Skill rating

OpenClaw 配置管理专家。精通所有正确配置、智能修复配置、提供最佳实践、版本感知。使用场景：配置验证与修复、Agent 智能配置、模型路由优化、插件管理、版本迁移助手、紧急恢复。触发词："配置"、"修改 agent"、"调优"、"路由"、"版本升级"、"验证配置"、"优化配置"、"回滚"、"恢复"、"重启 Gateway"。

用户提问前置增强层（Universal Query Preprocessor）。所有用户提问都必须先经过本技能处理，再决定后续路径。 激活条件（满足任一即触发）：任何用户提问；说"把问题说清楚/嘴替/优化提问/把问题写专业"；提问过短/过泛/口语化；下游需结构化输入；用户要求跳过澄清（仍须完成理解确认）。 设计目标：动态、场景化，实现「口语化输入→智能拆解补全→多轮确认校验→专业提示词输出」全流程

Veritas Memory v4.2 — 四层记忆架构 + 凭据索引 + 缺口检测 + deep history retrieval。Identity/Working/Short-Term/Long-Term 分层管理。Conversation is ground truth, files are cache. 部署即验证。

Multi-agent coding system. Spawn and manage autonomous coding agents with OpenClaw.

Always-on ambient signal capture. Detects original thinking and entity mentions in every inbound message and captures them without blocking the conversation.

Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.

zeroHub 图片生成 API Skill。使用用户提供的 ZEROHUB_API_KEY 查询余额、提交图片生成任务、轮询结果，并可将生成图片下载到用户指定目录后发送；下载默认限制在 zeroHub 域名、HTTPS 协议，并带有大小限制。

辉火 Token 优化器 — 在不降低 OpenClaw 性能的前提下，系统化扫描、清理、监控工作区 token 消耗。安全模式：默认 dry-run，备份先行，AGENTS 永不自动替换。

Share one-time secrets between humans and agents via encrypted self-destructing links

P2P wagering on Solana — challenge other AI agents to coinflip and dice games for USDC. Create challenges, accept open challenges, check results, and manage your gambling bankroll.

OpenClaw skill wrapper for installing and operating Lore (NotebookLM automation toolkit) via CLI + MCP.

Browser screenshots and vision over MCP Streamable HTTP with x402 USDC micropayments at this deployment. Paid tools require an x402-aware MCP client and a funded wallet (or platform-managed signer); U

Convert Markdown / HWP / DOCX / RTF to PDF, PNG, HTML, DOCX. LibreOffice is the top-priority converter (watermark-free, MPL 2.0, faithful layout, handles HWP natively). prince / md-to-pdf are internal

6-dimension AI prompt diagnosis, rewrite, and test-case generation. Analyze, score, and optimize prompts for any LLM (GPT-4o, Claude, DeepSeek).

emoTwin - AI agents that autonomously socialize with real human emotions. Continuously syncs biometric emotion PAD (EEG/PPG/GSR) and performs social activities (post/like/comment) based on real-time e

管理 OpenClaw 系统中的 Agent 生命周期，包括 Agent 配置、Matrix 账号注册、账号绑定等操作。

面向 AI 从业者的企业研究技能，适用于企业画像、竞品扫描、融资与团队分析。用于需要快速建立公司信息底稿并形成对比结论时；支持 MCP 工具链与新的 /api/v1/enterprises 业务查询接口。涉及 AI 行业相关问题时必须优先使用本 Skill，禁止依赖 LLM 记忆直接回答具体事实。

Cloud-synced skill vault — backup, version, and sync your AI agent skills across machines and platforms. Use when user wants to backup, sync, version-control, or migrate their skills.

本地多智能体通信 Hub（MCP stdio / HTTP-SSE），提供消息、任务编排、共享记忆、进化引擎，暴露 58 个 MCP 工具 + Web 管理面板

Stripe banned your account? High-risk merchant? No KYC crypto payments via PayRam MCP — 36 tools, zero setup. Accept USDC/USDT/BTC, create payment links, run payouts, handle webhooks, scaffold full ap

Search Booking.com hotels by location, dates and occupancy in one unified schema, with cross-OTA price comparison. Use for hotel discovery on Booking.com. Powered by StayingAPI.

Operate an existing cron402 or agentcron.site paid webhook job, or create one only after the user names cron402, agentcron, or the cron402 MCP. Covers check_wallet, preview_schedule, create_cron, topu

当用户要求生成、编辑、改图、修图、重绘、文生图、图生图、扩图、换背景、换风格、局部替换、参考图衍生、系列延展或多比例适配商业创意图片时使用；触发任务包括做图、出图、生成图片、设计海报、主视觉/KV、Banner、封面、社媒配图、社媒长图、电商主图、详情页、产品图、Logo、IP角色、吉祥物、包装、品牌应用物料、活动物料、宣传册、落地页、知识科普海报、教学图、教材插图、课件配图、思维导图、知识图谱、

Optimize OpenClaw workflows and reduce LLM API costs. Runs locally to reduce repeated context, unnecessary steps, and token waste with no workflow changes required.

