Skill rating
24 653 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 |
|---|---|---|---|---|---|---|---|---|---|
| 1201 | A | Extract structured data from websites using Zyte API (formerly Crawlera) with smart proxy rotation and browser rendering. Use this skill when users want to scrape dynamic JavaScript-rendered pages, ex | 100 | 79 | C | — | ↓ 2 444 ★ 32 | 17 Jun 2026 | |
| 1202 | A | Read the user's coding preferences from /memory/coding-prefs.md before making non-trivial style decisions, and append new preferences when the user gives durable feedback. | 100 | 80 | C | — | ★ 29 406 | 9 h ago | |
| 1203 | A | Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:ar-resume or asks to pick up a previously started autoresearch experime | 100 | 80 | C | — | ★ 25 956 | 16 d ago | |
| 1204 | A | Use when the user asks to write code efficiently, avoid over-engineering, reduce dependencies, or prevent unnecessary abstractions. Enforces a strict efficiency ladder: YAGNI, reuse, stdlib, native pl | 100 | 80 | B | — | ★ 25 956 | 16 d ago | |
| 1205 | A | Use when the user says 'no hallucinations', 'verify APIs', 'reality check', or 'don't invent functions'. Prevents the agent from calling methods, imports, or variables that do not provably exist in th | 100 | 80 | C | — | ★ 25 956 | 16 d ago | |
| 1206 | A | Your Claude Code wingman - orchestrate multiple Claude Code sessions across projects, monitor them all from WhatsApp | 100 | 80 | B | — | ↓ 4 834 ★ 10 | 18 May 2026 | |
| 1207 | A | Scan your codebase for distinctive patterns — get structured scoring and evidence for patent consultation. NOT legal advice. | 100 | 80 | B | — | ↓ 3 623 ★ 13 | 11 May 2026 | |
| 1208 | A | Control Claude Code via MCP protocol. Execute commands, read/write files, search code, and use all Claude Code tools programmatically with agent team support. | 100 | 79 | D | — | ↓ 7 592 ★ 6 | 18 May 2026 | |
| 1209 | A | Turn your code scan findings into search queries — research existing implementations before consulting an attorney. NOT legal advice. | 100 | 80 | C | — | ↓ 3 168 ★ 14 | 11 May 2026 | |
| 1210 | A | Writes, debugs, and reviews Python code — runtime traps, packaging, typing, async, tests, performance. Use when Python raises or misbehaves: ModuleNotFoundError, circular imports, AttributeError on No | 99 | 81 | B | — | ↓ 6 498 ★ 6 | 25 Jul 2026 | |
| 1211 | A | Send messages, manage chats, handle files, and automate Telegram bot workflows via the Telegram Bot API. Use this skill when users want to send messages, manage groups, handle media, or automate notif | 100 | 79 | C | — | ↓ 2 324 ★ 26 | 9 Jun 2026 | |
| 1212 | A | Builds, debugs, and reviews Vue 3 apps: reactivity, components, composables, Pinia state, Vue Router, forms, and performance. Use when the UI does not update after a state change, a reactive object lo | 100 | 81 | B | — | ↓ 4 395 ★ 8 | 26 Jul 2026 | |
| 1213 | A | Manage personal finances, track spending by category, set budgets, and receive reminders for EMIs and one-time annual expenses. Use for logging expenses, checking budget status, or setting up financia | 100 | 79 | D | — | ↓ 4 964 ★ 6 | 11 May 2026 | |
| 1214 | A | Use when completing tasks, implementing major features, or before merging to verify work meets requirements | 100 | 81 | C | — | ↓ 6 294 ★ 5 | 11 May 2026 | |
| 1215 | A | Builds, debugs, and hardens FastAPI services: async endpoints, Pydantic models, dependency injection, auth, and deployment. Use when writing or reviewing a FastAPI app, router, or schema; when the API | 100 | 81 | B | — | ↓ 4 185 ★ 7 | 26 Jul 2026 | |
| 1216 | A | Humanize AI content by detecting and auto-fixing AI generated content. Humanize AI text using Python scripts. Scans for AI vocabulary, puffery, chatbot artifacts, and auto-replaces filler phrases. Use | 95 | 87 | C | — | ↓ 3 360 ★ 8 | 11 May 2026 | |
| 1217 | A | HaS (Hide and Seek) on-device text and image anonymization. Text: 8 languages (zh/en/fr/de/es/pt/ja/ko), open-set entity types. Image: 21 privacy categories (face, fingerprint, ID card, passport, lice | 100 | 81 | B | — | ↓ 2 181 ★ 14 | 11 May 2026 | |
| 1218 | A | Comprehensive deep reasoning framework that guides systematic, thorough thinking for complex tasks. Automatically applies for multi-step problems, ambiguous requirements, architectural decisions, debu | 100 | 80 | C | — | ↓ 5 576 ★ 4 | 11 May 2026 | |
