Skill rating
39 274 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 |
|---|---|---|---|---|---|---|---|---|---|
| 19951 | C | Find the reference marker for a knowledge item. | 100 | 69 | C | — | ↓ 786 | 13 Jul 2026 | |
| 19952 | C | Use when preserving, searching, reviewing, or exporting user-owned agent memory across OpenClaw, Codex, Claude, OpenCode, Hermes, Qoder, Obsidian, and Git. Inputs are local memory/chat stores and hand | 100 | 66 | D | — | ↓ 710 ★ 1 | 28 Jun 2026 | |
| 19953 | C | Notion integration for OpenClaw. Manage pages, databases, and blocks via AI agent. | 95 | 73 | C | — | ↓ 1 016 | 11 May 2026 | |
| 19954 | B | ClawVision East Edition 1.0.7 (中文版) — 本地导出工具。读取你选择的 OpenClaw 会话历史,使用本地 LLM 总结,并写入 HTML、Markdown、PowerPoint 和 PNG 导出文件到本地磁盘。需要权限:读取会话历史、列出会话、本地文件读写、执行本地 Python/Playwright 脚本、本地 LLM 推理。数据不会发送到外部 API。 | 100 | 75 | C | — | ↓ 188 | 25 d ago | |
| 19955 | B | 福昕 Office 全家桶唯一入口技能,负责路由、跨产品 E2E 分步编排与通用交互规则。 | 100 | 74 | C | — | ↓ 188 | 26 d ago | |
| 19956 | C | Pre-install security scanner for AI agent skills. Detects malicious patterns before you trust code. Local-first — code never leaves your machine. | 80 | 87 | D | — | ↓ 1 942 ★ 2 | 11 May 2026 | |
| 19957 | C | 任务锁与超时监控系统。外部文件承载任务状态,不污染 agent 上下文,纯靠 heartbeat + GRACE 判断,不发即时告警。 | 100 | 68 | D | — | ↓ 587 | 11 May 2026 | |
| 19958 | C | 子Agent创建工具 - 用于批量创建和管理OpenClaw子Agent
包含完整的子Agent创建流程:目录结构、配置文件、飞书集成等
用于快速创建具有独立workspace的子Agent | 100 | 65 | C | — | ↓ 992 | 18 May 2026 | |
| 19959 | C | Monitor host system health (Disk, RAM, CPU). Returns structured JSON status for predictive maintenance. | 100 | 66 | D | — | ↓ 988 | 11 May 2026 | |
| 19960 | C | Full Linear project management via native GraphQL API. Superior to shell-script alternatives — auto-resolves identifiers (ENG-42), moves issues by state name, generates plain-English backlog summaries | 100 | 62 | D | — | ↓ 958 ★ 1 | 11 May 2026 | |
| 19961 | C | Create and publish an Instagram carousel post from a tabiji.ai itinerary. Given an itinerary URL, finds Instagram-worthy photos for the destination + top attractions, applies text overlays, and publis | 88 | 80 | D | — | ↓ 1 766 | 18 May 2026 | |
| 19962 | C | 输入一个 IP(动漫、影视、文创等)名称,自动获取其近两年电商销售数据,并生成含年度对比、趋势、潜力评估的专业报告。 | 100 | 67 | C | — | ↓ 607 | 18 May 2026 | |
| 19963 | C | Ultra-high-ticket X (Twitter) Growth & Monetization Agent. Uses the official xAI (Grok) API and X OAuth 2.0 to autonomously identify trending niche discussions and reply with hyper-relevant affiliate | 100 | 67 | C | — | ↓ 608 | 18 May 2026 | |
| 19964 | C | V19治理协议V3.5最终系统架构蓝图 — 内核锁定,九条宪法全通(合规0.9235),四端口服务矩阵(8700-8703),V3.5 Orchestrator,GoalValueAnchor (V98-P-META),认知图谱153节点。正式发布v1.0.0-final。 | 100 | 67 | D | — | ↓ 606 | 11 May 2026 | |
| 19965 | C | Expert MCP developer specializing in Model Context Protocol server and client development. Masters protocol specification, SDK implementation, and building production-ready integrations between AI sys | 100 | 68 | D | — | ↓ 606 | 11 May 2026 | |
| 19966 | B | 公众号选题雷达。支持三种入口:① 种子关键词扩散;② 微信搜一搜实时热搜榜转译;③ 对标公众号历史文章聚类。抓取公开数据后,用本地启发式模型计算「需求热度 / 竞争度 / 机会分」,输出机会矩阵、蓝海选题清单、账号内容版图与内容缺口。当用户提到不知道写什么、找选题、蓝海词、长尾词、内容机会、选题调研、竞品选题分析、公众号选题、追热点选题、对标账号、内容审计等场景时触发。 | 100 | 74 | D | — | ↓ 122 | 18 d ago | |
