⭐ All-in-one AI companion! Super Agent Party = Self hosted neuro sama + openclaw! ⭐ 全能AI伴侣！超级智能体派对 = 自托管neuro sama + openclaw!

A lightweight local SkillHub and MCP bridge for sharing agent skills across AI agents.

Real-time interview copilot CLI. Hears the question and surfaces the answer you already prepared from your local Markdown knowledge base — verbatim, in milliseconds. Instant recall instead of LLM hallucination.

Agent-friendly CLI for searching the Releases.sh catalog of release notes, changelogs, and product announcements

Agent skills for frontend UX/UI design that actually looks good

Claude Code pack for Instagram & Facebook content creators: FTC/Meta disclosure, copyright, brand-safety & no-fabricated-stats guardrails + skills for Reels/carousels/Stories/captions/repurposing/sponsorships, loops & review agents. Not legal advice.

Agent memory over an Obsidian vault — bash + ripgrep, no database. A restricted-TOML vault registry, a curated Agent Index, a wikilink graph, and a Projects→Sessions lifecycle. Ships the vaultmem CLI + memory skills as a Claude Code plugin.

Curated, production-tested Codex skills and reusable workflows for reliable agentic work.

《末日NPC都不太正常》的 Agent Skills 仓库 · 可复用工作流技能

Reusable Agent Skills for coaching, reasoning, document conversion, and publishing workflows. 通用 AI Skills 仓库。

Agent Skills for building production-grade REST APIs with Go and the Gin framework

Octomind Agents Registry

My AI Agent Plugins. There are many like these but these are mine.

Torii: Agent plugin for SUMO with OSM-to-SUMO tools, TLS review, routeability probes, and evidence-aware feedback diagnosis.

Portable Agent Skills that turn repositories into agent-ready workspaces with AGENTS.md orientation, an OKF/LLM-wiki knowledge layer, reusable skill creation, and harness adapters.

Portable Claude Code skills

Floom Starter Pack. 65 hand-picked AI agent skills for Claude Code, Codex, Cursor, Kimi, OpenCode. One install, auto-activates. +16.2pp pass-rate lift.

面向 Codex、Cursor、CodeBuddy、TRAE 的中文 AI IDE 项目初始化模板，内置多角色协作、Skills、MCP、Hooks 与安全验证。

A practical template for Building AI Agent Skills with Python, FastAPI, and Domain-Driven Design (DDD).

AI-powered multi-agent stock analysis skills for A-share, Hong Kong, and US markets

Provide standard AI/ML task definitions as portable skills for use with major coding agents like OpenAI Codex and Claude Code.

Agent-agnostic skills that turn a fuzzy app idea into evidence-backed AI execution.

Portable AI-engineering skills for Claude Code, Codex, and coding agents: bounded scope, mini-specs, vertical slices, verification, ship gates, and handoff.

Agent skills for Study Dart

A modular, composable, production-grade Android skill system for agentic engineering workflows, designed to behave like a senior Android Staff Engineer under real-world constraints.

`opencode-session-toolkit` is a skill for reading the local OpenCode SQLite database, querying sessions across directories, inspecting messages and schema details, and exporting matched sessions to Markdown files.

AI Political Personality Modeling Framework — reconstructing personality structures, not labels. Powers NPCs for Absolute Majority and standalone political simulation, debate, and character creation.

AI-agent skills for Sanskrit language

Connect your AI to Reanthesis — MCP server, agent skills, and plugins so Claude, ChatGPT, and Copilot can build flashcards from your notes and manage your study data. Your AI, your data, your cards.

Auditable .env secret manager featuring aggressive CLI safeguards and GitHub JIT access.

Grill → Gate → Build: interrogate requirements until accurate and complete, score them with an independent gate, then hand the human-approved PRD to autonomous development.

AI coding agent runtime that makes LLMs understand your codebase with repository-aware context, memory, and continuous learning

Mug is an AI automation platform for building deployed agents, real code workflows, & headless web surfaces for everyday business, integrated with any API, and accessed via email, SMS, & Slack — all built locally using Claude Code, Codex, & Cursor.

Measured, opinionated Claude Code rules for frontend work (React / Next.js / Vite / Astro) — skills, path rules, review agents, sign-off hooks, installer & plugin. Every claim backed by committed eval reports.

Graduate AI skills into cheap, fast, deterministic workflows

Skills that teach AI coding agents (Claude Code etc.) to use university HPC clusters safely — deploy, submit, monitor SLURM jobs via SSH. Currently: Tufts. Contributions welcome.

Comprehensive collection of 380+ production-ready Agent Skills (26 domains) conforming to the Agent Skills Standard, featuring native auto-discovery for Antigravity, Gemini CLI, Claude Code, Cursor, and Codex.

公开的 AI Agent Skills 合集

Make your AI agent paranoid about the right things — money in integer minor-units, idempotent mutations, timeouts + backoff, no N+1. One portable SKILL.md for Claude Code, Codex, Cursor, Copilot & more. Field-tested on real payment code.

Write agent skills once, ship to Cursor, Claude Code, Codex, Copilot and any SKILL.md-compatible agent

Skills that help AI agents build better AI agents — prompt engineering, architecture, evaluation, and more.

Reusable skills for AI coding agents (Claude Code, Codex, Forge) covering paper review, commit triage, GPU rentals, reference search, research logs, image-prompt composition, and more.

Picks and Shovels for digging AI

This repository contains small, focused skill cards that you can load into AI coding assistants (e.g., GitHub Copilot, Cursor, Antigravity, Replit Agents). Each skill is a short markdown file that teaches the assistant conventions and patterns for a given topic.

Re-usable skills for agents at Way

Claude Code skills for issue-driven development — design in a GitHub issue, ship a gated PR to green CI, and triage AI code review.

18 trust tools for AI agents — verify, score, route, compare, and delegate with confidence.

Non-custodial Solana swap & limit order engine for AI agents.

Credential broker that signs your AI agent up to SaaS dev tools, within a signed spending mandate.

Security proxy that wraps MCP servers with real-time monitoring and policy enforcement

MCP server for Google Search Console Search Analytics (read-only, OAuth or service account).

Vibes-Coded x402 agent tools MCP: reliability guards, pay tool, day-pass, prepaid.

MCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper

Zoom Revenue Accelerator server for sales insights, conversations, and deal intelligence.

VMware NSX security: DFW policies, security groups, tags, Traceflow, IDPS — 21 MCP tools.

Chainlink MCP: CCIP, CCT pools, Data Feeds, Data Streams, VRF v2.5, PoR, Automation, Functions.

Syslog receiver and MCP server for homelab log intelligence.

A documentation library for governance, risk, compliance, cybersecurity, privacy, resilience, AI assurance, and operational control practices + a Claude Code rules-and-skills pack distilled from maintaining it.

Claude Code skill bundles for hardware/maker engineering: 8 skills across 3 plugins — parametric CAD (Fusion 360 MCP-Bridge, OpenSCAD), FDM/3D-printing workflows (BOM validation, embedded UI docs), embedded systems (Victron Cerbo Modbus onboarding). Sibling to ed3design-skill-bundles.