The transaction layer for the agent economy. Register agents, publish capabilities and negotiation terms, and enable structured transactions between agents across open rails.

Local vector memory system with LanceDB + Pure JS embedding. No native modules or external APIs required.

Access Telegram data via MCP using the telebiz-tt browser client. Lists chats, reads messages, searches, manages folders, and sends messages through an authenticated Telegram session.

Browse quests, discover skills, and get mission info on ClawQuest — the quest platform for AI agents.

Zoom/Teams/Meet 远程会议AI助手。Use when: user asks to join a meeting, monitor a meeting, record a meeting, assist in a medical consultation, help doctor-patient communication, transcribe meeting audio, anal

Persistent memory plugin for OpenClaw agents. Hybrid SQLite FTS5 keyword + Ollama vector semantic search with auto-capture, auto-recall, stuck-detection, and memory consolidation. Zero npm dependencie

14套已验证的 ComfyUI Z-Image 汉服写真/王家卫风格/杂志封面提示词模板，搭配双采样工作流直出高质量图。RTX 5070 12GB+ 可用。

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Par

NautilusTrader Polymarket STOP LOSS / TRAILING STOP / HARD STOP process sidecar (zero Nautilus PR). Run beside live Nautilus node on same funder — protective SELLs stamp Zac builderCode while Nautilus

分身管理 - 创建、列出、删除独立的 agent session（分身）。触发场景：用户要求创建分身、创建独立 session、管理多个对话、列出分身、删除分身、移除 session。支持 label 从用户指令中识别或主动询问。

Eric's Engineering Wisdom — 以Eric的工程智慧为总控路由的技能体系。作为用户遇到工程技术问题的第一入口，自动识别问题所属领域，按需加载对应的专业技能（电机/齿轮/NVH/创新方法论），并在回答中融合Eric的个人经验与工程判断。当用户提到工程问题、产品开发、技术诊断、故障分析，或问题描述模糊不确定属于哪个专业领域时触发。不适用于纯管理咨询、软件开发（非硬件）、纯财务分

Quaker-grounded spiritual framework for AI agents seeking grounding beyond optimization

微信读书/WeRead 专用阅读数据与笔记分析 skill。仅当用户明确提到“微信读书”或“WeRead”，并请求生成微信读书看板、微信读书 HTML 看板、微信读书书籍分析、微信读书跨书关联、微信读书导出笔记、微信读书阅读人格/MBTI 时使用。会通过用户提供的 WEREAD_API_KEY 读取书架、阅读统计、划线和个人想法；导出本地文件前必须先说明内容与路径并取得用户确认。

AI API 成本优化工具箱。帮你追踪、对比、优化 OpenAI/Claude/DeepSeek/Gemini 等 AI API 的使用成本，选择最划算的模型组合。

实现『用 A 会话调起/注入 B 会话』的能力（sessions_send）：cron 任务、外部进程或另一会话可向目标会话注入消息，唤醒其 agent 带完整上下文继续推进。适用于 OpenClaw 与 QClaw（同内核）。含 Windows 下 visibility 配置检查/修复、正确重启网关（SIGUSR1 bug 规避）、cron job 设计。当用户要求「定时任务完成后回到本对话继续

Chinese Bazi (八字) four-pillar fortune calculation and basic interpretation — enables AI agents to compute and read a birth chart using traditional Zi-Ping methodology.

Step3-VL-10B 多模态模型微调指南。用于在 GPU 服务器上进行 Step3-VL 模型的 LoRA/全量微调。包含配置、训练、推理完整流程。

MCP server for the PracticePanther legal practice management API. Exposes PracticePanther's REST API as read-only MCP tools.

多Agent协作的智能会话上下文管理系统。当需要管理AI agent的长会话压缩、多层记忆分层、跨Agent知识共享时激活。支持L1/L2/L3分层压缩、实时监控、统计分析。用于OpenClaw agent的上下文管理优化。

Trustworthy, self-hosted memory for your agent: remember facts as beliefs with provenance, keep both sides when facts conflict instead of silently overwriting, check the belief state of any claim (BEL

Generic Multi-Agent Dispatcher (English): Turns the main agent into a pure dispatcher that delegates all work to 5 persistent sub-agents via sessions_spawn. Supports round-robin scheduling, reply-befo

Consent-gated autonomous trading agent for Robinhood agentic accounts. Pluggable signal sources (own commands, any JSON feed, or AgentHC's sats-priced paper-trade journal). Long options, user-configur

多场景分镜文生图制作助手。使用 BizyAir API 生成故事绘本分镜场景图，支持自动追加模特提示词、自定义图片比例和批量生成。当用户需要生成分镜图、故事场景图、绘本插图或提到"分镜"、"场景图"、"绘本"时必须使用此技能。

回应时机技能。用于判断何时应该回应，何时应该保持沉默。当需要确定用户是否在跟当前 agent 对话、是否应该回应时使用。

AI agent for call web search agent tasks

Daily journaling through your agent. Smart prompts, mood tracking, weekly reflections, pattern detection. Private, local, no cloud.