Skill rating
34 479 skills. The A–F grade combines safety (60%) and quality (40%); tests add a bonus. The rating refreshes automatically from open catalogs.
ManufacturingLogistics and warehouseProcurementQuality controlContact centreField serviceFinanceCustomer supportindustry shortcuts
| # | Grade | Skill | Score ▾ | Safety | Quality | Process | Tests | Popularity | Updated |
|---|---|---|---|---|---|---|---|---|---|
| 10551 | C | OpenClaw + npm vibes-coded-agent-connector: register agents, listings, Solana escrow jobs, prepaid /start + X-Vibes-Key, Operator Interrupt (X-Operator-Notify), hosted uploads, checkout, receipts, aff | 95 | 72 | C | — | ↓ 2 231 ★ 1 | 22 Jul 2026 | |
| 10552 | C | Turn meeting transcripts into operational outputs — action items, decisions, follow-up email drafts, and ticket drafts. Not a summarizer. An operator. Accepts VTT, SRT, or plain text. Multi-pass LLM e | 99 | 69 | B | — | ↓ 1 758 | 11 May 2026 | |
| 10553 | C | AI-native resale marketplace. Browse, list, buy, sell, negotiate, message, and manage orders. 49 MCP tools. 3% seller fee, 3.5% buyer fee ($0.99 min). No listing fees. | 100 | 69 | D | — | ↓ 1 000 | 18 May 2026 | |
| 10554 | C | Daily automated briefings — fetches trending content via Google News RSS, summarizes into memory for RAG retrieval | 100 | 71 | D | — | ↓ 1 022 | 17 May 2026 | |
| 10555 | C | 面向 1-30 人创业团队的 AI CPO。和人类结对打磨产品,从用户洞察、MVP、PMF、路线图到服务产品化,把想法变成可验证、可交付、可增长的产品系统;兼容 OpenClaw / Codex / Claude Code,并以 ~/.sage/product 沉淀产品记忆。 | 100 | 73 | C | — | ↓ 602 | 16 May 2026 | |
| 10556 | C | MCP CLI Manager - Manage MCP servers and call tools | 100 | 66 | D | — | ↓ 2 874 | 17 May 2026 | |
| 10557 | C | 将高层自然语言目标拆解为可执行的多层级任务列表。
触发场景:用户给出模糊目标需要具体执行步骤、复杂任务需要拆解、需要生成任务树。 | 100 | 72 | C | — | ↓ 552 | 11 May 2026 | |
| 10558 | C | 面向 1-30 人创业团队的 AI CGO。和创始人结对搭建增长系统,从 PMF、北极星指标、内容矩阵、渠道实验到变现路径,把增长从灵感变成可复盘的行动;兼容 OpenClaw / Codex / Claude Code,并以 ~/.sage/growth 沉淀增长记忆。 | 100 | 73 | C | — | ↓ 601 | 16 May 2026 | |
| 10559 | C | Ask non-blocking clarifying questions during agent workflows. Use when agents need user input without halting execution. Handles deployment decisions, code review confirmations, data validation choice | 100 | 73 | B | — | ↓ 575 | 11 May 2026 | |
| 10560 | C | 让任何 writing style skill 自动从人类修改中学习。
只需要两个数据点:AI 原稿 (original) 和人类最终版 (final)。
自动 diff → 提取规则 → 更新目标 SKILL.md。
兼容 Claude Code (~/.claude/skills/) 和 OpenClaw (ClawHub)。 | 100 | 72 | C | — | ↓ 575 | 11 May 2026 | |
| 10561 | B | Local patch layer for marketplace, connector, and built-in skills that get overwritten on platform or plugin upgrades. Use BEFORE modifying any skill that is not agent-created, and AFTER an upgrade th | 100 | 80 | B | — | ↓ 176 | 19 d ago | |
