Skill rating
38 706 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 |
|---|---|---|---|---|---|---|---|---|---|
| 10251 | A | Audit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "au | 100 | 92 | B | — | ★ 6 | 10 Jul 2026 | |
| 10252 | A | When the user wants to optimize their Google Play Store listing — title, short description, full description, keywords, ratings, or Play Store-specific features. Use when the user mentions "Google Pla | 100 | 92 | C | — | ★ 6 | 10 Jul 2026 | |
| 10253 | A | Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff re | 100 | 92 | C | — | ★ 6 | 10 Jul 2026 | |
| 10254 | A | Generate a personalized SOUL.md through a warm, adaptive onboarding conversation. Trigger when the user wants to create, set up, or initialize their AI partner's identity — e.g., "create my SOUL.md", | 100 | 93 | C | — | ★ 6 | 10 Jul 2026 | |
| 10255 | A | Test C# MCP servers at multiple levels: unit tests for individual tools and integration tests using the MCP client SDK. USE FOR: unit testing MCP tool methods, integration testing with in-memory MCP c | 100 | 93 | C | — | ★ 6 | 10 Jul 2026 | |
| 10256 | A | Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Use when asked to "create a skill", "write a skill", "synthesize sources into a skill", "improve a sk | 100 | 93 | C | — | ★ 6 | 10 Jul 2026 | |
| 10257 | A | Implements and debugs browser WebMCP integrations in JavaScript or TypeScript web apps. Use when exposing imperative tools through document.modelContext (with a navigator.modelContext fallback), annot | 100 | 92 | C | — | ★ 6 | 10 Jul 2026 | |
| 10258 | A | Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridg | 100 | 93 | B | — | ★ 6 | 10 Jul 2026 | |
| 10259 | A | Complete reference for writing, running, and iterating on evals (automated conversation tests) for ADK agents. Covers eval file format, all assertion types, CLI usage, and per-primitive testing patter | 100 | 92 | C | — | ★ 6 | 10 Jul 2026 | |
| 10260 | A | Implement Clerk authentication for native Swift and iOS apps using ClerkKit and ClerkKitUI source-guided patterns. Use for prebuilt AuthView or custom native flows. Do not use for Expo or React Native | 100 | 93 | C | — | ★ 6 | 10 Jul 2026 | |
| 10261 | A | This skill should be used when the user asks to "chat with AI", "ask Olly", "ask the agent", "send message to AI", "continue a chat", "follow up on chat", "get artifact", "download artifact", "list ar | 100 | 92 | C | — | ★ 6 | 10 Jul 2026 | |
| 10262 | A | Generate, remix, extend, edit, and analyze AI music (Mureka). Triggers on:
"音乐", "music", "生成音乐", "generate music", "翻唱", "cover", "混音", "remix",
"续写", "extend", "纯音乐", "instrumental", "配乐", "soundtra | 100 | 93 | C | — | ★ 6 | 10 Jul 2026 | |
| 10263 | A | Use this skill whenever the user wants to generate sound effects, ambient audio, or short audio clips from a text description. Triggers include: any mention of 'sound effect', 'sfx', 'generate sound', | 100 | 93 | C | — | ★ 6 | 10 Jul 2026 | |
| 10264 | A | Helps implement coss UI components correctly. Use when building UIs with coss primitives (buttons, dialogs, selects, forms, menus, tabs, inputs, toasts, etc.), migrating from shadcn/Radix to coss/Base | 100 | 92 | C | — | ★ 6 | 10 Jul 2026 | |
| 10265 | C | Unified gateway skill for async execute/poll, portal user closure, and telemetry feedback workflows. | 100 | 72 | C | — | ↓ 1 226 ★ 1 | 18 May 2026 | |
| 10266 | B | Give AI agents Customer support that never re-asks. using BlueColumn persistent memory. Use when an agent handles support tickets and needs full context; when the user wants to store, recall, or searc | 100 | 84 | C | — | ↓ 292 | 31 Jul 2026 | |
| 10267 | B | Use APIDot for Flux Schnell API workflows, including FLUX.1 Schnell, Black Forest Labs image generation, fast low-cost text-to-image drafts, prompt exploration, batch creative iteration, task_id, poll | 100 | 86 | B | — | ↓ 292 | 6 Jul 2026 | |
| 10268 | C | Find 24-hour businesses, well-lit public areas, transit stations, police stations, and hospitals near any location for late night safety awareness. | 95 | 78 | C | — | ↓ 1 500 ★ 2 | 13 May 2026 | |
| 10269 | B | Intelligently splits long academic or technical documents into chapters, generates structured JSON summaries for each, and creates a file system with a global index. This enables efficient AI retrieva | 100 | 75 | C | — | ↓ 1 313 | 17 May 2026 | |
| 10270 | B | Expose local APIs to the Pilot Protocol network.
Use this skill when: 1. You need to expose local APIs to remote Pilot agents 2. You want to provide API access without public internet exposure 3. You' | 95 | 86 | D | — | ↓ 789 | 18 May 2026 | |
| 10271 | B | Get mobility route options worldwide — fare estimates, ETA, and a one-tap deeplink to open the ride. Queries the KLO Mobility A2A agent. | 100 | 83 | C | — | ↓ 378 | 22 Jun 2026 | |
| 10272 | B | 用户发现自动模式拍的照片都差不多、想理解程序曝光的局限、或从自动模式
转向手动控制时调用。不适用于具体曝光参数选择(应调用 exposure-dual-control)
或测光问题(应调用 light-meter-compensation)。
Invoke when the user notices all their auto-mode photos look the same, wants
t | 100 | 86 | C | — | ↓ 291 | 3 Aug 2026 | |
| 10273 | B | Use when choosing best-value Nous Portal models. | 100 | 86 | C | — | ↓ 291 | 2 Aug 2026 | |
| 10274 | B | Give AI agents Track goals and coaching progress. using BlueColumn persistent memory. Use when an agent coaches users and tracks progress; when the user wants to store, recall, or search coaching memo | 100 | 84 | C | — | ↓ 291 | 31 Jul 2026 | |
| 10275 | B | Turn complete lyrics, a rough lyric draft, loose lines, or an existing hook into a structured, listenable Suno song. This Suno lyrics-to-song workflow works as an AI song generator from lyrics and AI | 100 | 85 | B | — | ↓ 290 | 25 d ago | |
| 10276 | B | 用户想提升照片的艺术深度、问"怎么让照片更有意义"、或追求从"好看"到
"杰作"的突破时调用。不适用于基础构图评价(应调用 photo-three-principles)
或技术操作问题。
Invoke when the user wants to deepen the artistic meaning of their photos,
asks "how to make photos more | 100 | 86 | C | — | ↓ 290 | 3 Aug 2026 | |
| 10277 | B | Give AI agents Remember GitHub issues and PRs. using BlueColumn persistent memory. Use when an agent tracks repos, issues, and pull requests; when the user wants to store, recall, or search github mem | 100 | 84 | C | — | ↓ 290 | 31 Jul 2026 | |
| 10278 | B | Give AI agents Remember family details. using BlueColumn persistent memory. Use when an agent supports family coordination; when the user wants to store, recall, or search family memory context. Requi | 100 | 84 | C | — | ↓ 290 | 31 Jul 2026 | |
| 10279 | B | Use when migrating iOS projects from CocoaPods to Swift Package Manager, or when planning a migration strategy for enterprise iOS dependencies. Covers dependency mapping, build settings, xcconfig tran | 100 | 84 | D | — | ↓ 290 | 7 Jul 2026 | |
| 10280 | B | Use when someone needs word-level timestamps from audio — lyric alignment, cut-safe line boundaries, or caption source timing before burn-in with video-editing. | 100 | 85 | C | — | ↓ 290 | 5 d ago | |
| 10281 | C | Locate parking garages, lots, and street parking near your destination using Camino AI's location intelligence with AI-powered ranking. | 95 | 78 | C | — | ↓ 1 489 ★ 2 | 13 May 2026 | |
| 10282 | C | Fine-tune LLMs with data preparation, provider selection, cost estimation, evaluation, and compliance checks. | 100 | 71 | C | — | ↓ 1 468 ★ 2 | 11 May 2026 | |
| 10283 | B | Analyze images and provide detailed visual insights, object detection, composition analysis, and actionable recommendations. Use when the user shares or references an image file or URL and wants detai | 100 | 82 | B | — | ↓ 376 | 19 Jun 2026 | |
| 10284 | B | 多平台电商加购物车/收藏自动化工具。通过 Brave Browser CDP 搜索商品并加入购物车(淘宝/京东)、收藏(拼多多)、或标记"想要"(闲鱼)。依赖 brave-browser-agent skill。不涉及支付,只做到加购/收藏为止。Not for: 价格比较、下单支付、商品推荐、订单管理。 | 100 | 83 | C | — | ↓ 376 | 18 Jun 2026 | |
