Skill rating
138 041 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 |
|---|---|---|---|---|---|---|---|---|---|
| 10001 | A | Analyze resource usage patterns and predict future scaling needs using trend analysis and forecasting methods for capacity planning and auto-scaling decisions. | 100 | 87 | C | — | ↓ 744 | 11 May 2026 | |
| 10002 | B | Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use PROACTIVELY for quantitative finance, trad | 100 | 83 | B | — | ↓ 2 095 | 11 May 2026 | |
| 10003 | B | Fornece um dashboard visual para informações do dia a dia como localização, clima, economia, previsão do tempo. Use sempre que o usuário pedir "briefing diário" ou o comando "briefing". | 100 | 84 | C | — | ↓ 1 251 | 17 May 2026 | |
| 10004 | B | Intent-alignment orchestration for OpenClaw agent teams across diverse host environments. Use when work must stay anchored to user goals while allowing flexible execution: (1) coding with repos/PRs/is | 100 | 84 | C | — | ↓ 1 229 | 17 May 2026 | |
| 10005 | B | Query employee data, time clock entries, schedules, and requests. Requires authentication — employees see own data, managers see team. | 100 | 84 | C | — | ↓ 1 230 | 18 May 2026 | |
| 10006 | A | Control Meta/Facebook/Instagram ads through Meta's official `meta ads ...` CLI. Use for read-only audits, reporting, safe planning, and approved one-step mutations of campaigns, ad sets, ads, creative | 100 | 88 | C | evals | ↓ 800 | 11 May 2026 | |
| 10007 | A | Design product warranty and guarantee programs that increase buyer confidence and conversion rates while managing liability exposure, including policy language, claim workflows, fulfillment costs, and | 100 | 88 | C | — | ↓ 742 | 11 May 2026 | |
| 10008 | A | Extract a structured Hong Kong IPO snapshot with company fields, offer mechanics, timing, source provenance, and field-level quality signals. Use when the user asks about one IPO symbol, wants normali | 100 | 87 | C | — | ↓ 741 | 11 May 2026 | |
| 10009 | A | 用户询问回收、估价、报价、回收价、值多少钱、能卖多少、转转回收时触发,支持全品类商品回收估价,结合图片、文字、型号、规格、成色等信息给出参考回收价 | 100 | 87 | B | — | ↓ 741 | 11 May 2026 | |
| 10010 | B | Amazon product research and seller analytics for FBA and FBM businesses. Find winning products with 14 selection strategies, track competitors, monitor BSR trends, analyze reviews, estimate monthly sa | 100 | 83 | D | — | ↓ 1 198 ★ 1 | 11 May 2026 | |
| 10011 | A | Use this skill when a patent agent, patent attorney, or in-house IP counsel needs to turn an invention disclosure into a structured patent claim set for US, EPO, or PCT prosecution. Produces a DRAFT i | 100 | 87 | B | — | ↓ 832 | 28 May 2026 | |
| 10012 | A | A brilliant, hyper-intelligent lobster persona. Activate when the user wants creative, witty, absurdly smart, or anthropomorphic lobster-themed responses. Triggered by: '龙虾', 'lobster', '天才龙虾', 'geniu | 100 | 87 | C | — | ↓ 797 | 11 May 2026 | |
| 10013 | A | Run an ISO 27001 internal audit. Walk through controls by domain, identify gaps, collect evidence, and generate findings with corrective action recommendations. Uses NIST SP 800-53 (public domain) as | 95 | 96 | C | — | ↓ 768 | 11 May 2026 | |
| 10014 | A | When the user wants to plan, design, or optimize pricing strategy and structure. Also use when the user mentions "pricing strategy," "pricing model," "pricing tiers," "freemium," "value-based pricing, | 100 | 88 | C | — | ↓ 739 | 11 May 2026 | |
| 10015 | A | Cross-platform prediction market data via AIsa API. Query Polymarket and Kalshi markets, prices, orderbooks, candlesticks, positions, and trades. Use when user asks about: prediction market odds, elec | 100 | 88 | D | — | ↓ 768 | 11 May 2026 | |
| 10016 | A | Explain how email and Google Calendar work for OpenClaw agents, including the distinction between agent email and owner email, how gog and the Google Workspace skill are used, where related credential | 100 | 87 | C | — | ↓ 768 | 11 May 2026 | |
| 10017 | A | Browse, search, and download ebooks from OPDS catalogs using the opdscli CLI. Use when adding/managing catalogs, searching for books, downloading ebooks, or browsing latest additions. | 100 | 87 | C | — | ↓ 798 | 17 May 2026 | |
