SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
agentclash
Run lightweight Go-specific checks (detect go.mod, run tests) after commits when Go code is present to catch regressions early.
pgrx
Guidance and commands for building, testing, and running pgrx-based Postgres extensions in Rust; clarifies #[test] vs #[pg_test] and appropriate cargo pgrx subc
manten
Compact Node.js testing patterns with standalone imports, AsyncLocalStorage-based context, concurrency controls, hooks, snapshot testing, and simple timeouts/re
claude-skills-collection
Run and manage Playwright-based end-to-end test regimes: discovery, execution, evidence capture, and reporting for web apps.
claude-skill-registry
Guides agents to create, validate, and optimize Agent Skills (SKILL.md) with best practices, frontmatter rules, and testing workflows.
awesome-omni-skills
Master orchestrator for test-driven development workflows: enforces red-green-refactor discipline, coordinates multi-agent TDD workflows, and preserves provenan
workflows
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
claude-skill-registry
Provides dbt project patterns and examples for staging, incremental models, testing, and best practices for analytics engineering.
vet
Run a vet-style review immediately after each logical code change to detect issues in diffs and conversation history; complements tests but focuses on human/age
skills
Opinionated JavaScript/TypeScript tooling and conventions (Anthony Fu) for project setup, linting, monorepos and publishing workflows.
skills_collection
Coordinate test strategy, automation, and quality gates across unit, integration, E2E and performance tests for a component or service.
skill-demoflow
Generate and run Playwright browser or terminal automation scenarios from natural-language descriptions, producing HAR captures and polished demo videos (MP4) w
security-skill
Send concurrent request bursts to detect TOCTOU, coupon reuse, double-spend and other web endpoint race conditions.
aaas-vault
Guided playbook for integrating large language models into the game development lifecycle — design, prototyping, code generation, testing, and review.
artusx
Opinionated best-practices and recipes for building applications, plugins, and libraries on the ArtusX (Artus.js) framework.
skill
Run one-off Node.js packages or CLIs directly via npx — useful for scaffolding, testing package versions, and ad-hoc tool execution.
opencode-skills-collection
Guidelines and utilities for TDD, factory-based test data, mocking strategies, and testing patterns for React/TypeScript projects.
antigravity-awesome-skills
Guidelines and decision-making for Node.js architecture, runtime, async patterns, security, validation, and testing to inform framework and system choices.
farming-labs
Repo-specific skill for the Farming Labs ORM monorepo: schema DSL, runtime drivers, tests, docs, and release workflows.
claude-skill-registry
Structured guidance for test strategy, safe execution, and coverage analysis for agent workflows; includes commands, isolation rules, and a review checklist.
multi-agent-shogun
Design, validate and review Claude Code-style SKILL.md files: frontmatter guidance, trigger design, testing patterns, and recommended file structure for robust
grove
Defines a test-first workflow (red–green–refactor) for coding agents: write failing tests, implement minimal code to pass, then refactor with repeatable rules a
specialist-agent
A four-phase, evidence-first debugging methodology agent skill: gather evidence, analyze patterns, formulate hypotheses, and implement & prove fixes.
antigravity-awesome-skills
Structured workflow for testing REST and GraphQL API security: authentication, authorization, input validation, rate limiting, and common API vulnerabilities.
stella
Guides creation, testing, and iterative improvement of Agent Skills (SKILL.md) including running evals, generating benchmarks, and packaging skill bundles.
product-forge
Provides dbt project patterns, example models, testing snippets, and best practices for building staging→marts pipelines and tests in analytics engineering.
vexjoy-agent
Interactive micro-step pair-programming protocol: announce changes, show diffs, wait for user approval, apply, and verify (lint/tests).
ckb-standalone-debugger
Repository-specific skill for offline CKB contract debugging: run mock transactions, GDB sessions, flamegraph/coverage analysis, and WASM-compatible runs for co
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-code-tauri-skills
Testing patterns and tooling for Tauri v2 apps: unit/integration mocks, WebDriver e2e tests, and CI integration with GitHub Actions.