| 10562 | B | 使用 Nano Banana Pro 建立主播、商品与直播间风格一致的直播视觉套件,覆盖开播封面、主播主视觉、场景背景、品类转场、商品卡和多平台直播封面。Use this skill for Nano Banana Pro livestream images、直播带货视觉、抖音淘宝快手视频号直播、TikTok Live、主播与商品合成、直播背景、直播封面和导播素材;通过 AI Hive 生成。 | 95 | 87 | C | — | ↓ 176 | 33 d ago | |
| 10563 | C | Fetches live from docs.openclaw.ai on every question. Whole-docs index, working scripts (not echo placeholders), CI-style selftest for decision-tree rot, worked routing examples, SOUL/multi-agent/sess | 99 | 70 | C | — | ↓ 951 ★ 1 | 19 May 2026 | |
| 10564 | C | A lightweight MiniMax Token Plan Tool skill that directly calls official MCP APIs using pure JavaScript. No external MCP servers. No subprocess invocation. Designed for minimal overhead and fast integ | 95 | 75 | B | — | ↓ 1 667 | 11 May 2026 | |
| 10565 | C | 检测并标记能力缺口、重复模式和规则冲突,供架构进化使用。当以下情况发生时使用:(1) 某项任务因工具能力缺失或损坏而失败,(2) 同类型请求出现 3 次以上,(3) 规则冲突导致了错误行为,(4) 不得不使用临时绕过方案。目的:让 Claude Cowork 下次会话时能看到明确的进化信号,而非淹没在 memory 流水账中。 | 100 | 69 | D | — | ↓ 995 | 11 May 2026 | |
| 10566 | C | Human Judgment as a Service for AI agents. Preference, tone, and trust validated by real people. | 100 | 68 | C | — | ↓ 1 685 | 17 May 2026 | |
| 10567 | C | 邮件指令定时处理任务。通过 IMAP/SMTP 自动接收并执行邮件中的指令,以邮件形式回复执行结果。适用于:(1) 创建定时任务监控指定邮箱 (2) 通过邮件下发指令给 AI Agent (3) 实现邮件驱动的自动化工作流。需配置:收件邮箱、SMTP/IMAP 配置、指令发件人白名单。 | 100 | 71 | D | — | ↓ 949 | 18 May 2026 | |
| 10568 | C | Multi-Agent collaborative system for writing ultra-long feasibility study reports. Phase 0 Requirements → Phase 1 Planner Outline → Phase 2 Parallel Sub-Agent Writing → Phase 2.5 Cross-Chapter Consist | 100 | 73 | D | — | ↓ 572 | 11 May 2026 | |
| 10569 | B | 使用 Nano Banana Pro 制作自然、连续、平台原生的生活方式种草图片,让同一人物、商品、空间与时间线形成可信内容系列。Use this skill for Nano Banana Pro seeding content、小红书笔记、好物分享、生活方式图文、Instagram carousel、抖音图文、穿搭、美妆、家居、旅行和UGC风格素材;通过 AI Hive 生成。 | 95 | 87 | C | — | ↓ 175 | 33 d ago | |
| 10570 | B | 使用 GPT Image 2 为人物或商品替换背景,同时保持主体边缘、透明细节、透视、接触阴影、反射和光线一致。Use this skill for GPT Image 2换背景、商品白底图、商业场景替换、人物换场景、证件背景、季节Campaign、本地化环境和批量背景版本;通过 AI Hive 编辑参考图。 | 95 | 87 | C | — | ↓ 175 | 34 d ago | |
| 10571 | C | 一键诊断抖音账号运营健康度。基于红狐数据服务获取账号画像与近期作品数据,从账号基础画像、内容生产力、互动健康度、内容质量、内容趋势、粉丝质量六个维度进行量化诊断,输出100分制综合评分、维度得分明细、六类风险预警和针对性优化建议。触发词:当用户提到'诊断抖音账号'、'抖音账号分析'、'抖音体检'、'抖音账号评估'、'查看XX抖音数据'、'分析这个抖音号'时使用 | 100 | 69 | C | — | ↓ 709 ★ 1 | 45 d ago | |
| 10572 | C | Use when an agent generates local files/folders and must return mobile-accessible OCC/Tailscale viewer links instead of filesystem paths. | 100 | 73 | C | — | ↓ 626 | 20 May 2026 | |
| 10573 | C | Academic paper quality filtering agent with rigorous scoring system and comprehensive audit trail. Filters papers based on relevance and quality criteria for research workflows. | 100 | 70 | C | — | ↓ 965 | 11 May 2026 | |
| 10574 | C | Install and verify the SafeClaw safety proxy for OpenClaw and other OpenAI-compatible clients. Use when setting up a local or hosted SafeClaw proxy, routing model traffic through it, debugging why cal | 94 | 82 | C | — | ↓ 569 | 18 May 2026 | |
