Custom agents

RL agent for Slay the Spire 2 — headless simulator + trained model + real game bridge

Render LaTeX from any CLI agent directly in Kitty-compatible terminals

A Claude Code skill that bridges Claude Code to the Codex CLI: externalizes plan, files, conversation and conventions into an on-disk bundle, runs codex exec, validates the JSON response with jq.

Agent skill for revising research papers given an Overleaf project.

Embedded PostgreSQL for Agents

Interactive Sandboxes for AI Agent Evaluations & Reinforcement Learning on 3rd party APIs (Slack, Linear, Box, gCalendar)

DevExpress AI Skills for coding agents (.NET, JS/TS)

Snail AI 企业级 AI Agent 平台 - 让 AI 更智能，让开发更高效

A curated collection of operational system prompts and behavioral patterns for AI assistants, LLM agents, and prompt engineers. Each `.skill.md` file can be injected as a primary system instruction to enforce specific reasoning, execution, or formatting behaviors.

Zero-sidecar MCP server inside the Godot editor. AI agents (Claude Code, Cursor) inspect, author, run and SEE your game. GDScript + C#, validate-before-write, no Node.js. Godot 4.2+. Free Lite; Full adds autonomous playtesting.

Agent Skills for Palmier Pro

The One Dashboard every Voice Agent needs

NVIDIA NIM API provider extension for pi coding agent - access 100+ models from build.nvidia.com

Go-to hub for building and deploying production-ready AI Agent solutions

A fast, native browser automation CLI built from the ground up for AI agents, powered by Chrome DevTools Protocol. 63 commands covering navigation, interaction, screenshots, accessibility, network mocking, visual diffing, test generation, and more — all from a single binary.

让 Agent 安全常驻桌面的独立 dsh 客户端：官方 Web UI 原封不动，长任务常驻托盘，精选插件先审查、再安装。Independent dsh desktop client: the official Web UI untouched, long tasks alive in the tray, curated plugins reviewed before install.

A concise, opinionated set of design rules for coding agents to produce better user interfaces.

Executable security regression testing for agentic applications and MCP-integrated systems.

Hermes Agent weather plugin — NWS-grade model imagery, NEXRAD radar, and verified meteorological calculations. Pure Rust stack.

An agent-native runtime for embedded devices, powered by PocketJS. Build installable, updatable JavaScript apps for people and agents.

Sync reMarkable to PDF and MarkDown via either USB or Wifi. Backup your device and let your AI agents reason over the content.

AI agent orchestration for open and closed source — a fully customizable fleet of AI agents covering every level of project maintenance, from brainstorming to full autonomy

Unofficial Grafana Agent Observability plugin for Hermes Agent

Cloud FinOps Skill & MCP by OptimNow. FinOps Foundation aligned knowledge for AI agents: cloud cost (AWS/Azure/GCP/OCI), AI inference economics, Kubernetes, data platforms, allocation, chargeback, anomaly management, waste detection, GreenOps. Installs into 12 AI tools, or connect the hosted MCP server by URL. Refreshed twice a month.

A powerful command-line interface for Redmine, enhanced with first-class AI agent capabilities via Skills and MCP integration.

Documenting the internals of Fingerprint Pro's commercial agent, not the open-source FingerprintJS library

Agent Skill and repository template for reliable software development from constrained chat AI environments.

多agents协作平台

Its Factorio for coding agents

These are agent templates that can be used by teams to adopt a developer agent workflow for their repos.

Desktop agent built on H Company's Holo3 vision-language models

日本語 Markdown ノートのローカル検索 CLI 👀 — BM25 全文検索 (SQLite FTS5) + optional なローカル semantic/hybrid。単一バイナリ・外部 API 不使用、AI コーディングエージェント向け。

Agent skill for Pandadata-based A-share after-close daily market review reports.

[ECCV 2026] Official code implementation for paper "PathAgent: Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoning"

Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents

UIKit Max - Agent skill that teaches AI coding assistants to write correct, modern, and performant UIKit code from iOS 13 through iOS 26

File-based multi-agent project workflow for Claude Code and Codex

Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workflow.

ARCHIVED. See https://github.com/ephemeraHQ/xmtp-agent-examples instead.

An Agent Skill for translating papers from arXiv

Caveman mode for Pi coding agent - ultra-compressed communication that cuts ~75% of output tokens

Make your website agent-ready: a coding-agent plugin for Claude Code and Codex that adds WebMCP tools to your web app

A markdown knowledge base for agents that's CLI and skill driven. Full featured with Google's OKF support and network vaults to share between users and systems.

Opslane finds the bugs your users run into by watching real user sessions, and writes the fix. You review and merge.

Code Trace Tree is a JetBrains/VS Code plugin that traces code in a tree structure with AI support. Build and display code workflows as trace points. Add traces from the editor menu or the Agent Skill; double-click to jump to the source.