| 10018 | A | Generate AI music with Producer via AceDataCloud API. Use when creating songs, generating lyrics, extending tracks, creating covers, swapping vocals/instrumentals, replacing song sections, or uploadin | 100 | 88 | D | — | ↓ 767 | 26 d ago | |
| 10019 | B | Automatically generate a structured, high-quality Pull Request (PR) description based on the provided git diff or code changes. Trigger when the user asks to write a PR description, summarize changes, | 100 | 84 | C | evals | ↓ 680 ★ 1 | 11 May 2026 | |
| 10020 | A | Plan and optimize travel within China using flyai / Fliggy search capabilities plus public metro-network data when needed. Use when the user wants a domestic China trip plan, weekend getaway, city iti | 96 | 94 | C | — | ↓ 738 | 11 May 2026 | |
| 10021 | A | Write detailed, academically rigorous Chinese discussion chapters or discussion sections for theses, dissertations, and undergraduate papers from a user's findings, research questions, hypotheses, the | 100 | 87 | B | — | ↓ 795 | 11 May 2026 | |
| 10022 | A | Aggregates real-time crypto market data and Twitter signals into actionable alerts for traders and researchers. Use when you need to monitor price movements, volume spikes, and social sentiment simult | 100 | 87 | C | — | ↓ 765 | 18 May 2026 | |
| 10023 | A | When the user faces brand impersonation, fake websites, phishing sites, or trademark infringement. Also use when the user mentions "fake site," "impersonation," "phishing site," "trademark infringemen | 100 | 88 | C | — | ↓ 766 | 11 May 2026 | |
| 10024 | A | Production-grade Playwright testing toolkit. Use when the user mentions Playwright tests, end-to-end testing, browser automation, fixing flaky tests, test migration, CI/CD testing, or test suites. Gen | 100 | 88 | C | — | ↓ 766 | 11 May 2026 | |
| 10025 | A | Generate optimized paper titles for different academic venues and styles. Activated when Chopin submits a paper draft and needs title suggestions, or when struggling to name a paper. Input: full paper | 100 | 87 | B | — | ↓ 766 | 11 May 2026 | |
| 10026 | A | Universal smart routing skill that chooses the best installed skill or skill chain across mixed environments, and automatically applies OpenClaw-aware routing when an OpenClaw workspace or skill inven | 100 | 88 | B | — | ↓ 766 | 11 May 2026 | |
| 10027 | A | internal-app-bootstrapGeneratorPostgreSQLSoftware developmentWriting and documentsClawHubAgent Skills Use when creating a new internal application from scratch, standardizing a 0-to-1 app build workflow, or helping teammates bootstrap a Next.js/FastAPI/Keycloak/PostgreSQL style product with a docs-fir | 100 | 87 | C | — | ↓ 766 | 11 May 2026 | |
| 10028 | B | Fetch a known URL and return the page as markdown, plain text, raw HTML, or a downloaded image file using the local fetch.js helper. Use this whenever the user gives or implies a specific URL and want | 100 | 84 | C | — | ↓ 1 290 | 11 May 2026 | |
| 10029 | B | Orchestrate multiple AI coding agents (Claude Code, Codex, Aider) from a single config — launch teams, run workflows, track capacity, and manage handoffs. | 100 | 84 | B | — | ↓ 1 292 | 11 May 2026 | |
| 10030 | B | Run long-lived AI coding agents (Codex CLI, Claude Code, Ralph loops) in persistent tmux sessions with completion hooks and automatic monitoring. Use when launching coding agents for multi-step tasks, | 100 | 84 | C | — | ↓ 1 266 | 18 May 2026 | |
| 10031 | B | Use this skill whenever the user wants to read, parse, extract content from, modify, or otherwise process an .epub file. Triggers include any mention of ".epub", "ebook", "epub file", or requests to e | 100 | 85 | C | — | ↓ 1 244 | 11 May 2026 | |
| 10032 | B | Set up and operate dual Discord bots on one machine with isolated memory, channel allowlists, mention-gated reviewer bot behavior, optional one-way reviewer-to-primary context bridge, and safe backup/ | 99 | 87 | C | — | ↓ 1 222 | 17 May 2026 | |
| 10033 | B | Use when 需要理解紫鸟ERP API 的定位、能力、权限体系或调用流程, 用于 ERP 系统对接规划、集成设计或接口评估。 不要用于直接查阅具体接口参数——查阅时读取 reference/ 下对应文件。 | 100 | 85 | C | — | ↓ 1 244 | 11 May 2026 | |
