Loading...
Loading...
Found 1,098 Skills
Use when running tests to validate implementations, collecting test evidence, or debugging failures. Load in TEST state. Covers unit tests (pytest/jest), API tests (curl), browser tests (Claude-in-Chrome), database verification. All results are code-verified, not LLM-judged.
Use this skill when you need to test or evaluate LangGraph/LangChain agents: writing unit or integration tests, generating test scaffolds, mocking LLM/tool behavior, running trajectory evaluation (match or LLM-as-judge), running LangSmith dataset evaluations, and comparing two agent versions with A/B-style offline analysis. Use it for Python and JavaScript/TypeScript workflows, evaluator design, experiment setup, regression gates, and debugging flaky/incorrect evaluation results.
QA skill orchestrator for test strategy, Playwright/E2E, mobile testing, API contracts, LLM agent testing, debugging, observability, resilience, refactoring, and docs coverage; routes to 12 specialized QA skills.
Use when implementing Network.framework connections (NWConnection, NetworkConnection), debugging connection failures, migrating from sockets/URLSession streams, or handling network transitions. Covers UDP/TCP patterns, structured concurrency networking (iOS 26+), and common anti-patterns.
TanStack Query v5 expert guidance - migration gotchas (v4→v5 breaking changes), performance pitfalls (infinite refetch loops, staleness traps), and decision frameworks (when NOT to use queries, SWR vs React Query trade-offs). Use when: (1) debugging v4→v5 migration errors (gcTime, isPending, throwOnError), (2) infinite refetch loops, (3) SSR hydration mismatches, (4) choosing between React Query vs SWR vs fetch, (5) optimistic update patterns not working. NOT for basic setup (see official docs). Focuses on non-obvious decisions and patterns that cause production issues. Triggers: React Query, TanStack Query, v5 migration, refetch loop, stale data, SSR hydration, query invalidation, optimistic updates debugging.
Guide for defining and using Claude subagents effectively. Use when (1) creating new subagent types, (2) learning how to delegate work to specialized subagents, (3) improving subagent delegation prompts, (4) understanding subagent orchestration patterns, or (5) debugging ineffective subagent usage.
Up-to-date Zig programming language patterns for version 0.15.x. Use when writing, reviewing, or debugging Zig code, working with build.zig and build.zig.zon files, or using comptime metaprogramming. Critical for avoiding outdated patterns from training data - especially build system APIs (root_module instead of root_source_file), I/O APIs (buffered writer pattern), container initialization (.empty/.init), allocator selection (DebugAllocator), and removed language features (async/await, usingnamespace).
Guidance for developing CoreWars warriors that achieve target win rates against specific opponents. This skill should be used when tasks involve writing, optimizing, or debugging Redcode assembly warriors for the CoreWars programming game, particularly when win rate thresholds must be met against multiple opponents.
Use the Playwright MCP server (@playwright/mcp) for browser-driven verification, screenshots, console logs, and UI flow validation; use when debugging or validating Angular UI behavior beyond unit tests.
Gemini CLI - Google's AI-powered command-line interface for building, debugging, and deploying with AI. Use when working with Gemini CLI configuration, commands, tools, extensions, hooks, skills, or MCP servers. Keywords: gemini-cli, google-ai, terminal, code-generation, workflow-automation, cli-commands, gemini-md, authentication, configuration, sandboxing, headless-mode, custom-commands, agent-skills, extensions, hooks, mcp-servers, file-system-tools, shell-commands, web-search, ide-integration.
Foundry development workflow for Solidity smart contracts. Use when building, testing, or deploying with Foundry (forge, cast, anvil). Covers project setup, foundry.toml configuration, testing patterns, fuzz testing, invariant testing, fork testing, cheatcodes, deployment scripts, and debugging. Triggers on tasks involving forge build, forge test, forge script, cast, anvil, or Foundry-based Solidity development.
Browser automation skill for UI testing via Chrome MCP tools. Use when: (1) QA Agent needs to verify UI visually or test interactions, (2) UI/UX Designer needs to check responsive design or component states, (3) Frontend Dev needs quick visual verification during development, (4) Test Writer needs to document user flows with screenshots/GIFs, (5) Any agent needs to test web interfaces, record demos, or debug UI issues. Capabilities: screenshots, interaction testing, accessibility checks, GIF recording, responsive testing, console/network debugging.