Web
Global Chat
Cross-protocol agent discovery across MCP, A2A, and agents.txt. Searchable directory of 18K+ MCP servers and agents with a free agents.txt validator and MCP server for programmatic…
Productivity
hermes-ai-team
Phase-by-phase guide to building a team of Hermes agents: SOUL, memory, vault, nightly research, kanban and a chief of staff. Written to be read by the agent, not just about it. 36…
Productivity
xerg
Audit and reduce AI agent runtime spend in dollars. Use for AI costs, agent spend, token waste, runtime attribution, detector coverage, and FinOps. Works with OpenClaw, Hermes, QM,…
Research
HF Daily Deep Researcher
HuggingFace Daily Papers + arXiv 多Agent深度研究系统。 采用编排器+专业Agent架构，支持两种模式： 1. 轻量扫描模式：周期性追踪（周/月），发现新论文 2. 深度调研模式：全时间范围调研，产出全面深入的研究报告 支持动态配置、自适应关键词、周期版本控制、跨平台搜索工具适配。
Automation
crear-agente-imperio
Crea automatizaciones inteligentes (agentes de IA) en la nube de Cloudflare, paso a paso, en español sencillo, sin necesidad de saber programar. Úsalo cuando alguien escriba "/crea…
Engineering
ai-coding-ok
USE THIS SKILL FIRST on any coding task (feat, fix, bug, refactor, plan, design, brainstorm, code review, implement, add feature, write tests, 新功能, 修复, 重构) when the project contain…
Automation
cmux
MUST be read ANY time you interact with cmux in ANY way — listing/inspecting/creating/closing cmux workspaces, panes, or surfaces; reading or capturing pane/screen output; sending …
Engineering
copilot-cli
Use the GitHub Copilot CLI for agentic coding, session management, custom agents, skills, plugins, SDK integration, and Ralph Wiggum loops. Use when: (1) running Copilot CLI sessio…
Productivity
grading-claude-agents-md
Grades and improves CLAUDE.md (Claude Code) and AGENTS.md (Codex/OpenCode) configuration files. Use when asked to grade, score, evaluate, audit, review, improve, fix, optimize, or …
Automation
workflow-automation
Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry custom…
Documentation
agent-docs
Scaffold (or retrofit) a project with the docs-driven agent conventions: a root AGENTS.md as the single source of agent guidance, a thin CLAUDE.md that imports it, an append-only L…
AI / ML
agent-goal-skill
Take a rough goal description and shape it into a polished, doctrine-compliant agent goal prompt. Output is for the user to copy/paste into Codex, Claude Code (native /goal), Droid…
Engineering
claude-code-agents
Invoke Claude Code from Codex for bounded delegation to Claude Code agents or subagents. Use when the user explicitly asks to run, invoke, compare with, or delegate work to Claude …
Engineering
project-agentification
Assess repository agent-readiness, harden against failure modes, scaffold AGENTS.md / SKILL.md / MCP servers / hooks / specs from observed failures, and diagnose why coding agents …
AI / ML
metaharness
Design, evaluate, and iterate on Claude Code agents, commands, and skills with structural best practices. Use when creating a new .claude/agents/ file, updating an existing agent's…
Automation
custom-agent-router
Selects interaction mode, capability tier, risk level, task shape, review intensity, and limited redundancy for non-trivial agent work with clear goals, scope, and authority. Guide…
Research
lobster-tank
Connect an agent to Lobster Tank, a collaborative platform where AI agents tackle major scientific challenges together—researching, forming hypotheses, debating, and co-authoring p…
AI / ML
secondmind
Autonomous three-tier memory system with proactive initiative, project tracking, and social intelligence. Ingests conversations, extracts knowledge and emotions, and suggests autom…
Engineering
modularize
Cache-aware task decomposition — split large coding tasks into independent modules, define interface contracts, schedule execution waves, and execute each module as an isolated Rea…
AI / ML
conf-preference-elicitation
Builds a compact preference profile by selecting highest-information-gain questions that contrast real options across clusters, balancing known interests with uncertainty explorati…
Documentation
awl-frontmatter
YAML frontmatter standard for agents and commands: required fields (name, description), recommended (tools, model), optional metadata (version, category, color), with four-tier mod…
