Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 371,838 indexed, measured the same four ways as everything else here.
jcarlosrodicio/opencode-agent-orchestration-kit
Skill Claude CodeCodex
Patterns and architectures for autonomous loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems. Use when setting up autonomous development workflows, choosing the right loop architecture, or building CI/CD-style continuous development pipelines.
Plugin Claude Code
Bundles 7 skills, 7 commands, 1 agent, 12 MCP servers · 835 tokens together
Mine, evaluate, backtest, benchmark, and report on quantitative alpha factors with the FactorMiner research engine.
Skill Claude Code
A command-line toolkit for WeCom, a Chinese business platform used for contacts, documents, tables, calendars, meetings, messages, files, and related work. It includes rules for choosing the right business area and checking access before use.
Skill Claude Code ✓ vendor
A command-line toolkit for producing AI-generated comic videos, from images and video to audio, prompts, projects, episodes, shots, storyboards, and media assets. CRUD means creating, viewing, editing, and deleting records.
Plugin Claude Code
Bundles 1 skill, 5 commands, 4 hooks · 150 tokens together
Claim, execute, and deliver cards on your own self-hosted OverClick board. Ships the workflow skill, the /overclick: commands, and hooks: a session-start board snapshot and a delivery commit check run by default, while the claim guard and the stop/harness guards ship disabled. The only network endpoint is the OverClic.
Skill Claude CodeCodex needs its repo ✓ vendor
Use early in an AI-agent project — before ship, before real traffic — to decide which evaluations to set up and to scaffold a starter experiment. Reads the agent's own code (system prompt, tools, task), recommends specific evaluators with reasons that cite real lines, and writes a labeled draft test suite as an Agent…
Skill Claude CodeCodex
Use this skill to create or improve README content. Cover what the project does, setup, common commands, configuration, development workflow, and troubleshooting.
MCP server Claude CodeCodexCursor +2
Spectral Python (SPy) is a Python module for hyperspectral image processing. Runs locally from the spectral Python package.
Agent Claude Code
Expert in big bang integration testing where all modules are combined simultaneously for comprehensive system validation. Orchestrates complex system-wide testing with advanced debugging and rapid issue isolation techniques.
Dicklesworthstone/jeffreysprompts.com
Skill Claude CodeCodex
Generate 30 improvement ideas, rigorously evaluate each, distill to the very best 5.
MCP server Claude CodeCodexCursor +2
One of 2 in mcp.json
MCP server "energyplus" as configured in LBNL-ETA/EnergyPlus-MCP. Runs energyplus_mcp_server.server with /workspace/energyplus-mcp-server/.venv/bin/python. Needs 1 environment variable to run.
Skill Claude CodeCodex
Deploy docker-compose projects to Kubernetes using Kappal. Use when the user wants to run docker-compose on Kubernetes, deploy with kappal, or says "make this run in kappal". Handles setup, build, deploy, logs, and teardown autonomously.
Plugin Claude Code
Bundles 2 skills, 2 commands · 96 tokens together
Verify a change works by driving the real system the way a user does. Approved acceptance criteria, a recorded run, and a four-axis report.
Chat2AnyLLM/awesome-claude-plugins
Command Claude Code
Generate a custom checklist for the current feature based on user requirements.
Plugin Claude Code
Bundles 18 skills, 18 agents · 1,969 tokens together
Turn feature requests into review-ready pull requests: issue, implementation, tests, a review-and-fix loop, and docs. Runs locally or on GitHub Actions, and is built for complex brownfield repos. Each week its retrospective reads what you actually merged and proposes improvements to your skill extensions.
Skill Claude CodeCodex
Disciplined task execution with planning, verification, and self-improvement loops. Use when starting non-trivial tasks (3+ steps), fixing bugs, building features, refactoring code, or when rigorous execution with quality gates is needed. Includes subagent delegation, lessons tracking, and staff-engineer-level…
Skill Claude CodeCodex
Structured memory capture for Ogham shared memory. Use when the user wants to store findings, remember something, save what was learned, or capture a decision. Triggers on "remember this", "store this", "save this finding", "save what we learned", "capture this decision", "log this", or any request to persist…
Skill Claude CodeCodex
Use parallel review subagents to inspect recent edits, suggest low-risk refactors, and apply only safe changes.
Skill Claude Code
Converts any web page URL to LLM-ready Markdown via a headless browser. Bypasses passive anti-bot fingerprinting and JavaScript rendering, then strips navigation, footers, scripts, and cookie banners. Triggered by URLs that need the actual readable page content.
Skill Claude CodeCodex
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
MCP server Claude CodeCodexCursor +2
One of 10 in .mcp.json
MCP server "filesystem" as configured in skuramatata/my-pi-agent. Launched with /bin/sh -c repo=${MY_PI_AGENT_MCP_REPO_DIR:-$(pwd)}; workspace=${MY_PI_AGENT_MCP.
Skill Claude CodeCodex
Skill "Monet" from Monet-AI-Editor/Monet, covering ai video editor — agent control reference, ⚠️ finding editorctl — mandatory (read this first), ⚠️ output file naming — mandatory (read this first), ⚠️ audio on multi-clip timelines — mandatory and ⚠️ canvas mode — mandatory rules (read this first).
Agentchengfeng/writing-assistant-skill
Skill Claude CodeCodex
An interactive assistant for writing Chinese-language social-media and other self-published content. It supports the process from choosing a topic through publication and later review.
Plugin Claude Code
Automatically evaluates whether Claude should continue working instead of stopping prematurely using Claude-judged decision making.
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: