review, an interim/fallback AI review, or as part of the default pre-push review set.
rebase
Rebase the current branch onto the latest main. Use when asked to rebase, sync with main, update branch, or pull latest changes. Fetches and rebases onto latest main; does not push automatically.
which-pr
Report which PR is being worked on in the current conversation. Use when asked about the current PR context.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.