AI / ML
tool-schema-design
Design and validate model-facing tool schemas with precise names, action-oriented descriptions, bounded JSON parameters, explicit side effects, safe defaults, idempotency, and test…
Engineering
repo-task-proof-loop
Repo-local workflow skill for large coding tasks. Initializes .agent/tasks/TASK_ID artifacts, installs project-scoped Codex and Claude subagents, updates AGENTS.md plus the repo's …
AI / ML
zonein
Build, backtest, and run autonomous trading agents from plain-English specs. Pulls real-time signals from 500+ smart-money wallets, multi-timeframe TA, derivatives flow, and Telegr…
Engineering
minimal-agent-design
Reference for building minimal, hackable agent harnesses — linear message history over branching state, shell-based tool access over custom abstractions, and subprocess isolation f…
Engineering
agent-backend-standard
Production-grade backend engineering hub for agent/LLM systems. Load when building or reviewing any backend touching databases, establishing repository gates, or enforcing architec…
Automation
aspirations-execute
Executes a chosen goal end-to-end: runs precondition checks, intelligent retrieval, memory deliberation, subagent delegation, primary execution, fail-fast handling, archival, and d…
AI / ML
Agents
Dynamic agent composition and management system. USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available trai…
Documentation
agents-md
This skill should be used when the user asks to \\\\\"create AGENTS.md\\\\\", \\\\\"update AGENTS.md\\\\\", \\\\\"maintain agent docs\\\\\", \\\\\"set up CLAUDE.md\\\\\", or needs …
Business
raio-x:enriquecer-agentes
Transforms business diagnostics into operational context by generating `PERFIL-DO-NEGOCIO.md` and customizing any installed agents—copy, sales, ads, finance, product, positioning—w…
Automation
ir:onboarding-factory
Maintains the canonical scenario × agent fixture matrix for irrlicht. Dispatches intent to specialized subagents via the `of` CLI for creating scenarios or agents, assessing cells …
Web
aiprotocol-sbi
Deploys a self-sustaining SBI economy: creates an agent wallet on Base, funds via AIP Grant or self-payment, and launches an ERC-20 token with bonding curve and Uniswap v4 hooks th…
Productivity
codex-discuss
Facilitates iterative, non-code discussion and debate between the local agent and a second AI on open-ended topics such as strategy, decisions, writing, or planning. Orchestrates a…
Productivity
extract-best-practices
Analyzes the current session for repeated workflows, decision patterns, and error-recovery sequences, then surfaces candidates for new skills or agents after cross-checking install…
AI / ML
hephaestus-storm
Drives goals to verified completion via a force-robust Stormbreaker loop: routes work to specialists, builds dependency-ordered pipelines, and executes verifier-first hardened pack…
Automation
valet
Manages Valet agents, channels, connectors, organizations, and environment variables through the CLI, supporting creation, deployment, linking, teardown, and multi-step workflows. …
Automation
claude-managed-agents-webhooks
Receive and verify managed agent webhooks. Use when setting up webhook handlers, debugging signature verification, or handling agent session and vault events such as session.status…
Engineering
blocks-network
Non-linear reference for managing Blocks Network agents — features, configuration, CLI, IO schemas, streaming, consumer SDK, publishing, invites, troubleshooting. Use when working …
Engineering
hermes-graphify-gsd-project-integration
Use when integrating Hermes Agent, graphify, and GSD into a specific repository, especially for adding project-local graph refresh scripts, AGENTS.md guidance, README workflow docs…
Automation
orchestrating-subagents
Manages subagent delegation: selects agent type, model, and effort level by role (explorer, implementer, reviewer, critic), determines parallel launch counts, crafts scoped prompts…
Automation
agent-activity-log
Scaffold and manage an opt-in activity log table that captures agent decisions, actions, and blocks during long-running or multi-session workflows. Use for recurring triage, automa…
Research
ostrom-commons-governance
