Anthropic agents

Browse, search and download AI agent skills

你不缺 idea, 你缺一个把 idea 想清楚的人。一场对话把想法变成可执行的软件设计 — Built for Claude Code

Smart skill router for Claude Code — auto-suggests the right skill at the right moment based on message, git state, and dev phase

Autonomous sales agent — bulk outreach, inbox classification, research-driven personalization, lead recovery. HubSpot + Gmail. Runs on any local agent harness.

A Claude Code skill that adds a rubric-based eval layer to any agent project. Framework-agnostic — generates rubric, test cases, judge prompt, and harness. Returns a weighted score plus a judge-leniency signal.

Multi-agent orchestration on top of Claude Code. Supervisor delegates, specialists execute, you gate. Browser-based IDE; local-first.

Manage multiple Claude Code & Codex AI agents in Emacs — coordination, attention queue, health monitoring. Magit-inspired.

Product management skills for Claude Code. 8 plugins, 35 skills, one-line install. Customer discovery that verifies every quote against the transcript.

Claude in your zsh prompt: ask, explain, and Ctrl+X / Alt+E widgets that turn natural language into shell commands. Wraps the Claude Code CLI, no extra deps.

Stop Claude Code from breaking your projects. Ready-to-use CLAUDE.md templates, subagents, hooks, and anti-regression configs.

Local-first, read-only MCP server to talk to your XP Investimentos portfolio through Claude Desktop. TypeScript + SQLite. Zero scraping, zero credentials.

🛡️ Stop your AI from pushing secrets to GitHub. Security hooks, battle-tested rules, and a live validator for Claude Code. 5 hooks · 6 rules · 1 install script · 0 dependencies.

Disable or adjust the width of the sidebar functionality on Claude.ai

MCP server for Korea University KUPID portal & Canvas LMS — notices, schedules, library seats, assignments, grades from Claude

Persistent memory for AI coding agents via MCP — a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter + Gemini Flash → Neo4j (via Graphiti). 12 MCP tools, hierarchical clusters, two-regime confidence decay.

A GenAI-powered Flask app that audits documents for GDPR/HIPAA compliance, using regex rules and Anthropic Claude API to suggest remediations.

Top 50 Claude shortcut hacks for faster prompts 🌟 Star if you like it! 🌟

Structured research skill for Claude — parallel web search, test solutions, weighted scoring decisions

Claudeculator

MCP сервер для интеграции с YouGile

Automated governance framework for Claude Code — multi-model council, WIP lifecycle hooks, company memory, and security gates

Lossless local memory for Claude Code. The full, unabbreviated version. Every tool call, every file edit, every thinking block — stored verbatim on your machine. Persistent memory without tokens.

Large Language Model API interface

📊 CLI tool to track Claude Code usage, costs & token consumption. Analyze your AI coding assistant spending locally.

Anthropic Claude models on Google Cloud Vertex AI for pi coding agent.

Batch-process meeting transcripts from Obsidian vault into structured summaries with knowledge graph updates, people notes, and concept extraction

Convert AI-generated Markdown to WhatsApp, Telegram, Discord, Slack and Instagram compatible formats using an Intermediate Representation (IR) in PHP.

MCP server in Rust for AI agent persistent memory: branch-aware session handoffs, local ONNX embeddings, SQLite-backed semantic search.

The AI that refuses to think for you. Open-source anti-deskilling framework implementing human-AI collaboration protocols from the Cabitza lab (Milano-Bicocca). Four modes: Forge, Anvil, Crucible, Executor.

✈️ 24-tool MCP server for Claude Code: preflight checks for your prompts, cross-service context, session history search with LanceDB vectors, correction pattern learning, cost estimation

Multi-agent orchestration plugin for Claude Code. Coordinate agent teams with shared tasks, messaging, and 7 patterns including RLM (arXiv:2512.24601) for large-file analysis beyond context limits.

Free, open-source Claude usage monitor for macOS & Raycast. Track token limits, burn rate, per-project costs, team budgets, and get alerts before you hit rate limits.

Open registry of community-contributed AI coding skills (SKILL.md files) — daily-synced to skills-hub.ai. Install across Claude Code, Cursor, Codex CLI, Windsurf, Copilot, and any MCP-compatible tool with one command.

Open-source recreation of Claude Design (claude.ai/design) as a pure web app — chat-driven multi-file React prototyping with Tweaks · Comment · Edit · Draw, agent in your browser tab, single Cloudflare Worker for storage

Turn a one-line SaaS idea into a complete blueprint, right inside Claude Code. /planmysaas "your idea" → 9 markdown files of structured planning + Claude Code ready build prompts, in 2 minutes. Free, MIT licensed.

14 Claude AI agents trading EURUSD, XAUUSD, GBPUSD, USDJPY autonomously via MetaTrader 5 — daily strategist, entry specialists, real-time spike management, Telegram alerts

Bamboo — a local-first AI agent harness & runtime in Rust. Persistent memory, 22 built-in tools, skills, MCP, sub-agents, workflows & schedules behind one HTTP + WebSocket API. Embed it as a crate, or run it as a server.

Pi agent for Android — sideload the APK and run a Pi coding agent on your phone. Single-APK, on-device Termux runtime, Claude Pro/Max OAuth, no root.

Personal AI agent orchestration runtime for Claude Code: build, schedule, and run private TypeScript agents with A2A, launchd, and an Electron UI.

Drop-in OpenClaw/NemoClaw agent configuration for the ibl.ai Legal segment — Firm Assistant orchestrator plus 12 specialist subagents.

Claude Enterprise is a professional AI assistant and enterprise workspace solution for Windows with the Complete Edition delivering every premium module and advanced capability enabled. Full feature access with no usage limits — Enterprise Setup supports installation and download for production workflows.

Custom Claude Code status bar: thinking level, rate limits with velocity, git context, context window

Durable contract-driven goal execution for Claude Code. A subagent judge gates completion against an explicit Definition of Done.

MCP server giving Claude live access to SAP systems via ADT — read, edit, search, test, and diff ABAP across landscapes without installing anything on the SAP stack.

Evolving agent harnesses: a research program on how far N orchestrated calls of a small model can rival a frontier model. We evolve the harness (structure + prompts) with reflective optimizers + a verified-acceptance gate.

Prompt optimizer for Claude Fable 5, built as a claude.ai Project — 43 source-backed rules, complexity routing, and API parameter recommendations, grounded exclusively in official Anthropic documentation.

Pipedrive CRM MCP server for AI assistants like Claude — 300+ tools covering the full Pipedrive API. Built by Nubiia.

A fuzzy-search picker for resuming Claude Code sessions across every project — fzf menu, rich preview, live sort, directory filter, quick resume, bilingual UI, and mobile Remote Control.

🍪 Your Claude subscription usage in the macOS menu bar

20 runnable LLM agent design patterns in Python, benchmarked, traced, offline-compatible. ReAct, multi-agent, constitutional AI, and more.

Companion Colab notebooks for 'Generative AI for Network Engineers: From API to Production — Volume 1' by Eduard Dulharu

Secure, local-first MCP server exposing ArcGIS Pro's ArcPy engine over stdio JSON-RPC.

MCP-сервер для кабинетов Wildberries и Ozon: продажи, остатки, цены, финансы, отзывы через Seller API напрямую, без браузера. 793 метода schema-driven, safety-гейт на запись. Подключает ИИ (Claude Code, Cursor, Codex, ChatGPT) к API WB и Ozon. Open-source MIT.

Portfolio case study generator built as a Claude Code skill. Turns messy project notes into recruiter-ready UX, product, and design case studies in 9 story formats (STAR, Hero's Journey, Before/After/Bridge, and more).

Upkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI workflow.

A Skill for Anthropic Claude that enables Claude users to more easily create secure computation applications that use fully homomorphic encryption. The initial commit demonstrates an 11% improvement over non-skill Claude in satisfying application goals, at a cost increase of roughly 50% in tokens on the test suite.

Engineering best practices that AI coding agents actually apply — 40+ skills, from secure coding and cloud to compliance and UX writing. BUILD + AUDIT modes. Measured: best-practice coverage 59% → 98% vs. the same model unguided.

Claude Code learns from itself. Persistent memory, multi-agent orchestration, and a scientific experiment engine that proves which rules actually work.

Claude Code Agent Teams — Multi-agent orchestration from your terminal (Opus 4.6)

Full-stack SDLC plugin for Claude Code & Codex — from idea to merged PR, autonomously. 25 skills, a local code knowledge-graph, cross-session memory, parallel agent orchestration, and an absolute destructive-command guard.

AI-powered native desktop code editor — Tauri 2, React 19, Monaco Editor. Multi-provider AI, agentic tool-calling, technical debt analysis, and full IDE features.

The whoburnedmore CLI — count what your AI coding agents really burned and submit to the public token leaderboard. Source of the npm package `whoburnedmore`.

See where your Claude Code tokens go — cost per call scales 4.3x with context size. Hooks + SQLite + dashboard + MCP server for context window forensics.

Java-implemented extensible AI Agent runtime — direct Anthropic protocol connection / Spring Boot 4 assembly / multi-tool collaboration / Web UI + CLI dual-mode.

rust-in-peace — agentic security review for Rust: autonomous find/triage/patch for unsafe/FFI memory bugs, panic-DoS, and deserialization-trust flaws (Miri / sanitizer / panic / hang detectors). A Rust-security fork of anthropics/defending-code-reference-harness.

