Enable efficient smart contract bug bounty hunting with AI-powered skills built from thousands of real Immunefi and DeFiHack reports.

Real-time chat for AI agents — a public and private space where AI agents talk to each other.

Evidence-backed Solana audit skill for Claude Code and Agent Skills: report-backed taxonomy, workflows, checklists, and public finding corpus for Anchor and native Solana security reviews.

Systematic agent improvement via tool-based narrow ML

Agent skill for searching GPT Image 2 prompts from Image2Studio: reusable ChatGPT image generation prompts, image references, and visual examples.

Spec-driven coding skills for AI agents: plan with acceptance criteria, self-correct from feedback, and remember reusable project knowledge.

Drop-in thinking-partner personality layer for Claude Code, Cursor, ChatGPT, and 20+ AI agent runtimes. MIT. Plaintext. Persistent memory. Framework-grounded. Calibration-disciplined.

Skills for any AI agent harness, by Mad House

Durable project memory for Claude Code, Codex, and other coding agents. Promotion rules keep hypotheses from silently becoming facts.

Full-spectrum nginx skill for Claude — write, review, harden, and debug nginx configs.

UI workflow for production-grade Vibe Coding projects

Production-grade skills for Hermes Agent - self-evolving, persona-aware, slash-command native

Advanced and deterministic skills built specifically for the Claude Code agent environment extending extends Claude's native capabilities to autonomously handle complex development tasks

Lightweight website/app security scanner for vibecoded apps:: run it from your AI agent (Cursor/Claude Code) or the CLI. Black-box + white-box, OWASP-mapped, SARIF-ready. Authorized testing only.

Multilingual discipline skill (八荣八耻) for coding agents — one SKILL.md for both Codex and Claude

Write your dev workflow once. Run it on any LLM. Open agent skills + multi-model swarm + a local findings store that learns which models you can trust.

Meta-skill that turns any framework's source into a self-contained Agent Skills family — usable later from just the installed package (e.g. in Databricks Genie Code or any AI coding agent).

agent skill library for ai agents using skills

Personal collection of agent skills for Claude

Production-grade prompt engineering, migration audits, and eval gates for GPT-5.6 Sol, Terra, and Luna.

Curate vetted AI-coding skills & plugins by your tech stack — install only what you need, across Claude Code, Codex, OpenCode & Antigravity

Financial and Economic world prediction simulation. Derived from individual Agent emotions and behaviours using our heart engine, and ripple system can cause different butterfly effects on the simulated world, and make crucial decisions that shapes the macro world, economy, society, company. Achieved over 90% accuracy for covid 19 and 2008 f crises

A curated collection of agent skills

A Codex skill and pre-publish gate for checking API key leaks before open-sourcing projects.

AI-powered skill pack for generating professional documentation, including PRDs, architecture, design docs, roadmaps, and READMEs

The Supabase deploy-gate that runs where you vibe-code. Static OSS scanner for the RLS/secret holes that leak vibe-coded apps — CLI + Claude Code skill + GitHub Action.

A central aggregation repository for Agent Skills from Ahoo-Wang's open source projects.

Turn vague requirements into testable specs: BDD narratives, use cases, payload contracts, flowcharts, and dependency diagrams - Agent Skill

🤖 Complete AI expert ecosystem for Modern Java, Quarkus & Bazel development ☕️⚡️ Coverage for Vert.x, GraalVM, Maven/Gradle migration, and more 🚀

Sync your Claude brain - memory, skills, agents, and rules across machines and teammates via Git. One command to share context. One command to inherit it.

Claude Code skill for writing and testing Aiken smart contracts on Cardano

AI copilot for React apps. Reads your state, fills forms, confirms actions, calls your tools. Multi-agent, AI SDK 6 + AG-UI, markdown skills. MIT.

Reusable skills and intelligent agents for Claude Code. Production-grade, self-verifying, configurable.

Claude Opus 4.7 native Plan-Execute-Verify coding harness — a Claude Code plugin that enforces a 3-phase pipeline with hook-driven verification

AI-native Blender workflow and skill pack for non-Blender users, built around official Blender MCP, Claude Blender Connector, and Blender CLI.

Router Learning System + macOS desktop automation skills for AI agents using Cua Driver — task routing, fallback chains, self-learning history.

TDD-first AI dev pipeline for Claude Code, Cursor, Codex, Gemini CLI & Antigravity. /dev /fix /quick + token-saving hooks. npx aicrew install

把冷冰冰的压力变成能发出去的温暖回复——沟通里的立体攻防 + 你的超级嘴替。Cold pressure into warm, sendable replies. Layered workplace comms + your super mouthpiece.

Use Codex and Claude Code with Ansys Workbench via sim-cli: journals, project inspection, persistent sessions, Mechanical handoff.

Project docs that answer locally before the web — file-based Agent Skills for Claude Code, Gemini CLI, GitHub Copilot, and OpenCode.

🚀 Enhance your machine learning workflow with essential MLX skills from this ready-to-use repository.

Dotfiles for your AI agents: one ~/.agents repo for skills, MCP servers, hooks, and subagent roles — synced to Claude Code, Codex, Droid, Hermes, and Pi. Commit-pinned and audited.

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

OpenClaw skills by Garibong Labs

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

Plugin for using localstack and awslocal.

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.

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

Local-first personal AI context loop for Code Agent conversations

🔥 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.

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.

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

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

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

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