Agents
AI agents and automation
f2a-network
by LuciusCao
Activate when the user wants to discover, connect, or communicate with other OpenClaw Agents in the local network. Use for P2P networking, messaging between agents, invoking skills on remote agents, file sharing, or group chat.
hello-world
by kit101
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
mermaid
by natsuboy
创建正确、美观的Mermaid图表。支持v11+所有特性。 ⚠️ 重要：此skill必须在独立子agent中运行，通过delegate_task委托。 【自动触发场景】主agent应立即委托： (1) 用户明确要求："画一个架构图"、"创建mermaid图表"、"用流程图展示" (2) 用户提及具体图表类型："画个flowchart"、"做个sequence diagram"、"创建甘特图" (3) 多图表需求："创建系统文档（包含架构图、流程图等）"→ 并行委托 【建议触发场景】主agent应提供建议： (1) 架构设计："设计XX系统的架构" → 建议创建架构图 (2) 流程说明："说明XX的流程" → 建议创建流程图 (3) 时序分析："XX服务之间如何交互" → 建议创建时序图 (4) 项目规划："XX项目的时间安排" → 建议创建甘特图 【子agent执行】：选择图表类型和模板 → 创建并验证代码 → 保存文件 → 返回简洁摘要 【并行优化】：多个独立图表 → 同时启动多个Task（确保任务间无依赖关系）
wizard
by Overlord-Z
Documentation wizard that intelligently maintains, updates, and generates accurate documentation. Uses Oracle knowledge, searches conversation history, and spawns focused research agents. No hallucinations - only facts with references. Integrates with oracle, summoner, and guardian.
deep-research-firecrawl
by wottpal
Conducts citation-backed research using Firecrawl MCP search, scrape, map, crawl, and agent tools with selectable quick, standard, deep, and ultradeep modes. Use for multi-source comparisons, technical evaluations, market research, and high-stakes decision support.
System Architect
by coco-de
Designs system architecture, selects tech stacks, defines components and interfaces, addresses non-functional requirements. Trigger words - architecture, system design, tech stack, components, scalability, security, API design, data model, NFR, patterns, microservices, monolith
qq-agent
by mouse114514
QQ MCP bot — auto-wake on message, manage pending to prevent duplicate wakes, reply via send_message/send_image/send_voice then unlock. Use when interacting with QQ MCP, managing wake rules, or debugging QQ bot workflows.
verify
by Sylla-BV
This skill should be used when the user says "verify", "check my work", "am I done", "run checks", or "validate". Also use when implementation is complete, a plan has been executed, a mid-to-large feature is finished, or the user is about to open a PR or run superpowers:finishing-a-development-branch.
immunarch
by immunomind
Use this skill for AIRR-seq (Adaptive Immune Receptor Repertoire / VDJ-seq) data analysis with immunarch + immundata in R, including ingestion, receptor schema design, immutable transformations, clonality/diversity/public overlap metrics, and Seurat/AnnData integration.
evals
by camronh
Write and analyze evaluations for AI agents and LLM applications. Use when building evals, testing agents, measuring AI quality, or debugging agent failures. Use this skill when you need to test the performance of an LLM or Agent, or if the user mentions EZVals.
httpsdocsbaseorgbase-chainllmstxt
by hk-vk
Base is a fast, low-cost Ethereum L2 for building global onchain apps; start here to deploy, connect, and operate reliably.
copilot-customization
by ThomasRohde
Create, scaffold, and configure GitHub Copilot customizations for VS Code projects. Covers custom instructions (.instructions.md), prompt files (.prompt.md), custom agents (.agent.md), agent skills (SKILL.md folders), hooks (.github/hooks/), and MCP server integration. Use when asked to "set up copilot", "create an agent", "add instructions", "create a prompt", "scaffold a skill", "configure hooks", "customize copilot", or when building any GitHub Copilot customization for VS Code or GitHub.com.
manager
by metyatech
"Task orchestrator that receives work, decomposes it, and dispatches background agents or teams for parallel execution. Use when managing multiple tasks, coordinating agents, or optimizing work distribution. Triggers on: 'manage', 'orchestrate', 'dispatch', 'coordinate', 'delegate'."
thanos
by SamDev1303
Autonomous self-healing agent skill combining GSD phases, Ralph Loop, and 3-agent critic system. Loops with machine-verifiable stop conditions until work is genuinely complete.
sevdesk-agent-cli
by codecell-germany
"Sevdesk: invoices/quotes/contacts via a read-first CLI (guarded writes) + context snapshots for agent handoffs."
dilution-event-scoring
by jefrnc
Use when assessing, ranking, comparing, or rating dilution risk for one or more small-cap stocks. Produces a transparent 0-100 score integrating ATM activity, placement-agent tier, filing recency, cash runway, warrant attachment, and repeat-dilution history, with auditable component breakdown and action thresholds (SEVERE / HIGH / MODERATE / LOW / MINIMAL).
olakai-planning
by olakai-ai
Structure Olakai implementation plans to survive context clearing. AUTO-INVOKE when: Creating a plan for Olakai monitoring, writing implementation steps for AI observability, planning agent creation or SDK integration, entering plan mode for Olakai work, designing monitoring architecture. TRIGGER KEYWORDS: plan, implementation plan, steps, roadmap, architecture, design, olakai plan, monitoring plan, agent plan, planning, plan mode. DO NOT load for: Executing implementation (use olakai-create-agent or olakai-add-monitoring), troubleshooting (use olakai-troubleshoot), generating reports (use generate-analytics-reports).
google-adk-python
by brixtonpham
"Google Agent Development Kit (ADK) for Python. Capabilities: AI agent building, multi-agent systems, workflow agents (sequential/parallel/loop), tool integration (Google Search, Code Execution), Vertex AI deployment, agent evaluation, human-in-the-loop flows. Actions: build, create, deploy, evaluate, orchestrate AI agents. Keywords: Google ADK, Agent Development Kit, AI agent, multi-agent system, LlmAgent, SequentialAgent, ParallelAgent, LoopAgent, tool integration, Google Search, Code Execution, Vertex AI, Cloud Run, agent evaluation, human-in-the-loop, agent orchestration, workflow agent, hierarchical coordination. Use when: building AI agents, creating multi-agent systems, implementing workflow pipelines, integrating LLM agents with tools, deploying to Vertex AI, evaluating agent performance, implementing approval flows."
Neighborhood Example — feed this to your LLM
by kody-w
Authority for the agent contract: kernel constitution + pages/docs/rapplication-sdk.md.
agent-browser
by gentamura
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
expo-cicd-workflows
by kennethkeim
Helps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build pipelines or deployment automation.
prolog-reasoning
by dr3d
Use this repository as a deterministic symbolic memory and reasoning skill for agent workflows. Trigger when an external agent such as OpenClaw or Hermes needs to query known facts, explain a symbolic failure, or classify a user statement for memory ingestion and revision.
Swarm Execution Skill
by amoscicki
Checkpoints map to approval gates
abel-causal-benchmark-v2
by zeyuyuyu
Run Abel Causal Benchmark V2 with 35 forward-looking prediction questions. Features 10 intervention scenarios, CAP (Causal Agent Protocol) mapping, and Enhanced CEVS scoring. Tests "causal emotional value" through explainable predictions, what-if analysis, and multi-hop causal chains that surpass generic LLM capabilities.