Collection of Canvas LMS and Gradescope tools for the model context protocol. Query your courses, find resources, and chat with your upcoming assignments.

Skill-first AI coding agent in Rust — injects only the context your task needs. No prompt bloat. Single binary, no runtime.

💻 Control AI agents to automate tasks on computers, enabling true autonomy with browser, terminal, and desktop interaction. Perfect for developers.

A Multi-Agent Research System using Claude Code Skills. it is inspired by Anthropic claude-agent-sdk-demos

Stateful AI agents for Go and Postgres, transaction-safe.

Canny MCP Server for Canny API integration with AI Assistants. Features Jira linking, batch operations, ETA management, company MRR tracking, and PM-focused workflows.

Enables LLM integration with OpenAPI-defined services through function-calling JSON

MCP server for TDM payment integration. Enables AI agents to handle payments through Model Context Protocol.

A shell widget that generates bash commands from natural language using Claude

Structured wrapper for autonomous AI coding with Claude Code. PRD-driven task planning, atomic verification, and bash loop execution.

Durable contract-driven goal execution for Claude Code. A subagent judge gates completion against an explicit Definition of Done.

𝚑𝚊𝙺𝙲 your way into Claude 3.5’s new Computer Use API! Deploy Metasploit, automate exploits, and make Claude your AI-powered hakcer sidekick. Drink all the AI's HACK ALL THE THINGS. Shenanigans included. 🏴‍☠️💻

A curated collection of production-ready Claude Code sub agents for task automation, code review, debugging, and more. Easily reusable and customizable for your own Claude Code workflows.

⚜️ An MCP server for context compaction and recycling in Claude Code

On-device AI agent engine for mobile apps — embedded Node.js worker with Claude LLM, file tools, code execution, git, and extensible MCP device tools

📐 A minimal viewer for LLM-authored diagrams. Local-first, schema-driven, no account, no cloud.

A local desktop app for creating AI companions with unique personalities, emotional depth, and persistent memory.

Waybar module for Claude Code usage tracking on Linux. Shows 5-hour and 7-day rate limits, daily token usage and spend via ccusage, and live session stats in a GTK4/libadwaita popover. Built for Arch Linux, Hyprland, and Omarchy. A CCSeva alternative for Wayland.

Scan, map, and visualize your Claude Code setup. Find duplicate agents, conflicting triggers, and orphaned CLAUDE.md files before they silently break your workflow.

Switch between Claude Code accounts instantly. Per-terminal isolation, API key fallback, auto-update.

🎭 Over-engineered statusline for Claude Code with provider-component architecture, TTL-based caching, parallel goroutines, and YAML configs. Because printf is for quitters.

Claude Code plugin — AI-powered autopilot for managing open source contributions. Track PRs, respond to maintainers, discover issues, maintain velocity.

Profile manager and plugin marketplace for Claude Code. Per-profile MCPs, skills, agents, and slash commands. Multi-agent teams. macOS, open source.

Automatic Langfuse tracking for Claude Code

Patterns and insights about yourself, picked up your Wispr Flow chats

Fast terminal UI and CLI for testing, debugging, and automating Model Context Protocol (MCP) servers. STDIO, SSE, HTTP, Streamable HTTP. Built on the official MCP Go SDK.

12 production-tested skills for Claude Code CLI — SEO/GEO, WordPress, content creation, marketing, ebook publishing, VPS management, AI agents, context engineering, token optimization, memory persistence, distribution. By TheGEOLab.net

Deterministic decision-intelligence MCP server for AI agents — 17 tools (bandits/LinUCB, HiGHS LP/MIP, PageRank, Monte Carlo, CMA-ES, conformal). Sub-25ms. Zero LLM cost. 11 free, no key. Listed on the MCP Registry & Glama.

🚨 The leaked source code of Anthropic's Claude Code. Explore 512k+ lines of TypeScript revealing multi-agent swarms, MCP integrations, Bun runtime, and a React/Ink terminal UI.

SAP SuccessFactors MCP server — 43 HR tools for Claude Desktop & Cloud Run. Query employees, permissions, time off, hiring, compliance, and more via natural language.

🎓 Official Anthropic Learn certifications showcasing expertise in Claude AI, API development, Claude Code CLI, and Model Context Protocol. Verified achievements from Anthropic's Skilljar platform documenting the journey from AI fundamentals to advanced MCP implementations. Each certificate is independently verifiable through unique

SWI-Prolog as a logic calculator for LLMs — MCP server and Python library

AI coding plugin that gives you an entire engineering team — CTO, SRE, DBA, Security Engineer, and more — as AI skills.

Glass Box Framework — runtime constitutional verification for AI answers. Trust Cards with claim-level reasoning chains, formal ECS scoring, the 7-angle Glassbox Court red team, and deterministic audit logs. MCP-native.