Claude
Tools

Auto-route every Claude Code prompt to the right skill, subagent, or slash command — silently, locally, with zero API keys.

Watch a Claude agent's tool-calling loop — paste a trace, replay it step by step on a cinematic timeline. No key, no backend.

Claude Code plugin (Agent Skill) for BPMN 2.0 - read, explain, create & edit .bpmn process diagrams with clean auto-generated layout, validation, and control-flow linting (deadlocks, stuck tokens). Works with Camunda Modeler & bpmn.io.

让 Claude Code 从随机走向可控的长期协作约束系统。 长期与 AI 协作时，build 被跳过、文件只读一半、"应该正常"代替验证——这些问题缓慢累积，最终交付逐渐退化成"看起来已经完成"。 本项目提供一套完整的 7 层约束设计：Hook 输入端硬约束、Skill 持续性协议、CLAUDE.md 分级规范、交付前审计、关键决策点行为补丁、自动化脚本、跨会话记忆反馈。含可直接复用的配置、代码和脚本。 不是写更长的 prompt，而是搭更薄的约束层。

Token usage tracker & prompt optimizer for Claude Code. Hooks into your workflow to measure real spend, detect filler phrases (6 languages), and suggest leaner prompts — local SQLite, zero telemetry, zero friction.

Claude SMM Skills — production Claude Agent Skills for the Planable MCP server. Draft post batches, pending approvals roundup, monthly performance summary, content calendar audit, cross-client metrics overview, and content pattern intelligence.

Claude Code 股票智能分析 Skill — 3D 评分（技术 50 + 基本面 30 + 消息面 20）。Fork from @liusai0820/Stock-Analysis-Skill with extensive enhancements.

Extract and summarize social media content from platforms like Instagram, TikTok, X, and YouTube using Claude Code.

Agent profile manager for Claude Code & Codex. Per-directory profiles select which skills, MCP servers, and plugins load — automatically, before launch. Install: npm install -g cue-ai

A Claude Code engineering template for reliable data warehouse AI development./面向数仓 AI 开发的 Claude Code 工程化模板：hooks、skills、subagents 与八步标准流程。

基于 ETF 资金流向数据的 A 股市场趋势量化分析工具 | ETF fund flow quantitative trend analysis for China A-share market

UnifAPI MCP server: public-data APIs and Skills for AI agents via Model Context Protocol

Live index of Claude Code extensions, hooks, and plugins — refreshed every 15 minutes from GitHub

Claude Code skill that generates a self-contained Korean HTML EDA dashboard for clinical/medical tabular research data (xlsx/csv).

Official multi-LLM agent pack for the GhostSwap Partners API (no-KYC crypto swaps, 1,600+ coins). MCP server, OpenAPI 3.1, Anthropic Agent Skill, AGENTS.md, Cursor/Copilot/Windsurf rules, ChatGPT GPT Action. Works with Claude, ChatGPT, Cursor, Windsurf, Gemini, Copilot, OpenAI Agents SDK, LangChain, LlamaIndex.

A "trust, but verify" workflow of AI-agent skills: prompt to verified code, every step trackable and deviations logged — plus an autonomous maintenance loop to keep a built project honest.

A portable agent skill (SKILL.md + reference playbooks) for writing top-conference embodied-AI papers — distilled from 63 papers (CoRL/RSS/ICRA/IROS/Science Robotics, 2022–2026). Works with any LLM agent that loads markdown context.

A Claude Code subagent that audits your setup (CLAUDE.md, settings.json, skills, agents, hooks, headless claude -p) against a maintained best-practices reference, with an optional weekly job that keeps the reference current.

Claude Code plugin: runtime invariants + hooks (cycle-detector, approval gate, verification gate), four co-system agents (developer · analyzer · critic · epistemic-auditor), and a held-out evaluation harness. Anti-hallucination protocol grounded in game theory and the scientific method.

A Claude Code skill for generating Anthropic-style standalone HTML diagram files.

Production-ready Claude Code setup: team contract, rules, hooks, skills, and specs workflow, wired together.

A design-taste skill that removes what an interface doesn't need, then perfects what's left.

An Agent Skills compliant skill that enables AI agents to automatically organize user input and maintain a persistent, project-bound idea repository (mdbase) — so decisions, preferences, and constraints survive across sessions and agent handoffs.

小红书封面生成与样图排版库扩充的 Codex / Claude Skill