Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 379,385 indexed, measured the same four ways as everything else here.
Bridge selected questions and long coding/debugging subtasks to Doubao (豆包), ByteDance's AI assistant. Use when the user wants to forward a problem to Doubao, include environment context, wait for Doubao's real response, and use that response downstream.
MCP server "kali-lab" as configured in andrescaicedom/tribuia-taller-seguridad. Runs /workspace/docker/operator/tools/mcp-kali.py with python3. Needs 1 environment variable to run.
Claude Code package for routing work to non-Claude models: flat one-shot dispatch and dependency-ordered Workflow DAGs over repo-installed codex/kimi/opencode/grok/qwen transport shims.
★not rated 5 1mo agoA
tokens not measured
originalMIT
A set of detailed development-stage rules written in Chinese for implementation work, including workflows, coding standards, consistency checks, and plan migration.
Get a second opinion from Codex CLI (OpenAI) on plans, code, or debugging. Use this skill when the user asks to review plans with Codex, get a code review from Codex, or wants a second perspective on a bug. Also use proactively: after finishing an implementation plan, after completing a feature implementation, or when…
A comprehensive toolkit for interacting with Kaggle competitions: uploading notebooks, submitting predictions, downloading data, checking status, and viewing leaderboards.
Compose and send a readable Microsoft Teams message as the user — DM, group chat or channel: HTML that Teams actually renders, recipient verified by email, English body, draft shown before sending. Use whenever something goes out to a person or a chat in Teams (a finding, a handover, an answer, a heads-up), and as the…
End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
Run HeyReach cloud LinkedIn outreach from Claude via MCP/REST — research-to-send loop. Create lead lists, build campaigns (connection request + message sequences), push personalized leads, read the inbox, send replies, manage webhooks. Cloud-based, so it keeps sending while your machine is off.
Drive a Claude Code worker running in another tmux session. Use when the user wants you to be the "orchestrator" / supervisor / planner that delegates coding work to a separate Claude instance and only monitors progress. Triggers include phrases like "be the orchestrator", "the worker is in session X", "drive the…
Live-data GEO (Generative Engine Optimization) opportunity finder, powered by the Bright Data MCP. Give it your product and it runs deep research to find the AI-search prompts you can actually WIN — the prompts where ChatGPT cites nobody, cites something irrelevant, or cites a page you could easily beat. It profiles…
Set up Playwright E2E testing framework for any project — auto-detects stack, auth, routes, and selectors.
★not rated 5 3mo agoA31 tokens
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: