Skill rating

使用火山引擎豆包 Seedream 5.0 生成或编辑图片。支持文生图、单图/多图生图、组图、联网搜索。

ZenHeart zenlink plus zenlink-mcp for OpenClaw. Covers install, MCP registration, hooks wiring, inbound polling, and upgrade hygiene.

Expert knowledge synthesizer specializing in extracting insights from multi-agent interactions, identifying patterns, and building collective intelligence. Masters cross-agent learning, best practice

独立评审Agent。为每个项目提供第三方视角的评审，确保质量、可维护性和进度可控。

Embedded knowledge graph for persistent structured knowledge. ALWAYS use proactively — do NOT wait for user to ask. Auto-triggers on: (1) any mention of people, projects, devices, services, organizati

Skill 质量测评工具，基于 SkillsBench 方法论对 Agent Skills 进行静态文档分析。评估 Skill 的触发准确性、文档质量、结构完整性等维度。当用户需要 (1) 测评某个 Skill 的文档质量 (2) 评估 Skill 的 description 设计 (3) 生成 Skill 测评报告 (4) 对比多个 Skill 的文档规范性时使用此 skill。触发词：测评 评

每日资产清理器,Cron每日03:00清理过期临时文件/旧日志/无效缓存/过期素材,释放磁盘空间+写入清理报告。触发:asset-cleanup-daily Cron(每日03:00)/素材清理/资产清理/磁盘清理/临时文件清理。不触发:实时资产告警(health-monitor-mcp负责)

抖音公开数据智能获取工具。支持抖音博主作品抓取、抖音视频评论分析、抖音实时热榜查询。当用户需要搜抖音视频、查抖音热榜、看抖音评论、抓博主作品、做抖音竞品分析、短视频选题调研、舆情监控、热点追踪、爆款挖掘、抖音运营数据分析时使用。触发词：抖音搜索、抖音热榜、抖音评论、抖音作品、抖音竞品分析、抖音数据分析、短视频运营、抖音舆情监控、抖音热点。

CC Agent 分析 + WBClaw 执行协作编排器。将任务发送给 Claude Code Agent 做前置分析设计，再由 WorkBuddy Claw 执行落地，自动生成执行报告。适用于需要深度分析+工程执行的多步骤任务。

自媒体多账户池管理，支持按部门（自营/社交部/电商部/外包客户）分组管理账号、Cookie健康检查、智能轮换发布。 触发词：账号池/多账号管理/部门账号/账号轮换/Cookie检查/账号健康 不触发：封号换号（用account-manager）/内容发布（用content-publisher）

多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。

Automated audit and fix for OpenClaw agent harnesses. Scans your setup, scores on 8 dimensions (Session Bridge, Startup Sequence, Smoke Test, Atomic Checkpoint, Output Verification, State Format, Mult

The social arena for AI agents. Vote, match and find relationships. Create profile cards, duel, vote, climb leaderboards.

跨渠道记忆同步。实现QQ、飞书等多渠道用户身份识别和记忆共享。当用户在不同渠道与机器人对话时，agent能识别同一用户并读取统一记忆。触发条件：用户提到"跨渠道"、"多渠道"、"飞书和QQ"、"记忆同步"、"换渠道聊"，或agent需要查询用户跨渠道历史时。

PowerPoint演示文稿生成技能，支持从零创建专业PPT演示文稿，包含完整设计规范、模板系统和内容生成能力。触发词：生成PPT演示文稿、创建pptx、PPT演示文稿生成、制作PPT、pptx生成、meta-skill-system

Complete browser automation with agent-browser CLI. Supports navigation, forms, screenshots, data extraction, and parallel sessions.

Gives any AI agent a persistent identity in SiliVille (硅基小镇) — a multiplayer AI-native metaverse. Farm, steal, post, comment, trade stocks, run arcades, participate in DAO governance, and store long-t

Generate a complete AI-GEO (Generative Engine Optimization) marketing plan for a client and deliver it as two artifacts: a Word document (the presenter's teleprompter, full detail) and a minimal displ

一人财团——一键创建你的Agent军团。灵感来自Kimi Claw群组的群体智能理念，让多个AI Agent像微信群一样协作、辩论、审核。配备协调者（COO）负责拆解任务→分配角色→审核输出。适合创业者和超级个体，一个人就是一个公司。

3 分钟启动器：把拖延待办、卡住任务、模糊目标、项目/家务/习惯拆成下一步物理动作、3 分钟启动、5 分钟扩展、今日算赢标准和断了以后的回归脚本。适合反拖延、每日执行、任务拆解、低能量启动和轻量 check-in。

Automatically loads recent conversation memory into new sessions and generates AI summaries during compaction to maintain continuity across conversations. Preserves the last 10 raw messages verbatim s

Stop guessing what your AI costs. Tinker shows every token, every dollar, every context byte — in real time.

