Claude
Tools

File-based coordination protocol for AI coding agent squads. Drop .fireteam/ into your project — 2-6 agents coordinate through markdown. No server, no database.

Claude Code 多模型协作的 SESSION_ID 自动管理工具。通过 PreToolUse hooks /skill 在每次 MCP 调用前注入会话状态，防止跨任务上下文丢失和会话混乱

Describe any task in natural language — OmniDrive analyzes intent, installs dependencies, and executes automatically.

GitHub Action: Auto-generate CLAUDE.md governance files for Claude Code projects. Detects tech stack, frameworks, and tools.

Claude Code skill for Cortex XSOAR content pack development lifecycle

Claude Code 分级通知插件 — 11 个渠道，短通知即时触达，长通知异步兜底。人可以闲着，Agent 不可以。

亚马逊选品分析 Skill - 自动化 Best Seller 数据抓取、潜力分析和投资决策支持

Claude Code skill for reverse engineering, analysing, and building Chrome extensions

Stop prompting. Start engineering. Persona-driven installer that turns Claude Code into an engineering-governed development environment with enforced quality standards, specialist agents, and hooks.

GitHub Copilot agent skills adapted from Anthropic Claude plugins and OpenAI Codex Skills

Bridge hook and integration guide for running context-mode alongside jCodeMunch + jDocMunch in Claude Code — three MCP servers covering code, docs, and data files with zero conflicts

Claude Code → Lark (Feishu) notification hook. Get instant rich cards when tasks complete.

LLMLingua-2 prompt compression hook for Claude Code — cut token usage by ~55%

AI-powered study tool for Claude Certified Architect exam. The codebase IS the curriculum.

MCP server that turns Claude into a Fantasy Premier League analyst. 11 tools: captain picks, transfer suggestions, player comparison, hit calculator, chip strategy, differentials, fixtures, price predictions, live points, squad scout. pip install fpl-intelligence

AI-powered 3D design in Blender via MCP — agent skill for Claude Code, Codex & ChatGPT

Agent Telemetry for Claude Code

Point. Describe. Ship. Chrome extension for visual feedback, video direction, and QA assertions across the RenderDraw stack. Click any element on any page, describe what needs to change, and get structured annotation data that routes directly to Claude Code via MCP — or copy it to your clipboard when MCP isn't running.

A curated collection of 47 custom slash commands for Claude Code. Code review, security audits, architecture design, DevOps, and workflow automation — organized into 7 categories. Built for .NET/Blazor/TypeScript stacks, easily adaptable to any.

CAST: multi-agent orchestration framework for Claude Code with hook-enforced quality gates and observability.

CAST observability UI — React 19 + Express dashboard for cast.db session analytics, agent runs, and hooks

Production-ready Claude Code configuration: 27 skills, 37 hooks, 5 rules. Includes Anthropic best practices, gstack integration, and conditional attention tags.

Self-hosted long-term memory substrate for any LLM-using tool. Hybrid vector + lexical recall with MMR reranking, auto-extracted knowledge graph, sleep-style consolidation, per-project tuning, MCP server, REST + OAuth 2.0, embedded React admin UI. SQLite or Postgres + pgvector or Qdrant. Pluggable providers (OpenAI, Anthropic, Gemini, Ollama).

Governance infrastructure for Claude Code — hooks, agents, and workflows that prevent the failure modes autonomous coding sessions actually hit