Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 374,720 indexed, measured the same four ways as everything else here.
GitLab MCP: supports creating issues from requirements or modifying code and submitting merge requests from existing issues, while also providing a set of atomic GitLab API tools for issue-driven development. Runs locally from the @chntif/mcp-gitlab-workflow npm package.
★not rated 25 6mo agoA
tokens not measured
originalMIT
Search the web and extract URLs with routing across Serper, Brave, Tavily, Querit, Linkup, Exa, Firecrawl, You.com, SearXNG, SerpBase, and Keenable. Returns ranked sources and page text; supports freshness filters and research across providers.
Intent-bound action authorization for AI agents — authorise before a credential is used, require human approval for sensitive actions, and prove every action traces back to the instruction that authorised it. Runs locally from the delego Python package. Needs 1 environment variable to run.
★not rated 25 3mo agoA
tokens not measured
originalApache-2.0
MCP server for RAGStack knowledge base - search, chat, upload, and scrape. Runs locally from the ragstack-mcp Python package. Needs 2 environment variables to run.
★not rated 25 4d agoA
tokens not measured
originalApache-2.0
You are tasked with conducting comprehensive research across the codebase to answer user questions by spawning parallel sub-agents and synthesizing their findings.
NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels. MANDATORY: every optimization MUST start with NCU profiling, followed by multi-dimensional analysis, then targeted code modification, then re-profiling to verify. Supports roofline, memory hierarchy, warp stalls, instruction mix…
End-to-end testing patterns with Playwright for full-stack Python/React applications. Use when writing E2E tests for complete user workflows (login, CRUD, navigation), critical path regression tests, or cross-browser validation. Covers test structure, page object model, selector strategy (data-testid > role > label)…
Plan iron, verify real. Ironclad planning with independent verification chain. Turns any input into a bulletproof plan, executes with TDD, verifies with independent agents.
★not rated 25 2mo agoA
tokens not measured
originalMIT
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
Expert WordPress and Elementor Pro development skill. Use this whenever the user asks about WordPress theme development, Elementor Pro customization, plugin architecture, custom post types, hooks/filters, Loop Grids, Dynamic Tags, Theme Builder templates, off-canvas UIs, custom CSS/JS injection, performance…
Writes a single synthesis article (3000-5000 words) for one taxonomy bucket. Produces landscape analysis with approach categories, convergence, failure modes, and selection guide. Use when writing a synthesis article for a bucket.
An idea partner for a developer who discusses plans, checks current information online, and prepares self-contained tasks for Claude Code running in Windows PowerShell. It is designed for Russian-language work and mentions Telegram bots, Python, SQLite, and Railway deployment.
Delegate coding tasks to Codex AI for implementation, analysis, and alternative solutions. Use when you need a second AI perspective, want to explore different approaches, or need specialized Codex capabilities for complex coding tasks.
Activate once per session to route substantive requests to the right installed skill. Two modes: suggest (interactive, ranked proposals) or auto (silent with attribution footer). Trigger: /skill-router on | /skill-router on --auto | /skill-router status.
Pull public web sources into Claude Code. Indexes static and server-rendered sites as local Markdown with conditional-GET caching, then exposes them as MCP tools. Local, browser-free, no API keys.
★not rated 25
changed 24d agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: