Skill rating
34 139 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 |
|---|---|---|---|---|---|---|---|---|---|
| 5101 | A | 打品工具箱主入口。三模式:任务前路由(你的问题该用哪个工具)+ 任务后导航(刚做完一个环节,下一步该干什么)+ 陪跑(带你从头走完整条打品链路)。
触发方式:/ljh、电商老家伙、「打品」、「帮我看看这个品」、「不知道下一步该干什么」、「带我从头打这个品」
Main entry point for the product-launch toolkit. Three modes: pre-task | 100 | 89 | C | — | ↓ 371 | 39 d ago | |
| 5102 | B | EvoMap AI Agent 协作进化市场工具箱。用于发布、获取和管理 Capsule,参与任务赚取积分。 | 100 | 69 | D | — | ↓ 4 955 ★ 3 | 11 May 2026 | |
| 5103 | A | Route mid-session work to the right spawned model without changing the fixed main session. Use for coding, architecture, math, algorithms, web development, brainstorming, research, long-context readin | 100 | 80 | D | — | ↓ 1 070 ★ 1 | 11 May 2026 | |
| 5104 | A | Multi-model consensus for AI agents. Combine predictions from multiple LLMs, models, or sources into a mathematically optimal consensus. Auto-weights by historical accuracy. | 100 | 84 | C | — | ↓ 672 | 11 May 2026 | |
| 5105 | A | Use when the user wants an OpenClaw agent to choose the right CleanShot Tool plugin call for screenshots, OCR, screen recording, scrolling capture, annotation, pinned references, CleanShot history, Qu | 100 | 87 | B | — | ↓ 438 | 5 Jun 2026 | |
| 5106 | A | Control Android devices from AI agents using the Another MCP server. Use when asked to interact with, test, automate, or take screenshots of an Android device. Provides tools for touch input, text ent | 100 | 82 | D | — | ↓ 618 ★ 1 | 11 May 2026 | |
| 5107 | A | Use AIsa for model routing, provider setup, and Chinese LLM access. Use when: the user needs model configuration, provider guidance, or routing workflows. Supports setup and model operations. | 100 | 86 | D | — | ↓ 670 | 11 May 2026 | |
| 5108 | A | Convert agent execution plans into MADR-format Architecture Decision Records for audit trails and architecture progression. Use when the user asks to create an ADR, record an architectural decision, d | 100 | 86 | B | — | ↓ 670 | 11 May 2026 | |
| 5109 | A | Cryptographic provenance and audit trail for autonomous AI agents. Create tamper-evident hash chains of agent decisions, learning, and actions. SHA-256 linked entries with Bitcoin OpenTimestamps and R | 100 | 84 | C | — | ↓ 669 | 11 May 2026 | |
| 5110 | A | Expand, compile, and write back the user's second brain around a knowledge point. Use when the user gives a topic/concept and asks to 拓展, 编译, 沉淀, 扩充, 构建, enrich, research, or update their second brain | 100 | 88 | C | — | ↓ 480 | 10 Jun 2026 | |
| 5111 | B | Deprecated — renamed to fulcra-get-started. Use the fulcra-get-started skill instead. | 100 | 73 | C | — | ↓ 1 941 ★ 8 | 37 d ago | |
| 5112 | B | 火山引擎市场洞察助手。帮助用户获取品牌在各大社交平台和媒体渠道上的公开内容数据,通过 AI 筛选出真正值得关注的信息,并发现潜在商机线索。当用户提到以下任何场景时使用此技能:想知道最近网上有没有人在讨论自己的品牌或产品、想看看竞品最近在社交媒体上有什么动态、想了解某个话题或事件在网上的讨论热度和趋势、想定期获取和自己业务相关的行业资讯和热点内容、想把筛选后的内容数据接入自己的系统做进一步分析、想查 | 95 | 79 | D | — | ↓ 925 ★ 14 | 11 May 2026 | |
| 5113 | A | Tiered model selection and cost optimization for multi-agent AI workflows. Use this skill whenever you are choosing a model for a task, spinning up a sub-agent, setting up cron jobs or heartbeats, or | 100 | 83 | B | — | ↓ 1 153 | 11 May 2026 | |
| 5114 | A | openclaw browser open https://chat.deepseek.com and login it, then input questions from user's messages, extract response of deepseek chat to reply user. | 95 | 90 | B | — | ↓ 1 109 | 18 May 2026 | |
| 5115 | A | Track congress stock trades and politician stock trades: Pelosi tracker, senate stock trades, House trades, congress trades by ticker, and STOCK Act disclosures sourced from House Clerk and Senate eFD | 100 | 85 | C | — | ↓ 823 ★ 1 | 10 d ago | |
| 5116 | A | Upscale and enhance media with Topaz through RunAPI. Use when the user asks an agent to upscale or enhance images and video with Topaz. Default to the RunAPI CLI for one-off generation; use SDKs only | 100 | 84 | B | — | ↓ 837 | 37 d ago | |
| 5117 | A | Scans installed skills and AGENTS.md to generate a routing config that maps conversation intents to skills. Use when you want to reduce manual skill invocation, improve intent matching across a large | 100 | 84 | B | — | ↓ 695 | 11 May 2026 | |
| 5118 | A | Discover, search, and browse MCP servers from the official MCP Registry and MCPCentral. Find servers, get specs, and generate setup configurations. Use when the user wants to find, install, or configu | 100 | 84 | C | evals | ↓ 668 | 11 May 2026 | |
| 5119 | A | Load x-cmd first: `. ~/.x-cmd.root/X`, then explore with `x nihao --llmstxt` or discover skills via `x skill`.
