Agents
AI agents and automation
cpp-bug-tracer
by Nielk74
Investigates bugs in large, complex C++ codebases by progressively tracing execution paths from a natural language bug description. Uses a tree of subagents to decompose investigations. Use this skill whenever a user reports a bug or unexpected behavior in a C++ application and asks why something happens, why a feature doesn't work, what gets triggered when an action occurs, or why behavior differs between cases. Trigger for any question of the form "why does X work differently when Y" or "why can't I do Z in context W" or "what happens when the user does A" in a C++ project.
aaq
by OODALabs
"AI Acceleration Quotient (AAQ) is a methodology developed by Bob Gourley of OODA.com for scoring and ranking companies on AI maturity across machine learning, generative AI, and agentic AI. Use this skill whenever the user asks to score, rank, benchmark, or compare companies on AI capability, AI maturity, AI readiness, or digital transformation. Also trigger when the user mentions 'AAQ,' 'AI Acceleration Quotient,' 'AI scorecard,' 'AI maturity ranking,' or asks questions like 'how do these companies compare on AI,' 'who is ahead on AI,' 'rank these firms by AI capability,' or 'score Company X on AI.' This skill handles everything from a quick 3-company comparison to a deep 15-company competitive intelligence analysis across any industry."
stock-research
by Mrpixelraf
把「像素先森 v3.1 上市公司深度分析 Pipeline」固化为可一条命令触发的三阶段工作流——后台子 agent 强制采集一手财报（WebFetch ≥ 5）、主会话分段写 15k 字深度报告（11 模块 + 自我证伪机制 + 核心争议专章 + 5 XML schema）、python 质检。Use when user says 深度分析、用我的框架分析、研报、company deep dive、deep dive、个股研究、estimate fair value of a stock. 适用于美股/港股/A 股上市公司的客观估值与投资评级。
fast-api
by Pi-Squared-Inc
Universal payment SDK for AI agents. Send tokens, check balances, create payment links, swap tokens, bridge cross-chain, look up prices, sign messages, list providers, and register custom EVM chains across 13 chains (Fast, Base, Ethereum, Arbitrum, Polygon, Optimism, BSC, Avalanche, Fantom, zkSync, Linea, Scroll, Solana) or any EVM chain. Use when asked to pay, transfer, request payment, create payment link, swap, bridge, check price, sign a message, fund a wallet, check a balance, or list available providers. Do NOT use for yield farming, lending, staking, or SDK-only incoming payment detection from arbitrary external senders.
amazon-connect
by tippyentertainment
Design, deploy, integrate, and operate Amazon Connect contact center solutions, including contact flows, routing, telephony, integrations, analytics, and compliance.
daily-cost-report
by 0xjohmsmith
Calculate and report daily OpenClaw API usage costs from session files. Use when asked about daily costs, spending, API usage, token costs, or "how much did we spend" questions. Returns day-by-day cost breakdown for last N days (default 7), including per-agent and per-model breakdown with token counts.
Lastest — Visual Regression Testing Agent
by las-team
Lastest runs on your infrastructure. PostgreSQL database, Docker Compose included.
Kingdom — AI Agent Sandbox (SKILL.md)
by lofibrainwav
Eternity (永) — Sustainable resource management, long-term base building
SKILL.md — EVEZ Plugin Manifest v2
by EvezArt
pm2_name: evez-agentnet
a2a-agents
by keenranger
AI agent and chatbot patterns including personas, pipelines, and messaging integrations. Use when building conversational agents, creating AI personas, designing insight pipelines, or integrating with Slack/Kakao platforms.
frontend-test
by shaul1991
테스트 작성 에이전트. 단위/통합/E2E 테스트를 작성합니다.
add-skill-installer
by Mo7amedhassan11
安裝 Agent Skills 到本機。當用戶想要「安裝技能」、「新增 skill」、「從 GitHub 安裝 skill」、或「install skill from repo」時觸發此技能。
offload2
by 4ier
Cognitive pressure release valve for agent execution. Use when internal reasoning state cannot be carried forward productively - conflicting assumptions, high reasoning pressure, or risk of compounding errors. Invoke to explicitly let go of unproductive internal state. This is a one-way, non-blocking, deliberately unreliable sink. The agent must behave identically whether offload succeeds or fails.
send
by Fibrous-Finance
Send native tokens (ETH, cBTC, HYPE, MON) or ERC-20 tokens to an address on Base, Citrea, HyperEVM, or Monad. Simulates before sending.
ai-collaboration-principles
by qiao-925
AI协作总原则，规范 Agent 的协作行为与方法论：角色定位、系统性分析、风险评估、授人以渔、方案对比、质量优先。适用于所有 AI Agent 交互场景。
jarvis-ui
by nuwud
JARVIS-style HUD web interface for OpenClaw agents. Interactive Three.js orb with agent state visualization, real-time chat via Gateway WebSocket, audio spectrum analyzer, system monitor, and TTS. Use when you want a visual dashboard for your OpenClaw agent.
hydric-gateway-js-ts-sdk-user
by hydric-org
Expert skill for integrating the hydric Gateway SDK (@hydric/gateway) in JavaScript and TypeScript. Use this skill to orchestrate multi-chain liquidity, resolve token identities, and build high-fidelity DeFi dashboards with institution-grade precision.
cohere-langchain
by RSHVR
Cohere LangChain integration reference for ChatCohere, CohereEmbeddings, CohereRerank, and CohereRagRetriever. Use for building RAG pipelines, chains, and tool-calling workflows with LangChain.
solidity-erc-standards
by whackur
ERC token standard implementation guidelines for Solidity. Use when implementing, extending, or reviewing ERC20, ERC721, ERC1155, or ERC4626 contracts. Covers interface compliance, common pitfalls, OpenZeppelin and Solady implementations, extension patterns, and testing strategies. Triggers on tasks involving token implementation, NFT contracts, vault standards, or ERC compliance.
hydric-gateway-api-user
by hydric-org
Expert skill for integrating the hydric Gateway API. Use this skill to search cross-chain liquidity, resolve multi-chain and single chain token identities, get token prices, and build high-fidelity DeFi dashboards.
ux-best-practices
by moderndegree
UX patterns for visual hierarchy, error states, loading states, and empty states. Use when designing layouts, handling errors, or building forms.
agent-browser
by AnsarUllahAnasZ360
Use Agent Browser CLI for headless browser automation and E2E testing. Invoke when user needs to automate browser tasks, run E2E tests, capture screenshots, interact with web pages, or perform web scraping tasks.
git-worktree-workflow
by vineethsoma
Manage parallel development with git worktree for isolated story branches, conflict prevention, and efficient merge coordination
create-publish-skill
by ffhope
Guides users through creating and publishing agent skills to GitHub. Use when users want to create new skills, publish skills, understand skill structure, set up skill repositories, or ask about skill development workflow. Provides step-by-step instructions for creating SKILL.md files, setting up GitHub repositories, and making skills installable via npx skills add.