مهارات للغة العربية لأدوات ووكلاء الذكاء الاصطناعي

Agent skill for VASP result analysis, including energies, DOS, bands, magnetism, voltage, and NEB.

Multi-platform agent skills (Claude Code + Gemini CLI + OpenAI Codex) for EU AI Act compliance, anchored on ISO/IEC 42001 (AIMS) and ISO/IEC 27090 (AI cybersecurity). Citation-grade. Decision-support, not legal advice.

Skills repository for RISC OS agents

给 Codex 一篇论文、作者代码仓库，或者一个实验文件夹来复现整篇论文。并且这个 skill 会提醒 Codex：先检查数据、代码、实验流程和结果证据，然后严格检查实验是否按照论文逻辑复现完毕。

A profession-agnostic Agent Skills OS that interviews how you work, compiles a personalized workflow architecture, and improves it from evidence.

Lecture

OpenClaw skills by Garibong Labs

A simplicity-first skill for reviewing architecture, refactors, APIs, and testing strategy without adding unnecessary complexity.

Public sanitized agent skills by SwiftAdviser

Plugin for using localstack and awslocal.

Skills for developing software carefully and steadily. Plan tasks, review code, and refine design to improve overall quality.

这是一个社会化能力训练Skill，同时是一本精简版的社会化指南。以《乌合之众》《关键对话》《人情世故大全》三本经典为理论根基，便于大家能够更好的进行社会化能力的训练提升。

AlphaMeta is an IBKR (Interactive Brokers) trading tool providing real-time market data for stocks, options, futures, and crypto via a standardized REST API.

An Agent Skill for reviewing translated scales, adapted questionnaires, paired surveys, and pre-launch survey quality. For OB, management, marketing, psychology, and social science researchers.

Evidence-informed Indonesian and English copywriting skill for AI agents

The headhunting firm for your AI agent skills — source, vet, place, and keep your skill library clean. 为 AI agent 物色/背调/落位并长期管理 skill 的"猎头公司"。

Ready-made OpenClaw skills for operating WhatsApp via the TimelinesAI public API

A reusable agentic coding starter kit (Claude Code) for web projects

A collection of shareable, high-quality AI coding agent skills and workflows. These skills provide structured guidance, recipes, and helper scripts to make LLM agents significantly more effective at complex codebase tasks.

Codex + Obsidian LLM+wiki loop for task-driven agent memory, durable result writeback, source boundaries, and lint.

Scan every AI agent skill on your machine for prompt injection and malicious code. Fast local rules by default, with optional local LLM review for deeper context.

Reusable Agent Skills for ChatCut talking-head editing and AI-driven publishing to Xiaohongshu, Douyin, and WeChat Channels

Claude Code meta-skill: single entry point for all frontend design, animation & 3D — detects your stack, sets direction, routes to 24 specialist skills.

Create Apple-style bento grid cards as self-contained HTML files for AI coding agents, with pixel-perfect output and no design tools required

Automate Odoo development tasks including addon reviews, OCA migrations, test writing, and OWL frontend changes.

Guide your agent to effectively fetch structured, verified knowledge from Cala

Light as air, firm as law. Spec-driven AI coding with hooks.

Local-first personal AI context loop for Code Agent conversations

A skill that evaluates whether a suggested change is truly worth making before giving advice or editing.让你的agent三思而后行

A Skill that teaches a coding agent (like Claude Code) how to create a statusline

Write, review and improve SwiftUI: state, composition, performance, animations, accessibility and iOS 26 Liquid Glass - Agent Skill

🔥 Code reviews that hit different. A Claude Code skill for brutally honest roast-style reviews with actionable fixes.

Ship an iOS app to App Store review end-to-end via the App Store Connect API — an agent skill. ~90% automated, config-driven, SOLID clean-architecture.

Local-first semantic search across tens of thousands of agent skills (SKILL.md) for Claude Code, Codex & OpenClaw — describe your task, get ranked matches with install commands. FAISS + Ollama, no API calls.

Agent Skills for integrating Outlit customer journey analytics

Build a controllable Chinese long-form fiction system with outlines, character files, continuity checks, and chapter-by-chapter tracking

Open-source Agent Skill that turns any LLM agent into a residential property-management maintenance coordinator: work-order intake, triage, severity classification, tenant-side troubleshooting, and vendor routing.

Agent Skills for building on the XRP Ledger with AI agents: xrpl.js, XLS standards, xrpl-go, and XRPL EVM.

Asolytics API agent skill — App Store Optimization (ASO) API for App Store & Google Play keyword research, app rankings, keyword metrics, competitor analysis and store charts. For Claude Code & OpenAI Codex.

Learn Harness Engineering by Building a Mini Openclaw

The Spiel Engine turns your actual build sessions into publishable content, so you don’t need to stop working to create posts

Compañero de lectura activa con 6 modos: Explorar, Leer, Sintetizar, Conectar, Activar y Exportar. SKILL.md para Claude Code.

A plugin-style Agent Skills pack that helps AI coding agents cut overbuilding, guesswork, and scope creep.

Harness-agnostic single Agent Skill for Multica: the full multica CLI, machine onboarding, and an explore->work->review->qa->learn board pipeline. Runs in Claude Code, Codex, Gemini, OpenCode, and Pi. Landing: cskwork.github.io/multica-skill

A local dashboard and agent skill for visible, reviewable data transformation workflows.

A collection of simple AI skills

🩺 A GitHub Action to validate Agent Skills against the official specification with helpful diagnostics

32 AI agent skills for credit, finance, data intelligence, and document generation — by Steven Crawford-Maggard (EVEZ)

Agent skills — reusable prompt modules providing specialised domain knowledge

Agent skills for software delivery, from requirements gap analysis to reviewed, shipped code. Supports Claude Code, Codex, Cursor, Copilot, and OpenCode.

Search Israeli restaurants, check availability across date ranges, and get booking links. Agent Skills format for OpenClaw, Claude, Cursor.

This repository provides examples of Google's ADK agents equipped with extensible skills via MCP servers and demonstrates how to expose them to platforms like Gemini Enterprise using the Agent-to-Agent (A2A) protocol.

⭐ 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!

Claude Code skill for cross-model review. One command packages files + prompt for ChatGPT Pro deep reasoning.

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

Compile any Claude Agent Skill into a multi-agent Workflow — a meta-workflow that recovers the parallelism hidden in a skill's prose and emits a fan-out · pipeline · adversarially-verified Workflow.

Cross-platform end-to-end AI/software engineering workflow skill for Claude Code (plugin marketplace, 10 modes).