Important: This creates a Technocore agent identity and signed check-in. It does not guarantee a $FLOP airdrop. Never use a wallet seed phrase, exchange key, or a private key you use anywhere else.

一款基于AI技术帮助你智能学习/复习的软件喵！

Web search, deep research and fetch content tools for Pi Agent, powered by Exa

Agent Skill: turn a character image into a looping transparent sticker pack (WebP/GIF/PNG + ZIP).

Keep your Mac awake while your code agent works — even with screen off, lid closed

Auth0 Agent Skills

Yet another minimal and lightweight terminal multiplexer built for the agent era.

A fast, Lua-scriptable AI coding agent for the terminal

Local audio-reactive rhythm maps and reusable timing packages for visual creators and coding agents.

优化拓展pi-agent，在Terminal-Bench 2.0 评测体系，任务完成率约48%。

data-analysis-report-agent

Shared Actions used with GitHub Agentic Workflows

AI Agent Engineering 101 — SeoulTech 2026 Fall. Lecture notes and PR-based assignment submission.

专门为 AI Agent 设计的本地数据分析与处理技能包（Skill），旨在解决日常办公场景下的高频、复杂数据分析任务。

AI-powered full-stack development on Android with app-managed PRoot Linux, Termux integration, and an Agent for on-device coding, builds, testing, and debugging.

IADE：A New Development Platform for the AI Era—An Integrated Agent Development Environment

Agent-ergonomic CLI for task/backlog management with pluggable backends (markdown, sqlite, remote trackers)

Shopping agent research project

半调纸拼贴风信息动画 Agent Skill · Halftone paper-collage info-graphic animations from voiceover scripts (HyperFrames, no image models)

EvoX：一个强大的多智能体协同框架，用于构建可演化、可优化的多Agent系统

Pivot (T3.14): T3 Code fork pivoted to omp — remote-ready agent control surface.

OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation

Agentic Product Development Operating System

Local API simulation and test evidence for AI-assisted development.

Lista completa com ferramentas desde IDE, Agents, CLI...

A native macOS overlay for AI provider usage and agent activity.

AI for Oracle developers (no 23ai or 26ai required)

Max is a federated data connectivity layer that puts searchable data next to your deployed agent

Deterministic, read-only Git evidence for coding agents and automation. Standard-library Python CLI.

An agentic environment abstraction for Agent Substrate

(ACL 2026 SAC Highlight) Repo for "Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents"

六爻纳甲筮法 Agent Skill - 开源免费版

Agent Skill for Toss Securities Open API with safe dry-run trading CLI

An open Agent Skill for extracting poster design systems and transferring them to original poster concepts.

Hades is a fully-featured cross-platform Chrome Extension agent. Hades is designed for Mythic 3.0 and newer.

Amazon Automation Skills | 亚马逊运营全流程工具集，含Listing生成、选品调研、广告策略、店铺管理，可接入AI Agent使用，Python开发

Piscord - Lightweight Discord gateway for pi coding agent. Architecture inspired by NanoClaw.

Oh My Pi (OMP) 配置合集 — 脱敏后可复用的 agent 配置、模型覆盖、hooks 和 skills

The home for the Knecht. Let agents boot, reproduce and test changes.

Research artifacts for provenance-bound agent authorization, signed effect evidence, and reproducible security evaluation.

Gate Skills is an open skills marketplace that empowers AI agents with native access to Gate's cryptocurrency ecosystem. From market analysis and derivatives monitoring to one-click MCP setup — all through natural language.

Voice Agent Framework

自用/精选的 Claude Code / Codex 技能：内容创作、客服、市场调研、SEO、Agent 工作流循环、Grok X 实时抓取与评审工具

⚔️ Benchmark your AI agent with 30 Docker-based web security labs inspired by real bug bounty findings, complete with canonical flags and reference solvers.

Permissive, modern alternative to Ghidra with Rust/Python core and first-class agentic AI integration

TRACER is a research toolkit for Lean 4 proof repair, failure reproduction, and evaluation.

🧊 300+ source-backed GPT-6 Astra 3D prompts with WebP/WebM results, X sources, and creator attribution—for Blender, Three.js, games, CAD, and agents.

X-Net — a self-hosted VPN & proxy management panel powered by sing-box, with multi-node (panel/agent) orchestration, SSH tunneling, and per-user traffic accounting.

A self-evolving skill framework for evaluable agent tasks, with reproducible multi-domain validation experiments.

agent402.tools: 500+ pay-per-call tools, metered models and finished reports for AI agents, paid per call in USDC over x402 and MPP or by card. Open source, self-hostable, MCP-native. The applied layer of agentic finance.

Modern React Guidance — authoritative agent skill for React 19+ (Actions, use, Compiler, View Transitions, Fragment refs, Activity, browser(), useEffectEvent). Optimized for AI coding agents.

Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.

SRC-6K Security Research Skills: black-box SRC and white-box audit agent package

L.A.R.R.I. = Local Agent for Remote Rigging of Inference.