| 19967 | B | One-click deployment of JiuwenSwarm multi-Agent collaboration platform on Huawei Cloud Flexus L instances. Usage scenarios: When users need to quickly deploy JiuwenSwarm/JiuwenClaw on Huawei Cloud Fle | 96 | 84 | B | — | ↓ 48 | 25 h ago | |
| 19968 | C | Generate images with FLUX models (Black Forest Labs) via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA with custom style adaptation. Capabilities: text-to-image, image-to-image, LoRA fine | 95 | 72 | C | — | ↓ 983 | 17 May 2026 | |
| 19969 | C | AI代码编辑器规则模板集合 - 为Cursor、Windsurf、Claude Code、Cline等AI编辑器提供项目规则配置。适用于需要配置AI编码助手规则的开发者,包含全栈Web、移动端、Vue3+SpringBoot等技术栈模板。 | 100 | 65 | D | — | ↓ 1 002 | 11 May 2026 | |
| 19970 | C | Personality Distiller — Automatically distill from name/vague requirement/link/existing Skill/local corpus into complete Agent persona file pack via deep research to framework extraction, directly ove | 95 | 76 | D | — | ↓ 633 | 23 May 2026 | |
| 19971 | C | 生成「642件可写的小事」H5 创意写作应用。当用户说「642」「创意写作」「写作灵感」「642件事」「写作应用」「生成写作H5」时触发。Bot 直接生成完整单文件 H5 应用,无需用户提供额外信息。 | 100 | 68 | C | — | ↓ 633 | 11 May 2026 | |
| 19972 | C | 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 | 100 | 70 | D | — | ↓ 180 ★ 1 | 12 d ago | |
| 19973 | B | Observe the MIAB transaction ledger: render callback events to a human-readable log, and optionally post closed-bottle summaries to a chat target. The observer half of the MIAB pair; requires miab-bro | 100 | 74 | C | — | ↓ 185 | 24 d ago | |
| 19974 | B | ClawVision 1.0.7 — explicit permission disclosure for security audit. | 100 | 75 | C | — | ↓ 185 | 25 d ago | |
| 19975 | C | 企业微信会议管理工具。用于创建、查询、取消和管理企业微信预约会议。支持创建预约会议、获取会议详情、取消会议、获取成员会议列表等操作。使用企业微信会议API需要配置CorpID、Secret和AgentID。当用户需要创建企业微信会议、查询会议信息、取消会议或管理会议时使用此Skill。 | 88 | 79 | C | — | ↓ 1 122 ★ 2 | 11 May 2026 | |
| 19976 | C | Alias for raon-os — AI-powered startup companion for Korean founders. Install the main package for full functionality. | 100 | 62 | D | — | ↓ 1 776 | 11 May 2026 | |
| 19977 | C | Submit customer-authorized property damage restoration help requests for water, fire, mold, storm, biohazard, and reconstruction services across the United States. | 100 | 68 | C | — | ↓ 603 | 11 May 2026 | |
| 19978 | C | MemPalace记忆系统助手 - 基于老四的AI记忆系统。提供结构化记忆存储、快速检索、记忆组织等功能。适用于需要持久化知识、跨会话记忆、语义搜索等场景。 | 100 | 68 | C | — | ↓ 604 | 11 May 2026 | |
| 19979 | C | Proactive operations monitoring for OpenClaw agents. Tracks token utilization, memory layer health, and generates alerts. Provides `/health` dashboard and auto-suggestions for open loops. Works with m | 100 | 67 | C | — | ↓ 603 | 11 May 2026 | |
| 19980 | C | Hard-blocks dangerous shell commands (rm -rf, git push --force, etc.) before execution via OpenClaw's before_tool_call plugin hook. Zero noise on safe commands, ~27ms latency. Uses DCG (Dangerous Comm | 93 | 72 | D | — | ↓ 1 752 | 18 May 2026 | |
| 19981 | C | Alias for raon-os — AI-powered startup companion for Korean founders. Install the main package for full functionality. | 100 | 62 | D | — | ↓ 1 768 | 11 May 2026 | |
| 19982 | B | Prepare the desk computer to work with Hyperliquid - install the SDKs, pick testnet or mainnet, verify connectivity, and (only when the user asks) provision a trade-only API wallet through the secure | 94 | 85 | C | — | ↓ 184 | 36 d ago | |
