83,201 skills sorted by stars.
Index skill for working in the AgentForge monorepo. Routes to runtime, CLI, dashboard, MCP, channels, testing, template sync, and...
Work on Agent-to-Agent protocol support, registry behavior, and delegation flows in packages/core.
Work on browser automation support in AgentForge, including the browser tool abstraction and Playwright-backed execution.
Work on AgentForge channel adapters across runtime and core, including Telegram, Discord, Slack, and WhatsApp.
Work on AgentForge CLI commands, project creation, run/start flows, and developer ergonomics in packages/cli.
Comprehensive Convex development skill for building production-ready apps. Covers functions (queries, mutations, actions, HTTP end...
Work on the AgentForge web dashboard built with React, Vite, TanStack Router, and Convex-backed state.
Work on MCP support in AgentForge, including MCP client/server abstractions, connection management, dynamic tools, and useful exte...
Work on research orchestration in AgentForge, including tool coordination, synthesis, and evidence-driven workflows.
Work on the persistent Mastra daemon in packages/runtime, including createStandardAgent, daemon lifecycle, environment validation,...
Work on sandbox execution in packages/core, including local, Docker, and E2B providers plus security constraints.
Work on skill discovery, parsing, registry behavior, install flows, and marketplace UI/data paths in AgentForge.
Keep template-backed files aligned across canonical template, dist template, and local convex copies.
Run and extend AgentForge test coverage across packages, CLI flows, runtime behavior, MCP integrations, and dashboard-adjacent log...
AgentHero AI - Hierarchical multi-agent orchestration system with PM coordination, file-based state management, and interactive me...
Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents wo...
Enforces high-level architectural thinking, separation of concerns, and scalability checks before coding.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI,...
AI assistant for creating clear, actionable task descriptions for GitHub Copilot agents
Ship production code with AI agents through acceptance contracts, micro diffs, red green loops, and deterministic handoff checkpoi...
Create, fund, and settle on-chain agent jobs via ERC-8183 Agentic Commerce Protocol.
Navigation and decision-making framework for autonomous agents.
Use when building AI agent systems. Covers agent loops, tool calling, planning patterns, memory systems, multi-agent coordination,...
Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)
Production-grade agent DevOps toolkit — Docker, process management, log analysis, and health monitoring. Built by engineers who ru...
Semantic diffusion model for code. Turns generation into iterative denoising using four distinct roles (Orchestrator, Generator/Ra...
Write clear, plain-spoken code comments and documentation that lives alongside the code. Use when writing or reviewing code that n...
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
Transition from a hands-on "bricklayer" to a high-level "architect" by managing a fleet of autonomous AI agents. Use this when you...
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and refle...
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when implementing self-critique and reflecti...
Export reusable assets from a project into this repository's v0.2 plugin architecture (skills, templates, agents).
Designing features for the "Action Era" that are AI-accessible by default