Claude
Tools

Claude Code plugin: end-to-end used car buying — multi-site research, mass dealer outreach, OTD negotiation with 50-state fee data, CARFAX analysis, decision tracking

Anthropic native tool-search policy extension for the pi coding agent. Conditionally injects Anthropic tool-search tools based on PI_ANTHROPIC_TOOL_SEARCH and appends tool-search guidance to the system prompt.

Per-project token usage tracker for Claude Code — live monitor, weekly budget, context-drain diagnostics. Desktop (Electron) + CLI + Chrome extension.

Goal-bounded autonomous turns for Claude Code — set an objective, set a budget, walk away. Stop-hook continuation engine + tool-equipped completion evaluator.

Claude skill + reference docs for the MagicMarkets REST & WebSocket API — place orders, manage heartbeats, stream live prices.

🔍 Claude Code skill that scrapes any social media post — metadata, comments, transcription & AI video analysis. Drop a link, get everything. Instagram · TikTok · Twitter/X · YouTube

Obsidian community plugin: exposes the vault to Claude (and any MCP client) as a local Streamable HTTP MCP server. Tools, resources, prompts.

One file. 9 questions. Stops AI agents from doing the obviously-wrong thing. MIT. Works with Claude Code, Codex, Cursor, OpenClaw.

A professional environment auditing skill for Claude Code to prevent dependency issues before coding starts.

Production-grade Claude Code skill for CN→EN deck globalization with McKinsey polish and layout audit. 4-stage pipeline (Sense → Translate → Audit → Handoff); swappable PROFILE block; polish-only mode for single-language decks.

Auto-inject 'critical rules' into every Claude Code turn via UserPromptSubmit hook. Tiny, auditable, MIT, fork-friendly. Includes r-check skill for on-demand rule lookup.

Drop-in wrappers for the Anthropic, OpenAI, and Gemini SDKs that make prompt caching effortless. Measure real cache hit rate from the response usage object, attach dollar savings to every call, canonicalize shuffled tools and RAG document order so a "slightly different" payload still hits the cache.

为 HTML demo 一键加上多人在线评论：贴 Pin / 回复 / 状态流转 / 跨页跳转，基于 Supabase，BYOSupabase，无共享后端。Cursor & Claude Code skill。

Type-safe Claude Code hooks for PHP. Every event, every tool input, every response — fully typed, mutation-tested, and kept in sync with the Anthropic spec by a daily drift job.

Curated, eval-tested collection of agent skills for Claude Code, Cursor, Codex, Cline, and 36+ more AI agents. Drop-in capabilities your agent can invoke automatically.

A minimal Python coding agent that runs an interactive loop with Anthropic (Claude) or OpenAI (GPT). The model gets four local tools: read_file, list_files, edit_file, and bash. It emits textual tool calls; this program runs them and feeds results back into the conversation.

Local-first task scheduling, calendar sync, and unattended Claude Code session launch.

Agent Skills for OnlyFans talent agency operations — referenced from meetanlora.com/.well-known/skills/index.json

Async design review and implementation loop between you and Claude, mediated by GitHub Issues.

Deterministic, auditable agent/skill dispatch for Claude Code. A typed seven-decision scoring kernel runs after the router has read the conversation — post-cognitive routing instead of prose-scanning. Auto-generates its catalog from skill sidecars and agent frontmatter.

Companion VSCode extension that patches Claude Code's webview to add an Auto plan mode entry to the mode picker

AI 产品经理的 Claude Skills 集合 · PRD 写作 / 项目脚手架 / SaaS 架构图 / 高保真原型 / 对话归档（5 个自创 skill，蒸馏自wdy Claw、JMaaS、SCRM 等实战项目）

A practical setup guide for Flutter developers using Claude Code — Anthropic's terminal-first AI pair programmer. Covers CLAUDE.md, skills, subagents, MCP, hooks, and Flutter-specific workflows.

Claude Code skill: orchestrate parallel teams of Claude agents — breadth/depth/mixed strategies, task coordination, optional per-agent TTS