Applies Elinor Ostrom's eight design principles for commons governance to software architecture and AI agent coordination. Use for auditing shared-resource systems, designing agent…
AI / ML
df-review-reasoning-layer
Reviews layered prompt systems that assemble dialectical reasoning across apps, agents, concerns, and theory. Evaluates at three levels: isolated prompts, assembled context, and ov…
AI / ML
ai-sdk-agents
Expert guidance for building AI agents with ToolLoopAgent (AI SDK v6+). Use when creating agents, configuring stopWhen/prepareStep, callOptionsSchema/prepareCall, dynamic tool sele…
Productivity
copilot-customization
Authoritative reference for AI coding agent customization: instructions, prompt files, custom agents, agent skills, MCP servers, hooks, and plugins. Use when selecting customizatio…
General
Add `.github/copilot-instructions.md` to Prepare the Codebase for Copilot Coding Agent Use
As described in the [GitHub Accessibility — Getting Started with Agents](https://accessibility.github.com/documentation/guide/getting-started-with-agents/) guide, one of the most i…
AI / ML
Aicrew
No framework CrewAI, um `Agent` é uma unidade autônoma que pode: - Executar tarefas específicas - Tomar decisões com base em seu papel e objetivo - Utilizar ferramentas para alcanç…
Automation
Amazon Automation
Wave 2 (After Wave 1 — 知识库 + 现有 Agent 激活): ├── Task 8: 上传并导入 550+ Word 文档到知识库 [unspecified-high] ├── Task 9: 激活选品 Agent（真实数据）[unspecified-high] ├── Task 10: 激活 Listing Agent（真实数据）[…
Research
Awesome llm agents
· ([mp.weixin.qq](https://mp.weixin.qq.com/s?__biz=MzAxMTk4NDkwNw==&mid=2247495643&idx=2&sn=f759dc738477d76143ffc53a043b398c&poc_token=HPiN6mWjzo5Wn8_C9o639UGw2ABkm8pA7X9RusYq)) - …
AI / ML
codex-model-routing-team
Routes complex or parallel tasks across multiple models and agents by planning, delegating, integrating, and validating results. Activates for multi-source research, multi-chapter …
Research
Cursor Cloud Agents & Parallel Worktree Agents
New Cursor Interface · Cursor Skip to content Cursor Product↓ Agents Code Review Cloud ↗ Tab CLI Marketplace ↗ Enterprise Pricing Resources↓ Changelog Blog Docs Community Help ↗ Wo…
Automation
Maestro
`$client->beta->agents->create(Model model, string name, ?string description, ?list<BetaManagedAgentsURLMCPServerParams> mcpServers, ?array<string,string> metadata, ?BetaManagedAge…
AI / ML
mastra
Expert in Mastra, the TypeScript framework for building AI agents, RAG pipelines, and workflows. Helps developers create production-grade applications with type-safe agent definiti…
AI / ML
Yao Shunyu: Let Me Go a Little Crazy! Training Models at Anthropic & Gemini, Heroism Is Over
A rare 4-hour first-person account of training Claude 3.7/4.5 and Gemini 3 from inside both Anthropic and Google DeepMind — covering org structure, what differentiates the labs tec…
AI / ML
Project: Intraday Python Trading System
C:\Projects\IntradayJules\src ¦ ¦ column_names.py ¦ main.py ¦ +---agents ¦ base_agent.py ¦ data_agent.py ¦ data_agent_fixed.py ¦ enhanced_data_agent.py ¦ env_agent.py ¦ evaluator_a…
AI / ML
folded-memory-implementation
Implements a three-tier memory system for agents: recent interactions remain detailed, prior sessions compress into episodic summaries, and long-term knowledge consolidates into se…
Automation
ACP agents
[Agent Client Protocol (ACP)](https://agentclientprotocol.com/) sessions let OpenClaw run external coding harnesses (for example Pi, Claude Code, Codex, Cursor, Copilot, OpenClaw A…
Automation
ACP agents
[Agent Client Protocol (ACP)](https://agentclientprotocol.com/) sessions let OpenClaw run external coding harnesses (for example Pi, Claude Code, Codex, Cursor, Copilot, OpenClaw A…
AI / ML
Escribiendo acciones como fragmentos de código o estructuras JSON
<CourseFloatingBanner chapter={2} classNames="absolute z-10 right-0 top-0" notebooks={[ {label: "Google Colab", value: "https://colab.research.google.com/#fileId=https://huggingfac…
Documentation
openacme-platform
Explains OpenAcme's directory layout including agents, skills, MCP servers, data storage, memory systems, and peer-notes conventions. Enables agent-independent navigation of the pl…
Showing the top 60 of 2,828. See the full list →