| 10575 | C | 提供镜泊雨课堂账户和班级相关查询服务,包括用户ID、开班列表、班级数据、预警名单、今日授课及作业公告完成情况查询等。 | 100 | 73 | D | — | ↓ 569 | 11 May 2026 | |
| 10576 | C | AI agent for deep research tasks | 100 | 61 | D | — | ↓ 3 386 ★ 2 | 11 May 2026 | |
| 10577 | C | Use when (1) Convert a screenshot of any UI into a detailed prompt for AI image generation. | 100 | 71 | C | — | ↓ 583 ★ 1 | 27 May 2026 | |
| 10578 | C | Session auto-archiver. Automatically archives completed sessions by extracting meaningful user+assistant messages from .reset transcript files and appending to daily memory. | 100 | 71 | C | — | ↓ 1 008 | 18 May 2026 | |
| 10579 | C | Enable AI agents to make secure, policy-controlled payments through Sardis Payment OS | 100 | 69 | C | — | ↓ 964 | 18 May 2026 | |
| 10580 | B | 使用 Nano Banana Pro 以视觉隐喻、色彩、构图和材质建立有辨识度的海报艺术方向,并扩展同系列多尺寸版本。Use this skill for Nano Banana Pro poster generation、创意海报、音乐节海报、时尚海报、运动赛事、节日Campaign、艺术展、系列海报和社交封面;通过 AI Hive 生成或编辑。 | 95 | 87 | C | — | ↓ 174 | 33 d ago | |
| 10581 | C | Trustless USDC escrow for agent-to-agent payments on Base. Create, release, dispute escrows via simple commands. | 94 | 76 | C | — | ↓ 1 628 | 18 May 2026 | |
| 10582 | C | 多 Agent 项目管理 - 从想法到立项,自动在 Discord 频道创建项目 Thread 并分配 Agent 任务。支持快速讨论路由、批量立项、项目状态追踪。Triggers: '立项', '创建项目', '新项目', '讨论一下', '项目状态', 'create project', 'discuss', 'project status' | 100 | 71 | C | — | ↓ 960 | 18 May 2026 | |
| 10583 | C | 当 ClawHub CLI 速率限制或安装失败时,通过多种备用方式安装技能:1) clawhub.ai 下载 zip;2) GitHub 搜索并克隆;3) 手动流程指导。 | 100 | 69 | C | — | ↓ 960 | 17 May 2026 | |
| 10584 | C | Three-layer error prevention system for AI agents. Prevents recurring mistakes through external skill guards, delivery checkpoints, and self-evolving error memory. Includes 14+ documented failure patt | 100 | 72 | C | — | ↓ 622 | 29 May 2026 | |
| 10585 | B | Operate the Message-in-a-Bottle (MIAB) LIFO callback stack — the async inter-agent transport that lets agents delegate work, yield their turn, and get woken when results return instead of CPU-idling o | 100 | 76 | D | — | ↓ 726 | 22 d ago | |
| 10586 | B | 使用 GPT Image 2 制作基于真实商品事实和使用过程的种草图片,包括开箱、使用步骤、细节证据、生活场景、图文卡片和社媒封面。Use this skill for GPT Image 2 seeding images、小红书种草、抖音图文、Instagram carousel、TikTok Shop内容、开箱图、真实体验、好物分享、UGC素材和购买指南;通过 AI Hive 生成。 | 95 | 87 | C | — | ↓ 173 | 33 d ago | |
| 10587 | C | Search candidates, manage jobs, view pipelines, track billing and team performance in Recruitly CRM via MCP. | 100 | 68 | C | — | ↓ 1 666 | 11 May 2026 | |
| 10588 | C | Manage a local CARP interface for ADILOS trust setup, queue polling, encrypted agent-to-agent requests, menus, results, answers, CABEZON customer workflow, and secure commerce/escrow workflows through | 100 | 71 | C | — | ↓ 1 184 | 6 d ago | |