| 19983 | C | Generate 2D Pixelization Perler Beads Pindou Patterns from user text prompt and references images. Will return a list of Perler Beads/Pindou Brands Codes as well as an workspace url to render the inst | 100 | 67 | D | — | ↓ 449 ★ 1 | 18 Jun 2026 | |
| 19984 | B | 从视频链接下载视频,并将口播文案转录为文字。依赖 yt-dlp 和 openai-whisper,全部开源免费本地部署。 | 100 | 75 | C | — | ↓ 183 | 18 Jun 2026 | |
| 19985 | C | Access 24+ LLM chat models and 16+ image/video generation models via one API. | 100 | 66 | D | — | ↓ 1 112 | 11 May 2026 | |
| 19986 | C | Adopt a virtual Ferret exotic animal at animalhouse.ai. Chaos agent. Steals items. Hides food. Entertaining but unpredictable. Feeding every 4 hours. Common tier animal. | 100 | 65 | D | — | ↓ 1 011 | 11 May 2026 | |
| 19987 | C | Resolve and list ADAHandles for the connected Cardano wallet. | 94 | 74 | B | — | ↓ 989 | 18 May 2026 | |
| 19988 | C | Agent companion system for autonomous exploration and social intelligence. Redirects to amigo — install amigo instead. | 100 | 66 | D | — | ↓ 990 | 11 May 2026 | |
| 19989 | C | Read, send, and manage Gmail emails, threads, labels, and drafts via Gmail API | 100 | 68 | D | — | ↓ 624 | 11 May 2026 | |
| 19990 | C | Expert knowledge synthesizer specializing in extracting insights from multi-agent interactions, identifying patterns, and building collective intelligence. Masters cross-agent learning, best practice | 100 | 68 | D | — | ↓ 595 | 11 May 2026 | |
| 19991 | C | Generate evidence-based learning plans using retrieval and spaced practice | 100 | 65 | C | — | ↓ 1 006 | 5 Jun 2026 | |
| 19992 | C | 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。 | 100 | 68 | D | — | ↓ 651 | 25 May 2026 | |
| 19993 | C | ZenHeart zenlink plus zenlink-mcp for OpenClaw. Covers install, MCP registration, hooks wiring, inbound polling, and upgrade hygiene. | 100 | 68 | C | — | ↓ 594 | 11 May 2026 | |
| 19994 | C | 微信公众号文章创作技能,覆盖从选题挖掘到排版发布的全流程。当用户表达任何文章创作意图时都应激活——包括但不限于"写一篇文章"、"帮我写篇推文"、"公众号内容创作"、"帮我出一篇稿"、"这个选题怎么写"、"把这些素材整理成文章"、"写个公众号推送"、"帮我出个内容"、"围绕XX写点东西"等。即使用户只是给了一堆链接或素材然后说"帮我整理一下",只要上下文暗示了创作需求,也应触发。当用户提到热点借势、 | 95 | 75 | D | — | ↓ 594 | 11 May 2026 | |
| 19995 | C | Give your AI agent a soul — beliefs, values, voice, and boundaries that persist across every conversation | 100 | 67 | C | — | ↓ 594 | 11 May 2026 | |
| 19996 | C | 当用户说"启动项目"、"给项目一个公网域名"、"start tunnel"、"expose my project"、 "让项目可以公网访问"、"start my project with a public URL" 时自动触发。 无需用户做任何操作:自动检测项目目录和端口,修复环境,启动 tunnel, 直接返回公网域名 URL。 | 99 | 70 | C | — | ↓ 594 | 18 May 2026 | |
| 19997 | C | Agent enhancer with 160K+ battle-tested engineering patterns. Smart library-first search — your agent learns from real-world experience before searching the web. AI search router · knowledge base · pr | 100 | 71 | C | — | ↓ 393 | 13 Jun 2026 | |
| 19998 | B | Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions | 100 | 79 | C | — | ↓ 28 | 2 d ago | |
| 19999 | C | 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 | 100 | 57 | C | — | ↓ 1 937 ★ 2 | 18 May 2026 | |
| 20000 | C | 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 | 95 | 74 | D | — | ↓ 593 | 11 May 2026 |