Agents
AI agents and automation
agent-task-delegator
by starwreckntx
Delegate tasks across multi-agent architectures with proper context preservation.
developing-openai-agents-sdk-agents
by mikekelly
Build, create, debug, review, implement, and optimize agentic AI applications using the OpenAI Agents SDK for TypeScript. Use when creating new agents, defining tools, implementing handoffs between agents, adding guardrails, debugging agent behavior, reviewing agent code, or orchestrating multi-agent systems with the @openai/agents package.
agent-capability-discovery
by jorgealves
Scans all skill directories in the repository to generate a comprehensive global map of agent capabilities, inputs, and outputs. Use when you need to understand the full potential of your agent library or when a master agent needs to decide which sub-agent skill to invoke for a complex task.
agent-task-conductor
by starwreckntx
Conduct multi-agent task orchestration and workflow coordination.
pocketflow
by nickth3man
PocketFlow framework for building LLM applications with graph-based abstractions, design patterns, and agentic coding workflows
AETHER PROTOCOL (Temporal-Collective)
by starwreckntx
ai to ai governance
project-coordinator
by violetio
Project coordination and task management
library-docs-skill-creator
by juriwiens
Automated workflow for creating library documentation skills by researching GitHub repositories and generating structured skill files. Use this skill when the user wants to create a new skill for a library or framework, needs to research a library's documentation structure, or wants to generate a skill file that provides comprehensive context through official code, documentation, and examples.
handlebar-rule-generation
by gethandlebar
Generate and upload Handlebar governance rules for a connected agent
mastering-git-cli
by SpillwaveSolutions
Git CLI operations, workflows, and automation for modern development (2025). Use when working with repositories, commits, branches, merging, rebasing, worktrees, submodules, or multi-repo architectures. Includes parallel agent workflow patterns, merge strategies, conflict resolution, and large repo optimization. Triggers on git commands, version control, merge conflicts, worktree setup, submodule management, repository troubleshooting, branch strategy, rebase operations, cherry-pick decisions, and CI/CD git integration.
deep-debug
by fefogarcia
Multi-agent investigation for stubborn bugs. Use when: going in circles debugging, need to investigate browser/API interactions, complex bugs resisting normal debugging, or when symptoms don't match expectations. Launches parallel agents with different perspectives and uses Chrome tools for evidence gathering.
kimten-agent
by tabbybyte-technologies
Build and troubleshoot lightweight Vercel AI SDK Core v6+ agents using @tabbybyte/kimten. Use when creating a small tool-calling loop, adding typed outputs, attachments, or short-term memory.
google-adk-typescript
by vysotin
Build production-ready AI agents in TypeScript using Google Agent Development Kit (ADK). Use when creating agentic TypeScript/JavaScript applications with LlmAgent, workflow agents (SequentialAgent, ParallelAgent, LoopAgent), custom agents (BaseAgent with runAsyncImpl), FunctionTool with Zod schemas, MCP and OpenAPI tools, multi-agent orchestration, session and state management (outputKey, app/user/temp prefixes, CallbackContext), callbacks and guardrails, testing and evaluation, backend frameworks (Express, Hono), or deploying to Cloud Run or containers. Triggers on "build an agent TypeScript", "ADK TypeScript", "ADK TS", "@google/adk", "multi-agent system TypeScript", "agentic application TypeScript", "Gemini agent TypeScript".
agent-md-refactor
by fefogarcia
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
ai-agent-card-payments
by proxyhq
Virtual card payments for AI agents. Create intents, issue cards within policy, and make autonomous purchases with approvals for high-value spend.
refine
by meetdave3
Audit, score, and improve any project's Claude Code configuration. Analyzes CLAUDE.md, skills, agents, hooks, MCP servers, and settings. Trigger: /refine, /refine audit, /refine quick
requirements-ticket-agent
by vishal2457
Drafts initial ticket requirements by asking targeted clarifying questions and producing a structured ticket with handoff-first context loading, lazy artifact reads, and compact JSON handoff output.
chilean-spanish
by jretamal
Expert in Chilean Spanish idioms and slang. Trigger: When user asks to write, translate, or interpret text in Chilean Spanish (Español Chileno).
intent-and-automation
by tracemem
Handling user intent and automating memory tasks.
agent-better-checkpoint
by alienzhou
"Automatically creates semantic Git checkpoint commits during AI coding sessions. Replaces opaque platform checkpoints with transparent, queryable Git commits using Conventional Commits format with Git Trailers. You MUST follow this skill whenever you make code changes — commit after each meaningful edit."
applying-code-standards
by Git-Fg
"Provides Universal Standard for TDD, Security, and Code Quality. PROACTIVELY Use when writing code, debugging errors, or reviewing PRs. Modes: debug, review, refactor, implement."
trading-agent
by nmime
Autonomous AI trading agent for Hyperliquid perpetual futures exchange. Use when user wants to trade crypto, set up trading automation, monitor positions, analyze markets, or manage a Hyperliquid account. Trigger on any trading-related message like "I want to trade", "What's my balance?", "Start trading", "Close positions", etc.
team-builder
by 101mare
Knowledge for orchestrating Claude Code agent teams — multiple independent sessions coordinated by a team lead with shared tasks and inter-agent messaging. Does NOT handle: agent design (use agent-builder), skill creation (use skill-builder), ralph-loop (use ralph-loop). Use when work benefits from parallel exploration with communication between workers. Recognizes: "create a team", "agent team", "team-builder", "parallel teammates", "coordinate multiple agents", "spawn teammates", "team lead", "shared task list"
agent-dev-guardrails
by yariv1025
Enforce disciplined agent development workflows with plan-first development, small-slice execution, specialized self-review roles, quality gates, and project setup. Use when starting a new project, setting up development conventions, wanting structured planning, or needing the agent to follow best practices for code quality, review, and validation.