SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
cc-skills
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
agents-collection
Fetch GitHub issues, spawn automated sub-agents to implement fixes and open PRs, and monitor PR review comments for follow-up fixes.
han
Guidance on the pytest plugin ecosystem: plugin development, pytest-cov, pytest-mock, configuration, CI integration, and advanced patterns.
first-tree
Operations skill for managing Context Tree syncs: detect drift, open proposed fixes, and route reviewer workflows via gardener and breeze.
skills
Author and run readable Maestro YAML flows for mobile UI tests, integrate with CI, and use Maestro Studio for element inspection on Android and iOS.
skills
Integrate and automate Percy visual testing via the Membrane CLI: manage connections, discover actions, run snapshots and proxy API requests.
htest
Guidance for writing hTest declarative tests (JS-first and HTML-first), including patterns for args/expect, checks, maps, hooks, and running tests in Node or br
skill-lib
Guidance for compiling and troubleshooting Microsoft Visual C++ projects with MSBuild, including environment detection, common fixes, and recommended commands.
studio-recipes
Detect infrastructure drift between Terraform state and real cloud resources; report unmanaged/changed/missing resources for remediation.
claude-skill-registry
Structured guidance for test strategy, safe execution, and coverage analysis for agent workflows; includes commands, isolation rules, and a review checklist.
awesome-omni-skill
Helps verify release readiness, generate changelogs, coordinate version bumps, and run pre/post-release checks for Morphir projects.
agent-guards
Guided iOS development and debugging workflow using the xcodebuildmcp CLI: discover projects/schemes, build/test/run on simulator or device, capture logs, and t
gstack-ko
Release-engineering workflow: merge a PR, wait for CI/deploy, run canary checks and optionally revert — designed for safe, auditable production landings.
alef
Generates fully-typed language bindings and scaffolding for Rust libraries across 16 target languages, and provides CLI workflows for generate, build, test, ver
claude-code-blueprint
Run end-to-end Playwright test suites or perform interactive browser walkthroughs to verify UI and user journeys for a project.
opensoul
Orchestrates fetching GitHub issues, confirming targets, and spawning code-fix sub-agents to create PRs and handle review comments via the GitHub REST API.
ai-playground
Scans a repository, discovers and runs tests, computes coverage, evaluates test quality, and generates a metrics report website and JSON output.
han
Generate Kubernetes ConfigMaps and Secrets with Kustomize from literals, files, and envs to manage environment-specific configuration and trigger safe rollouts.
megatron-lm
Reference guide for Megatron-LM CI: pipeline structure, PR scope labels, triggering internal CI, and investigating CI failures.
fallow-skills
Static and runtime codebase intelligence for JavaScript/TypeScript—find unused code, duplication, circular deps, and complexity hotspots; merge runtime coverage
skills
Reference guide to Megatron-LM CI/CD: pipeline structure, PR scope labels, triggering internal CI, and steps for investigating CI failures.
claude-code-tauri-skills
Testing patterns and tooling for Tauri v2 apps: unit/integration mocks, WebDriver e2e tests, and CI integration with GitHub Actions.
superclaude-plusplus
Run project-specific verification rules that check business logic, architecture patterns, and naming conventions beyond linters.
agentclash
Detect repository CI entrypoints after commits and surface whether checks should be run or automated.
claude-skill-registry
Run and manage Python test suites with pytest — discover tests, execute with coverage or parallelism, and produce failure analysis and checkpoints.
claude-skill-registry
Perform focused, automated code reviews for a PR: detect bugs, security issues, performance problems and test gaps, then post a structured GitHub review and com
gstack
Measure and detect performance regressions for web pages using automated benchmarks, baselines, and trend analysis.
claude-code-blueprint
Run a comprehensive, multi-agent code review that covers quality, security, and database concerns and synthesises a severity-ranked findings table.
dotclaude
Runs Prisma generate, lint (with auto-fix), typecheck and tests in sequence and applies minimal safe fixes until the repo is clean.
agenvoy
Generate concise bilingual commit messages (English subject + Traditional Chinese body) from staged git diffs, with multi-topic detection and tag prioritization