| 1219 | A | Production development workflow with TODO tracking, Graphite PRs, GitHub issues, Vercel deploy checks, and SMS notifications. Use when starting a new task, fixing bugs, implementing features, or any d | 100 | 79 | C | — | ↓ 4 225 ★ 5 | 11 May 2026 | |
| 1220 | A | 针对 Kimi Code CLI 的新增或变更功能,规划并执行可重复的端到端冒烟测试。从 git diff 推断功能边界,读取相关文档和代码,设计测试 prompt,以 --print 非交互模式运行本地 CLI,检查进程退出码和 session 产物,总结预期与实际行为之间的差异。发现问题时自动启动多路并行探查以定位根因。 | 100 | 79 | D | — | ★ 11 357 | 14 d ago | |
| 1221 | A | Twitter Command Center (Search + Post)IntegrationSoftware developmentWriting and documentsClawHubAgent Skills Searches and reads X (Twitter): profiles, timelines, mentions, followers, tweet search, trends, lists, communities, and Spaces. Publishes posts after the user completes OAuth in the browser. Use when | 100 | 79 | C | — | ↓ 4 125 ★ 5 | 11 May 2026 | |
| 1222 | A | Writes and debugs Tailwind CSS: utility classes, theme config, dark mode, variants, plugins, and build setup. Not for CSS mechanics themselves — stacking contexts, flex sizing, and cascade behavior be | 100 | 81 | B | — | ↓ 4 129 ★ 5 | 26 Jul 2026 | |
| 1223 | A | Ultra-compressed communication mode. Slash token usage ~75% by speaking like smart caveman while keeping technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "les | 100 | 79 | D | — | ↓ 5 176 ★ 4 | 11 May 2026 | |
| 1224 | A | Extract clean, readable markdown content from any URL using Jina Reader API. Use when you need to fetch and parse web pages without dealing with HTML, JavaScript rendering, or paywalls. Ideal for rese | 100 | 90 | C | — | ↓ 2 072 | 17 May 2026 | |
| 1225 | A | Profile and optimize application performance. Use when diagnosing slow code, measuring CPU/memory usage, generating flame graphs, benchmarking functions, load testing APIs, finding memory leaks, or op | 100 | 82 | D | — | ↓ 3 970 ★ 2 | 17 May 2026 | |
| 1226 | A | Extract content from specific URLs using Tavily's extraction API. Returns clean markdown/text from web pages. Use when you have specific URLs and need their content without writing code. | 100 | 90 | B | — | ↓ 1 126 ★ 1 | 11 May 2026 | |
| 1227 | A | This skill should be used when the user wants to compile and organize scientific research project outcomes. It guides WorkBuddy through a structured five-phase workflow: (1) intake and topic analysis, | 100 | 93 | C | — | ↓ 666 ★ 1 | 11 May 2026 | |
| 1228 | A | Generate realistic test data for software testing. Create structured data sets with Chinese locale support (names, ID cards, phone numbers, addresses, bank cards). Generate SQL inserts, JSON fixtures, | 100 | 94 | C | — | ↓ 718 | 11 May 2026 | |
| 1229 | A | OceanBus-powered evidence-based health checkup recommendation service. Use when users need personalized checkup plans based on age, gender, symptoms, and family history, backed by National Health Comm | 95 | 90 | D | — | ↓ 1 523 ★ 8 | 18 May 2026 | |
| 1230 | A | Turns ideas into live, full-stack web applications with editable code, built-in database, user authentication, and hosting. Anima is the design agent in the AI swarm, giving agents design awareness an | 100 | 82 | C | — | ↓ 2 181 ★ 5 | 11 May 2026 | |
| 1231 | A | Route requests for ACP or external coding agents such as Codex, Claude Code, Gemini CLI, and OpenCode into non-blocking OpenClaw background ACP runs instead of executing synchronously in the current c | 100 | 89 | B | — | ↓ 1 115 ★ 1 | 11 May 2026 | |
| 1232 | A | Modify code based on GitHub PR review comments and create a local commit using gh + git. Use when the user asks to "follow PR comments", "fix review comments", "update this PR", or provides a PR URL a | 100 | 92 | B | — | ↓ 1 167 | 17 May 2026 | |
| 1233 | A | Designs and refactors software codebases to be AI-friendly by aligning the filesystem with domain/feature boundaries, creating deep (greybox) modules with small public interfaces, enforcing import bou | 100 | 93 | B | — | ↓ 1 181 | 17 May 2026 | |
| 1234 | A | Use when building or modifying websites with AI Staff via Alibaba Cloud OpenAPI. Supports conversation creation, async chat with requirement collection, PRD generation, code generation, and incrementa | 100 | 94 | A | — | ↓ 766 | 5 Jun 2026 | |