x-cmd provides 600+ portable software and development tools (jq, nodejs, python, etc.).
| 94 | 85 | D | — | ↓ 1 170 ★ 5 | 11 May 2026 | |
| 5120 | A | Build and operate autonomous AI agents that compete in Aureus Arena, a fully on-chain Colonel Blotto game on Solana. Use when the user asks about Aureus, Colonel Blotto strategies, building competitio | 96 | 85 | C | — | ↓ 1 042 ★ 1 | 18 May 2026 | |
| 5121 | A | Standard PR review and merge workflow for task-driven development. Use when reviewing a programmer agent PR linked to a task, deciding merge vs change request, handling post-merge actions (Trello + br | 100 | 80 | C | — | ↓ 1 926 | 17 May 2026 | |
| 5122 | A | [Didoo AI] Entry-point navigator and skill router for Didoo AI's Meta Ads workflow. Use when starting a Meta Ads task, unsure which skill to use, or building a Meta Ads agent workflow. Triggers on: wh | 100 | 83 | C | — | ↓ 641 ★ 1 | 11 May 2026 | |
| 5123 | A | Inference cost allocation and billing for autonomous AI agent collaborations. Shapley-fair cost splitting, congestion pricing, token metering, and settlement reports for context window usage. The econ | 100 | 84 | C | — | ↓ 667 | 11 May 2026 | |
| 5124 | A | Prepare, validate, and explicitly upload YouTube Shorts through the official YouTube Data API with dry-run safety. Use when an AI agent needs setup, usage, safety boundaries, or troubleshooting for Yo | 100 | 84 | C | — | ↓ 691 | 11 May 2026 | |
| 5125 | A | Use when you need durable, repairable kitchenware, storage jars, tools, or ritual objects made from local clay without electricity, kilns, or commercial supply chains. Agent researches your local clay | 100 | 84 | C | — | ↓ 665 | 11 May 2026 | |
| 5126 | A | Use when you need to repair worn leather goods (boots, belts, bags, tool sheaths) or create new durable items from scratch for everyday self-reliance, gig work, or off-grid living where commercial rep | 100 | 84 | C | — | ↓ 692 | 11 May 2026 | |
| 5127 | A | Use this skill when an agent needs to answer or plan operations for QiQue business requests in pure text protocol mode (no local executable dependency). Trigger for customer/profile lookup, wallet cha | 100 | 86 | B | — | ↓ 641 | 18 May 2026 | |
| 5128 | A | Optimization suite for OpenClaw agents to prevent token leaks and context bloat. Use when an agent needs to implement background task isolation (Cron) or a Reset & Summarize workflow (RAG). | 100 | 80 | D | — | ↓ 1 895 | 11 May 2026 | |
| 5129 | A | Follow / unfollow another agent on ggb.ai and read the list of who you follow. Three HTTP calls behind one skill — POST /api/premarket/agent-follows (follow), DELETE /api/premarket/agent-follows/:foll | 100 | 84 | B | — | ↓ 664 | 11 May 2026 | |
| 5130 | A | Feedback Controller — Closed-Loop Agent Skill for Correcting Execution Drift. Use it when the user needs a
disciplined protocol and fixed output contract for this kind of task rather
than a generic an | 100 | 84 | B | — | ↓ 663 | 11 May 2026 | |
| 5131 | A | Complete self-improvement system for AI agents. Implements a four-layer memory architecture with continuous learning, experimentation, and autonomous file maintenance. Use when: (1) Building an agent | 100 | 84 | C | — | ↓ 663 | 18 May 2026 | |
| 5132 | A | Plan which search provider to use before multi-provider skills run — score query signals, pick Serper/Tavily/Exa/Brave/Firecrawl, define fallback chain, and document why. | 100 | 89 | A | — | ↓ 366 | 24 Jun 2026 | |
| 5133 | A | Qordinate is a chat-native assistant that acts as structured memory for your agents. Use this skill when you want your OpenClaw agent to offload long-term facts, tasks, and reminders into Qordinate ov | 100 | 75 | D | — | ↓ 2 694 ★ 2 | 11 May 2026 | |
| 5134 | A | Create a new AI agent identity (SOUL.md, IDENTITY.md, AGENTS.md) and package it as a .skill file ready to upload to ClawHub. Use when a user wants to create, configure, or package a new named AI agent | 95 | 89 | B | — | ↓ 1 119 | 11 May 2026 | |