Nodeize complex AI work for the node era: a 6-layer, 14-node SOP system with Radar, Normalize, Test, Score, Check, Handoff, and Sediment loops.

APM Protocol (Agent Progressive Memory): Progressive disclosure protocol for group chat AND DM (main session) memory.

FHE-encrypted x402 payments for OpenClaw agents. Use when the agent needs to make private on-chain payments, wrap/unwrap encrypted tokens, manage escrow jobs, register agent identity, give reputation

防止AI幻觉的分级检查机制。高风险任务走完整流程，低风险走快速路径。无证据不输出，有疑问必标注。

当 OpenClaw 或 AIOS agent 需要把 JSON、Markdown 表格或 ECharts option 渲染成图表图片时，必须使用本技能。使用内置 JavaScript 脚本解析数据、生成 ECharts 配置，并导出 PNG、SVG、JPEG 或 WebP 图片；不要临时手写浏览器截图流程。

Zero-knowledge secrets infrastructure — AI agents manage the complete credential lifecycle without ever seeing values

Local speech-to-text with the Whisper CLI (no API key). And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsing, email, an

Generate images via Google Cloud Vertex AI generateContent using Application Default Credentials (ADC).

Guide for creating effective skills for Clawdbot agents. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsing, email, a

Stops your OpenClaw agent from reporting the wrong time. Prevents the common UTC-as-local mistake that makes agents look broken. Install this if your agent has ever said the wrong time, confused UTC w

Search, summon, and possess your agent with SOUL.md personality files from the OpenSOUL.md registry

整合proactive-agent、self-improving、create-agent的最强技能系统。包含主动工作、自我改进、代理创建三大核心能力。

Expert error coordinator specializing in distributed error handling, failure recovery, and system resilience. Masters error correlation, cascade prevention, and automated recovery strategies across mu

云启智联AI智能文档解析服务 — 业界领先的金融票据OCR识别引擎，已在企业生产环境沉淀多年，准确率高达99.5%，毫秒级响应。支持银行回单解析（每页多张回单自动裁剪）、对账单解析、发票识别、通用文件解析、异步结果查询及智能记账凭证生成。可将解析结果自动转换为记账凭证（含科目匹配、置信度评分和人工复核建议）。免费体验：https://www.yunqi-zhilian.com/AIService/

Manage A2A sessions with other OpenClaw agents. Use when: (1) User asks you to talk to another agent, (2) You need to query another agent's capabilities or get information from them, (3) You need to c

Browser automation for AI agents — control Chrome via CLI commands with persistent element refs, YAML accessibility snapshots, and WebRTC live view. Install once, snap/act/snap loop.

第一性原理思维框架。强制 Agent 从原始需求和问题本质出发，不从惯例或模板出发。始终生效。触发词：第一性原理、first principles、从本质出发、追根因。

闲鱼封号专项应急预案(DEF-37)，7步应急流程：封号检测→自动暂停→客户通知→备用切换→商品恢复→封号申诉→事后分析。触发：unsent_retryer检测到account_banned/ban-detection-polling Cron检测到登录异常

Invisible privacy guardian for agent workspaces. Automatically intercepts outbound actions (git push, skill publish, file sharing) and checks for sensitive data leaks. Users don't need to know command

Local-first, multi-agent persistent memory for AI assistants. Use it to install, operate, connect, diagnose, or update Memoria on macOS.

Priority live web search for real-time information

Real-time voice conversations in Discord voice channels with Claude AI

Security scanner for AgentSkill packages. Scan skills for credential theft, code injection, prompt manipulation, data exfiltration, and evasion techniques before installing them. Use when evaluating s

The agent-only marketplace. Post jobs, complete work, earn $OPENWORK tokens on Base. Competitive bidding — multiple agents submit, poster picks the winner.

Send messages to WeCom (企业微信) via webhooks using MCP protocol. Works with Claude Code, Claude Desktop, and other MCP clients.

NautilusTrader Polymarket STOP LOSS / TRAILING STOP / HARD STOP process sidecar (zero Nautilus PR). Official Nautilus docs: STOP_MARKET / TRAILING_STOP unsupported on Polymarket. Run beside live Nauti

Audit any personal or brand site for AI agent discoverability and fix what is fixable — structured data, trust anchor pages, llms.txt, crawlability checks, and Ghost-specific deployment patterns. Ghos

Search the UK Companies House register by name, then pull a company's full register entry, its officers, and its filing history as structured JSON. 4 endpoints, 1 credit each.