| 10034 | A | API 安全扫描工具。对 REST API 端点进行自动化安全审计,检测 OWASP Top 10 漏洞、
认证/授权问题、敏感数据泄露、速率限制缺失等常见安全隐患。输出结构化安全报告。
适合开发者在部署前快速自检,也适合安全团队做轻量级审计。 | 100 | 87 | C | — | ↓ 828 | 24 May 2026 | |
| 10035 | A | You are an MLOps engineer with expertise in machine learning pipeline automation, model deployment, experiment tracking, and production ML. Use when: ml pipeline orchestration and automation, model tr | 100 | 87 | C | — | ↓ 737 | 11 May 2026 | |
| 10036 | A | You are a Tier 3 autonomous agent capable of goal-directed planning, adaptive learning, and self-correction with minimal human supervision. Use when: goal-directed planning, adaptive learning, self-co | 100 | 88 | C | — | ↓ 794 | 11 May 2026 | |
| 10037 | A | Audit a game, feature, level sequence, combat loop, progression curve, onboarding path, event structure, or return-player journey through the lens of Flow theory. Use when evaluating whether challenge | 100 | 87 | C | — | ↓ 764 | 11 May 2026 | |
| 10038 | A | Rewrite rough goals, scattered notes, or vague requests into clear, actionable prompts with explicit objective, constraints, output format, and missing assumptions. Use when Codex needs to turn a mess | 100 | 87 | B | — | ↓ 736 | 11 May 2026 | |
| 10039 | A | Use the globally installed edge-tts command to generate Chinese or multilingual text-to-speech audio on this machine. Use when the user wants text converted to speech, wants a natural online voice qui | 100 | 87 | C | — | ↓ 764 | 11 May 2026 | |
| 10040 | A | Run ExpertPack CLI tools for validating, fixing, graphing, and deploying packs. Use when: running ep-validate, ep-doctor, ep-graph-export, ep-strip-frontmatter, or ep-fix-broken-wikilinks on a local p | 100 | 88 | D | — | ↓ 764 | 11 May 2026 | |
| 10041 | A | Get things done in the real world — pickups, deliveries, errands, and gifts handled by a human tasker. San Francisco only. | 100 | 88 | B | — | ↓ 764 | 11 May 2026 | |
| 10042 | A | Apply timeless marketing and business principles to any problem. Use when someone needs strategic thinking, wants to evaluate a marketing decision, needs a framework for a tough choice, or mentions "f | 100 | 88 | C | — | ↓ 764 | 11 May 2026 | |
| 10043 | A | Systematic protocol for working through a project build queue (NEXT_TASKS.md). Use when a project has an ordered task list and you need to pick up, execute, verify, and hand off work across sessions. | 100 | 87 | D | — | ↓ 764 | 11 May 2026 | |
| 10044 | A | How do I breed two agents into a better one? Can two OpenClaw agents have offspring? Use this when you have two agents that each work and want a third that inherits from both: it crosses their workspa | 100 | 94 | C | — | ↓ 167 | 21 Sept 2026 | |
| 10045 | B | Translate text to any language with formality control and cultural notes. Target language defaults to English. | 100 | 83 | C | — | ↓ 1 144 ★ 1 | 11 May 2026 | |
| 10046 | B | Trade Kalshi prediction markets through conversation, powered by Fuku sports model predictions. Use when a user asks about Kalshi markets, wants sports predictions with edge analysis, wants to place o | 94 | 91 | C | — | ↓ 1 143 ★ 1 | 18 May 2026 | |
| 10047 | B | Plan multi-waypoint journeys with route optimization, feasibility analysis, and time budget constraints. Use when you need to plan trips with multiple stops or check if an itinerary is achievable. | 95 | 90 | C | — | ↓ 2 073 | 20 May 2026 | |
| 10048 | B | Source and send relevant reaction GIFs in WhatsApp chats using safe filters and deterministic ranking. Use when the user asks for a GIF/meme/reaction, or when a short visual reaction is better than pl | 100 | 85 | C | — | ↓ 1 198 | 11 May 2026 | |
| 10049 | A | Collect comments from a known Instagram post URL. Do not use for profile data or Reel details. | 100 | 88 | B | — | ↓ 954 | 1 Sept 2026 | |
| 10050 | A | 在测试工作流开始前检查用户输入是否包含有效的需求描述和足够的上下文信息。当用户的测试请求过于模糊(只说"帮我测试"却没说测什么)、缺少必要的需求文档或上下文时,应当使用此技能来验证输入完整性。如果输入验证失败,必须返回缺失信息清单要求用户补充。适用于启动任何测试设计流程的第一步。 触发场景:需求不清楚、信息不够、这个需求能测吗、用户输入模糊时自动激活(第一步)。 Use when the user | 100 | 89 | C | — | ↓ 1 057 | 39 d ago |