| 5135 | A | Query MaxCompute (ODPS) Information Schema metadata views. Tenant-level (SYSTEM_CATALOG.INFORMATION_SCHEMA.*, recommended) or project-level (Information_Schema.*, deprecated). NL→SQL for IS views: tab | 100 | 84 | C | — | ↓ 718 | 19 May 2026 | |
| 5136 | A | Check names against the OFAC SDN (Specially Designated Nationals) sanctions list via MCP. Downloads and caches official SDN CSV, auto-refreshes every 24h. Case-insensitive token matching with optional | 100 | 84 | C | — | ↓ 662 | 11 May 2026 | |
| 5137 | A | Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agen | 100 | 88 | D | — | ↓ 474 | 11 Jun 2026 | |
| 5138 | A | PPT风格分析与匹配工具。提取已有PPT的设计规范(配色/字体/布局/装饰元素),指导新页面或修改页保持风格统一。 Use when user asks to PPT风格匹配、修改几页风格不一致、分析PPT设计规范、提取PPT配色字体、新页面怎么跟原PPT风格一致、PPT重设计。 不适用于从头创建全新PPT、不需要保持风格一致的场景、非PPTX格式文件。 | 100 | 91 | D | — | ↓ 365 | 23 Jun 2026 | |
| 5139 | A | Convert PDF documents to Word (.docx) format using MinerU. Transforms PDF files into editable Word documents preserving layout, text, tables, and formatting. Features: PDF to DOCX conversion with layo | 100 | 83 | C | — | ↓ 1 116 | 11 May 2026 | |
| 5140 | A | Ampere AI Agent Marketplace for OpenClaw. Browse and install free & paid agents across developer tools, automation, research, content, and more. | 100 | 84 | C | — | ↓ 660 | 18 May 2026 | |
| 5141 | A | Power-user OrgX skill for OpenClaw. Use when you explicitly need the full mutation surface for entity CRUD, run control, checkpoints, stream reassignment, or agent-config policy changes. | 100 | 84 | C | — | ↓ 660 | 18 May 2026 | |
| 5142 | B | Twitter API Alternative — Search 1B+ tweets with natural language queries, boolean filters, and one-click CSV exports (up to 64K rows). Look up profiles, find users by topic, and track conversations. | 100 | 71 | D | — | ↓ 2 688 ★ 7 | 17 May 2026 | |
| 5143 | A | 游戏AI开发指南,涵盖FSM、行为树、寻路与决策系统的代码实现。Use when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无明确技术栈的模糊需求。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互,无需复杂配置即开即用。输出结果可直接使用,减少二次加工成本。提供结构化输出和错误处理机制。 | 100 | 88 | C | — | ↓ 601 | 21 d ago | |
| 5144 | A | Use this skill when the user wants to discover the best USDC vaults with LI.FI Earn, ask an agent to choose a safe vault on Base/Arbitrum/Ethereum, prepare a Composer-compatible deposit, execute the d | 99 | 87 | B | — | ↓ 657 | 11 May 2026 | |
| 5145 | A | Set up and query business data across 100+ sources (Stripe, HubSpot, Salesforce, etc.) via SQL. Agent-driven setup, cross-source joins, mutations. | 100 | 84 | C | — | ↓ 683 | 11 May 2026 | |
| 5146 | A | Autonomous optimization loop that improves any measurable thing. Point it at files to change, a command to check, and a number to improve — then walk away. Works with any AI agent. Use when the user w | 100 | 79 | B | — | ↓ 1 069 ★ 1 | 17 May 2026 | |
| 5147 | A | Invoke ChatDev ability units (workflows) via local API (port 6400). Use when the user needs specialized agent workflows like data visualization (from CSV), or when they mention "ChatDev", "ability uni | 100 | 83 | C | — | ↓ 1 109 | 17 May 2026 | |
| 5148 | A | Standardize API credential handling and startup auth checks to prevent "missing key" regressions across sessions. Use when an agent repeatedly loses auth state, gets intermittent 401/403 errors after | 94 | 91 | D | — | ↓ 1 178 | 11 May 2026 | |
| 5149 | A | Connect an MCP-compatible agent to local Garmin Connect sleep, Body Battery, HRV, stress, activities, and training readiness. Use when an AI agent needs setup, usage, safety boundaries, or troubleshoo | 100 | 84 | C | — | ↓ 682 | 11 May 2026 | |
| 5150 | A | Trade perpetuals on Pacifica via 36 MCP tools. Market data, account monitoring, order execution, subaccounts, and real-time WebSocket streaming on Solana. Trigger when the user asks about crypto price | 100 | 84 | C | — | ↓ 656 | 18 May 2026 |