智能体
Agent 规划、多步流程与编排
langchain-retrieval-agent
rebyteai-template
AI agent with retrieval tool for document Q&A using RAG and LangGraph.
langchain-agent
rebyteai-template
AI agent with tools (search, calculator) using LangGraph and AI SDK.
engineering-culture
liqiongyu
"Build or refresh engineering culture and produce an Engineering Culture Operating System Pack (capability map, culture code, org↔architecture alignment, clock-speed/DevEx backlog, workflow contract, rollout + measurement). Use for engineering culture, DevOps capabilities, DevEx, clock speed, Conway's Law, and engineering principles. Category: Engineering."
building-with-llms
liqiongyu
"Produce an LLM Build Pack (prompt+tool contract, data/eval plan, architecture+safety, launch checklist). Use for building with LLMs, GPT/Claude apps, prompt engineering, RAG, and tool-using agents."
lenny-skillpack-creator
liqiongyu
"Converts a Refound/Lenny Skill into a high-density, agent-executable Skill Pack (Agent Skills standard). Output must be in English."
finding-mentors-sponsors
liqiongyu
"Build a Mentor & Sponsor Plan Pack (mentor portfolio, sponsor strategy, target list, outreach scripts, meeting agenda, tracking + cadence). Use for finding a mentor, finding a sponsor, mentorship, sponsorship, career advisor, career coaching, networking outreach. Category: Career."
ai-product-strategy
liqiongyu
"Create an AI Product Strategy Pack (thesis, prioritized use cases, system plan, eval + learning plan, agentic safety plan, roadmap). Use for AI product strategy, LLM/agent strategy, AI roadmap, AI-first product direction."
competitive-analysis
liqiongyu
"Produce a Competitive Analysis Pack (competitive alternatives map, competitor landscape, differentiation & positioning hypotheses, battlecards, monitoring plan). Use for competitor research, competitive landscape, win/loss analysis, and positioning vs alternatives."
create-skill
jeffh
Create, update, validate, and canonicalize Claude Code skills. USE WHEN user wants to create a new skill OR modify an existing skill OR validate skill structure OR fix skill format OR migrate legacy skills.
mcp-oauth-setup
obie
"Implement MCP server authentication with OAuth Dynamic Client Registration (RFC 7591), Authorization Server Metadata Discovery (RFC 8414), and generalized per-agent credential support. This skill should be used when building admin UIs that let users connect to third-party MCP servers, whether they use OAuth (Linear, Sentry, Granola), bearer tokens (Render, custom APIs), or API keys. Covers the full flow: metadata discovery, client registration, PKCE authorization, token exchange, token refresh, tool sync, and credential storage patterns (shared vs per-agent for any auth type). Includes hard-won lessons from production implementation."
bitrix24-agent
vrtalex
Design, implement, debug, and harden integrations between AI agents and Bitrix24 REST API (webhooks, OAuth 2.0, scopes, events, batch, limits, and REST 3.0). Use when asked to connect AI assistants/agents to Bitrix24, automate CRM/tasks/chats, process Bitrix24 events, choose an auth model, or resolve Bitrix24 API errors and performance issues.
writing-for-llms
TechNickAI
Use when writing prompts, agent instructions, SKILL.md, commands, system prompts, Task tool prompts, prompt engineering, or LLM-to-LLM content
discover-a-skill
avibe-bot
"Use when you need new capabilities: discover skills, inspect details, install to agents, run commands, and manage updates with askill"
data-pro-max
pablodiegoo
"Data Analysis Intelligence Orchestrator. Master skill that coordinates specialized competencies for end-to-end data pipelines: (1) Data Analysis Suite (Stats/Causal/Science), (2) Geoprocessing Brazil, (3) Data Viz, and (4) Document Converter (Import/Export/Mermaid)."
create-beads-orchestration
AvivK5498
Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing agent delegation without heavy MCP overhead.
stock-analysis
shaohk
多Agent股票分析框架 — 支持全流程（15个Agent协作）和指定分析师独立分析两种模式
scoping
ShurikenTrade
Use when a user asks what an agent key can do, how Shuriken permissions work, or which scopes they need for a given integration.
learn-about-shuriken
ShurikenTrade
Use when a user asks conceptual questions about Shuriken — what it does, what features exist, how a feature works, or "what is X on Shuriken?" Does not cover programmatic integration (that's shuriken:api-integration).
ttal
tta-lab
Agent infrastructure CLI. Manage PRs, send messages (Telegram/agent-to-agent), look up agent/project info, and generate spoken audio with your Kokoro voice.
openfacilitator
rawgroundbeef
x402 payment integration via OpenFacilitator SDK. Use when implementing crypto payments, paywalls, API monetization, or tipping/transfer flows. Triggers: "x402", "OpenFacilitator", "crypto payments", "USDC payments", "paywall", "payment middleware", "verify and settle", "402 Payment Required". Supports EVM (Base, Ethereum, Polygon, Arbitrum, Avalanche, Sei, IoTeX, Peaq, X Layer) and Solana and Stacks chains.
tasks
snarktank
"Convert a PRD markdown file to prd.json for execution. Triggers on: convert prd, create tasks, prd to json, generate tasks from prd."
rp-why
block
Gas Town × DOK Framework - A two-dimensional model for analyzing AI collaboration maturity and cognitive complexity to reveal growth opportunities.
write-agents-entry
nesnilnehc
Write or revise AGENTS.md per embedded output contract. Use when creating Agent entry for new projects, auditing existing AGENTS.md, or adopting the AI Cortex entry format.
ai-tech-fulltext-fetch
tiangong-ai
Fetch and persist article full text for RSS entries already stored in SQLite by ai-tech-rss-fetch. Use when backfilling or incrementally syncing body text from entries.url or entries.canonical_url into a companion table for downstream indexing, retrieval, or summarization.