| 1235 | A | markitdown-skillGeneratorPowerPointYouTubeWriting and documentsSoftware developmentClawHubAgent Skills OpenClaw agent skill for converting documents to Markdown. Documentation and utilities for Microsoft's MarkItDown library. Supports PDF, Word, PowerPoint, Excel, images (OCR), audio (transcription), H | 100 | 87 | C | — | ↓ 3 584 | 11 May 2026 | |
| 1236 | A | Manage Porkbun DNS records and domains via API v3. Use when Codex needs to create, read, update, or delete DNS records on Porkbun; list domains; configure API access; work with common record types (A, | 100 | 91 | C | — | ↓ 2 040 | 11 May 2026 | |
| 1237 | A | Python web scraping toolkit for data extraction, pagination handling, anti-blocking techniques, Selenium for JavaScript-heavy sites, and structured output (JSON/CSV). Use when Codex needs to extract d | 100 | 94 | C | — | ↓ 731 | 18 May 2026 | |
| 1238 | A | Use when the user wants to pressure-test a product, internal-tool, or OSS concept against Amazon's Working Backwards PRFAQ gauntlet before committing to a spec. Triggers on: "work backwards", "write a | 100 | 96 | B | — | ↓ 703 | 11 May 2026 | |
| 1239 | A | Multi-engine web search aggregation via local Python script. Use when: (1) searching the web for information, articles, documentation, (2) searching code repos on GitHub/GitLab, (3) finding academic p | 100 | 94 | C | — | ↓ 704 | 11 May 2026 | |
| 1240 | A | Token-efficient Claude Code workflow. Other skills burn tokens polling tmux every 30s — this one uses completion callbacks and only checks when notified. Observable tmux sessions, smart dispatch rule | 100 | 91 | C | — | ↓ 2 032 | 18 May 2026 | |
| 1241 | A | Visual RPA desktop automation skill. Use when user asks to operate desktop apps, click icons, open applications, type text in input fields, click buttons, scroll pages, send messages via WeChat or oth | 100 | 90 | C | — | ↓ 819 ★ 2 | 18 May 2026 | |
| 1242 | A | Parse Claude Code session JSONL to extract implicit user feedback signals.
Detects skill invocations (tool_use blocks with name="Skill" or /slash-commands),
classifies user responses as correction/acc | 100 | 94 | B | — | ↓ 699 | 11 May 2026 | |
| 1243 | A | Bridges OpenClaw (QQ, Telegram, WeChat, and other messaging channels) to a persistent Claude Code CLI session running in a background tmux process. Enables starting, stopping, restarting, and monitori | 100 | 93 | C | — | ↓ 1 155 | 18 May 2026 | |
| 1244 | A | Build the Clawdbot macOS menu bar app from source. Use when you need to install the Clawdbot.app companion (for menu bar status, permissions, and Mac hardware access like camera/screen recording). Han | 100 | 84 | C | — | ↓ 3 233 ★ 1 | 18 May 2026 | |
| 1245 | A | GitHub Research Assistant. Use this skill when the user wants to analyze a GitHub repository. Analysis dimensions -- 1) Basic information; 2) Purpose, what it can be used for; 3) Tech stack, including | 100 | 91 | B | — | ↓ 1 082 ★ 1 | 11 May 2026 | |
| 1246 | A | Expert skill for building web-based game engines and games using HTML5, Canvas, WebGL, and JavaScript. Use when asked to create games, build game engines, implement game physics, handle collision dete | 100 | 84 | C | — | ↓ 2 313 ★ 2 | 11 May 2026 | |
| 1247 | A | Query and manage Langfuse traces, prompts, datasets, sessions, observations, scores, and metrics via Langfuse SDKs and the public API. Use when setting up or auditing Langfuse tracing in cloud or self | 100 | 91 | B | — | ↓ 1 201 ★ 1 | 11 May 2026 | |
| 1248 | A | Plan and implement OIDC and OAuth 2.0 integration for React or TypeScript frontends and Java or Spring Boot backends. Use whenever the user mentions OIDC, OpenID Connect, OAuth login, SSO, PKCE, autho | 100 | 96 | B | — | ↓ 694 | 11 May 2026 | |
| 1249 | A | Write git commit messages in Classical Chinese (文言文). Use when the user asks for a commit message 用文言文, 文言, 古文, classical chinese, or mentions 雅驯/骈俪 style for commits. Do NOT use for regular Conventio | 100 | 88 | D | — | ↓ 1 304 ★ 2 | 19 May 2026 | |
| 1250 | A | Create and manage InsForge projects using the CLI. Handles authentication, project setup, database management, edge functions, storage, deployments, and secrets. For writing application code with the | 100 | 89 | D | — | ↓ 1 068 ★ 1 | 18 May 2026 |