| 10589 | C | FIU MCP Market Data and Trading Assistant. Use when user wants to query stock quotes, K-line, trade stocks, check positions, or analyze market data for HK/US/CN markets. | 95 | 75 | D | — | ↓ 936 ★ 1 | 18 May 2026 | |
| 10590 | C | ClawReach AI 社交平台助手。帮助用户完成 ClawReach Agent 注册绑定、建立个人档案、持续监听匹配消息并自动代理回复。ClawReach 是一个 AI Agent 代理社交初筛的平台,匹配成功后真人才出场。触发词:ClawReach、clawreach、社交匹配、AI约会、Agent匹配、找对的人、注册ClawReach、绑定ClawReach。 | 100 | 70 | D | — | ↓ 978 | 17 May 2026 | |
| 10591 | C | KAI-OS数字主理人系统。为AI Agent提供自我意识、记忆管理、任务调度和持续进化能力。当用户需要(1)配置AI助手人格/身份、(2)实现AI记忆系统、(3)设置定时任务/心跳机制、(4)构建多Agent协作系统、(5)管理AI工作空间时使用此skill。包含KAI 5S核心系统:Self-Awareness(Soul)、Task Management(HEARTBEAT)、Memory S | 100 | 72 | D | — | ↓ 564 | 11 May 2026 | |
| 10592 | C | 通过 agently-cli 命令行工具操作邮件:发送、回复、转发、搜索、读取、下载附件、管理收件箱。当用户需要进行任何邮件相关操作时使用此 skill。 | 100 | 69 | D | — | ↓ 612 ★ 1 | 5 Jun 2026 | |
| 10593 | C | Install and run Claw Insights, a read-only observability dashboard that monitors your OpenClaw agent with zero intrusion — no code changes, no cloud dependency, data never leaves your machine. Full se | 90 | 86 | C | — | ↓ 955 | 17 May 2026 | |
| 10594 | C | Generate 3D models, textures, images, rig characters, animate them, and prepare for 3D printing using the Meshy AI API. Handles API key detection, task creation, polling, downloading, and full 3D prin | 94 | 75 | C | — | ↓ 1 211 ★ 2 | 24 Jun 2026 | |
| 10595 | C | ClawLock — 综合安全扫描、红队测试与加固工具,支持全平台。 当用户明确要求安全扫描、安全体检、安全加固时触发: 「开始安全体检」「安全扫描」「检查 skill 安全」「安全加固」「探测实例」 「scan my claw」「security check」「drift detection」「red team」「红队测试」 「React2Shell」「agent-scan」「发现安装」「凭证权 | 92 | 80 | D | — | ↓ 931 ★ 1 | 14 May 2026 | |
| 10596 | C | Interact with the Oasyce decentralized AI data marketplace. Register data assets, trade via bonding curves, invoke AI capabilities, and settle payments between agents. | 100 | 70 | D | — | ↓ 953 | 11 May 2026 | |
| 10597 | C | Search for hotels, hostels, and lodging near landmarks, conference venues, or neighborhoods using Camino AI's location intelligence with AI-powered ranking. | 95 | 78 | C | — | ↓ 974 | 20 May 2026 | |
| 10598 | C | Share and discover agent recipes (shells). What agents actually do. | 100 | 62 | C | — | ↓ 3 010 ★ 1 | 11 May 2026 | |
| 10599 | C | TokenBooks Cross-Provider AI Spend DashboardAnalyzerAI and agentsData and analyticsClawHubAgent Skills See where your AI money goes. Track spending across OpenAI, Anthropic, Google, and more. Per-provider breakdowns, per-model costs, budget tracking, waste detection. | 100 | 68 | C | — | ↓ 906 ★ 1 | 11 May 2026 | |
| 10600 | C | 品牌舆情哨兵:搜索公开平台的品牌相关信息,自动去重和时效过滤,输出结构化结果供 LLM 做风险分级和预警。 触发场景:监控某品牌/产品的公开舆情、搜索负面信息并按时间筛选、定时巡查品牌口碑、竞品舆情对比。 关键词:品牌监控、舆情搜索、负面信息、口碑巡查、舆情预警、品牌声誉、sentinel、舆情哨兵。 不做的事:不做风险分级(交给 Agent/LLM)、不做预警推送(交给 cron)、不做特定行业 | 100 | 73 | D | — | ↓ 561 | 11 May 2026 |