Best Meta Claude Code Skills (71)

71 open-source Claude Code skills for managing prompts, memory, context and other skills, ranked by GitHub stars with one-line install commands. Top picks: Ponytail, Awesome Llm Apps, Caveman.

Ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

meta 195085★ by DietrichGebert ★ Featured

Awesome Llm Apps

100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.

meta 145107★ by Shubhamsaboo

Caveman

why use many token when few token do trick. Skill + local proxy for coding agents: shorter answers, smaller tool output, every original recoverable.

meta 121637★ by JuliusBrussee

Claude Mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

meta 118510★ by thedotmack

Omniroute

Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors

meta 89022★ by cheaper-inference

Ruflo

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

meta 82128★ by ruvnet

Mem0

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

meta 69262★ by mem0ai

Openinterpreter

A coding agent for open models like Kimi K3.1 and GLM 5.3

meta 68918★ by openinterpreter

Get Shit Done

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

meta 64127★ by gsd-build

Hindsight

Hindsight: Agent Memory That Learns

meta 62090★ by vectorize-io

Mempalace

The best-benchmarked open-source AI memory system. And it's free.

meta 60634★ by MemPalace

Cliproxyapi

Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Devin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini Series, GPT Series, Grok Series, Claude model through API

meta 59048★ by router-for-me

Private Gpt

Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.

meta 57646★ by zylon-ai

Cowagent

Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.

meta 48019★ by zhayujie

Magpie

Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.

meta 39263★ by yetone

Nuwa Skill

你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

meta 38673★ by alchaincyf

Context Mode

Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OMP, OpenCode, Gemini CLI, Copilot CLI and 4 more agents. Zero telemetry.

meta 34320★ by mksglu

Claude Code Templates

Open-source registry and CLI for Claude Code components: agents, commands, skills, hooks, MCPs, settings and mods

meta 34018★ by davila7

Claude Hud

A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress

meta 29270★ by jarrodwatts

Beads

Beads - A memory upgrade for your coding agent

meta 28855★ by gastownhall

Distilly

Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill(原同事 Skill).

meta 26688★ by titanwings

Memori

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

meta 17601★ by MemoriLabs

Cc Haha

本地优先的跨平台 Claude Code / AI Agent 桌面工作台:多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物;支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git worktrees, diffs, skills marketplace, multi-model, Computer Use, task-aware desktop pets; remote via WeChat, Feishu, DingTalk, Telegram, WhatsApp & H5.

meta 15502★ by NanmiCoder

Ffmpeg Skill

Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.

meta 8509★ by kajisho5

Blender Skills

94 specialist Blender skills for Cursor, Claude Code, Kiro & Codex -> MCP-powered production pipeline from blockout to engine export.

meta 4425★ by arjun988

One Skill To Rule Them All

The meta-skill that improves your skills, including itself. Turns the corrections, judgement calls and repeated workflows of your sessions (autonomous or human-led) into small skill updates and new skill candidates, each with its evidence and reason. Nothing touches a skill until you approve it. Augmented Expertise in practice. CC BY 4.0.

meta 3978★ by rebelytics

Memsearch

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

meta 2913★ by zilliztech

Eli5

ELI5 — A Claude Code skill that explains anything to anyone: kids, managers, engineers, parents. Adapts tone, vocabulary, and analogies to match the audience.

meta 2029★ by DreambigOu

Hivemind

Hivemind turns your traces into reusable skills across agents

meta 1657★ by activeloopai

Claude Video Vision

Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis

meta 1520★ by jordanrendric

Fluent Korean

Claude Code가 명확한 한국어를 구사하게 만드는 output-style 플러그인 | Claude Code output-style for clear, fluent Korean

meta 1516★ by snflkd

Awesome Claude Code Mods

8,000+ Claude Code mods, with what each one can access before you install it. Context and usage meters, prompt cache warmers, status lines, guards and more, with install hints.

meta 1041★ by karanb192

Claude Council

Claude Code plugin that asks several AI coding agents the same question and shows their answers side by side. Gemini, OpenAI, Grok, Perplexity, Kimi and any model OpenRouter routes to over API; codex, antigravity, grok, kimi and cursor CLIs on subscription auth; ollama locally. Codex specialists take coding tasks on their own branch (experimental).

meta 950★ by hex

Unbrowse

Unbrowse - agents use the web faster without a browser

meta 936★ by unbrowse-ai

Citadel

The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.

meta 934★ by SethGammon

Playwright_Mcp

invisible playwright mcp: Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use.

meta 867★ by oss-invisible

Claude Code Ios Dev Guide

A comprehensive guide for setting up Claude Code CLI with PRD-driven workflows, extended thinking (ultrathink), and planning modes optimized for Swift/SwiftUI iOS development.

meta 863★ by keskinonur

Context Attachment Manager

A local plugin for image-heavy chats in Codex, Claude Code and other AI agents: earlier images become short placeholders instead of going out with every message, the model fetches the original back by its ID (also after compaction), and the prompt cache keeps working.

meta 808★ by chipfighter

Claude Smart

Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.

meta 796★ by ReflexioAI

Hippo Memory

One memory for every agent you'll ever use. Hippo writes what you teach a coding agent into a store in your repo, and your other agents read that same store.

meta 795★ by kitfunso

Recall

Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.

meta 770★ by raiyanyahya

Soul.Md

The best way to build a personality for your agent. Let Claude Code / OpenClaw ingest your data & build your AI soul.

meta 711★ by aeonfun

Xactions

X/Twitter automation toolkit: scrapers, CLI and an MCP server with approval-gated write actions, no paid API.

meta 662★ by nirholas

Misakanet

Re-debugging Solved Failures? No Way. 1000+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org

meta 565★ by Ikalus1988

Adversarial Spec

A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus.

meta 559★ by zscole

Operator Memory

The self-improving context engine for coding agents.

meta 520★ by aerovato

Math Modeling Skills

数学建模竞赛完整工具链:从拿到赛题到交出论文,一条龙解决。 覆盖 国赛 CUMCM(A/B/C) 和 美赛 MCM/ICM(A-F) 全部题型。

meta 449★ by Lupynow

Project Butler

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

meta 377★ by JamesShi96

Developer Kit

Modular plugin marketplace for Claude Code and agentic CLIs, with validated, spec-driven skills, agents, commands, and workflows for Java, TypeScript, Python, PHP, AWS, and AI.

meta 372★ by giuseppe-trisciuoglio

Claude Android Skill

Claude Code skill for building modern Android apps following best practices.

meta 362★ by dpconde

Prompt Architect

Agent skill for analyzing and improving prompts using 31 frameworks across 7 intent categories. Works with Claude Code, Gemini CLI, Cursor, Copilot, and 30+ Agent Skills compatible tools.

meta 337★ by ckelsoe

Claude Db

Free, open-source memory for Claude Code. Your own database, no cloud, no subscription.

meta 236★ by Avijit07x

Blender Kiln

Claude Code plugin: describe an object or show a photo, and Claude builds a clean 3D model in Blender, for games, the web, AR or 3D printing. It animates characters too. New in 3.0: Kiln Studio, a local page to view, check and fix your models with Claude.

meta 226★ by elithril

Embedded Debugger Mcp

MCP server + CLI + Codex/Claude skill for embedded debugging via probe-rs or OpenOCD — ARM Cortex-M, RISC-V, and Xtensa (ESP32), with AI crash diagnosis

meta 218★ by Adancurusul

Skillcompass

Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.

meta 214★ by Evol-ai

Pitchcraft

汇报.skill · pitchcraft — Structured persuasion for tech leads, PMs, and founders: kickoff, status, wrap-up, pitch, and solution selling on one 5-part framework (Hook→Context→Proposal→Evidence→Ask), with AI material intake and a pre-submit checklist. Works with Claude Code, Cursor, Codex, and more.

meta 202★ by moshuying

Attention Control

Air traffic control discipline for agent output. Written for a reader with ADHD.

meta 157★ by aaddrick

Deepeval Bcg

Detects structural prompt weaknesses before they affect production outputs — improving the quality, consistency, and reliability of every future generation across the pipeline.

meta 2★ by EvXata

Principle Deepdive Html Style

A reusable visual recipe for single-file analytical HTML articles - agent skill for Claude Code and Cursor. Dark/light theme, inline SVG diagrams, zero external dependencies, under 300KB.

meta 2★ by Misakakuroko

Agent_Memory

Simple file-backed memory layer for Claude agents. Markdown files on disk.

meta 1★ by adedayoagarau

Claude Code Dna

The behavioral operating system for Claude Code agents — distilled from 11 deeply-read libraries (179 skills + 99 agents + Karpathy 4 laws + memory architecture). Drop-in rules, scripts, and curated catalog.

meta 1★ by huangji6693-max

Good Decisions Only

A math-backed AI decision analysis agent which helps you take "good-decisions only" for your Career, Relationship or Life decisions, Investment or Financial bets, or for Opportunity evaluation with uncertainty. It uses following 6 framework of EV, Base Rates, Bayes Theorem, Sunk Cost, Survivorship Bias & Kelly Criterion.

meta 1★ by Pruthavirajsingh

Saiyanmod

Claude Code mod: a subagents progress bar with mascots per model.

meta 1★ by MHermand

Skill Creator

Create, edit, and benchmark your own Claude Code skills.

meta 0★ by Anthropic

Dsh Claude Agent

Claude Agent provider for DeepSeek Harness: opencode's official Claude Agent SDK approach, >90% steady-state prompt-cache hit, and Anthropic's current auth and branding policies.

meta 0★ by clioo

Prompt Optimizer

A Claude Code agent that turns vague task requests into grounded, structured specs for clean handoffs to your implementation agent.

meta 0★ by codyhxyz

Resume Writing Skill

Anthropic Claude skill that turns a ~30-page brain-dump (Typeless / Obsidian) or an existing resume into a structured US-market resume + moderncv-banking LaTeX + a personalized teaching handbook calibrated to a four-tier diagnosis rubric.

meta 0★ by zyziyun

Spec Weaver

Top AI Prompt Optimizer 2026 – Transform Vague Requests Into Structured Dev Specs

meta 0★ by tech-guru254