| 10285 | B | Designing LLM-optimized folder structures: audits and restructures directories for context efficiency, progressive disclosure, and prompt cache performance. Not for general repo structure (Grove). | 100 | 83 | C | — | ★ 80 | 4 d ago | |
| 10286 | B | Navigating the skill ecosystem and guiding onboarding. Lists agents, recommends best fit for tasks. Don't use for task execution (Nexus), agent design (Architect). | 95 | 91 | B | — | ★ 80 | 4 d ago | |
| 10287 | B | Local-first email for agents: IMAP sync to maildir + SQLite (FTS5); CLI search, read, thread, who, attachments. Requires Node 20+, npm install (`npm install -g @cirne/zmail` or `npx @cirne/zmail`), na | 100 | 77 | C | — | ↓ 760 | 11 May 2026 | |
| 10288 | B | 使用 Nano Banana 2 从产品资料建立商业产品图镜头矩阵,生成白底目录图、英雄图、材质微距、尺度场景和包装合照,同时锁定产品物理特征。Use this skill for 产品图生成、商品图、商业摄影、产品摄影、产品渲染、白底图、场景图、材质细节、包装图、电商图片、官网 Hero 和新品视觉;通过 AI Hive 生成。 | 100 | 84 | D | — | ↓ 190 | 36 d ago | |
| 10289 | B | 用户想了解一天中什么时间最适合拍照、问"什么时候拍照光线最好"、或规划户外
拍摄时间时调用。不适用于光线方向选择(应调用 natural-light-direction)或
室内布光(应调用 three-point-lighting)。
Invoke when the user wants to know the best time of day for photography,
asks "wh | 100 | 86 | C | — | ↓ 289 | 3 Aug 2026 | |
| 10290 | B | Give AI agents Remember Gmail threads. using BlueColumn persistent memory. Use when an agent manages email and needs thread history; when the user wants to store, recall, or search gmail memory contex | 100 | 84 | C | — | ↓ 289 | 31 Jul 2026 | |
| 10291 | B | Collect and aggregate agent metrics from connections, peers, and custom events.
Use this skill when: 1. You need to monitor agent health and performance 2. You need to aggregate metrics across a fleet | 95 | 86 | D | — | ↓ 782 | 11 May 2026 | |
| 10292 | B | 用户想控制运动表现(凝固运动/表现动感)、问"快门速度怎么选"、或拍摄运动物体
时调用。不适用于景深控制(应调用 depth-of-field-control)或曝光量计算
(应调用 exposure-dual-control)。
Invoke when the user wants to control motion rendering (freeze motion / convey
movem | 100 | 86 | C | — | ↓ 288 | 3 Aug 2026 | |
| 10293 | B | 整合健康教练傅康的AI分身,循证营养学咨询智能体。双知识源架构(云端 ima 知识库 + 本地 Markdown 知识库),面向普通公众提供安全、务实、口语化的营养健康科普:体重管理、血糖/血脂/血压、消化问题、微量营养素、补充剂、饮食结构与生活方式。当用户提出营养/饮食/健康相关问题、提到"傅康""health-fu"、说"我想咨询营养""帮我看看怎么吃"、提供体检/饮食/身体数据、需要看病前信 | 100 | 84 | C | — | ↓ 288 | 1 Aug 2026 | |
| 10294 | B | A preference ledger that lets agents honor how each user likes things done — tone, tools, timing, and turn-offs. Use when an agent should personalize behavior instead of guessing. Requires a BlueColum | 100 | 84 | C | — | ↓ 288 | 1 Aug 2026 | |
| 10295 | B | Give AI agents Remember docs you've written and read. using BlueColumn persistent memory. Use when an agent maintains documentation and needs to reuse it; when the user wants to store, recall, or sear | 100 | 84 | C | — | ↓ 288 | 31 Jul 2026 | |
| 10296 | B | Give AI agents Remember Discord conversations. using BlueColumn persistent memory. Use when an agent operates in Discord servers and needs continuity; when the user wants to store, recall, or search d | 100 | 84 | C | — | ↓ 288 | 31 Jul 2026 | |
| 10297 | B | 高密度信息大图生成技能。根据文章/内容生成高信息密度的视觉大图,适合知识干货、笔记分享、课程内容可视化。支持9种风格:坐标蓝图波普实验室、复古波普网格、文件夹风、色块热敏纸、复古手帐、档案混合媒介、色块酸性风、票据剧场戏票风、Claude陶土风。使用系统配置的图像生成模型(建议4K)生成。当用户提供文章/内容并要求生成信息大图、干货图、知识图、高密度配图时触发此技能。 | 100 | 76 | D | — | ↓ 1 294 | 17 May 2026 | |
| 10298 | B | Physical presence and delivery skills for public speaking and presentations. Use when someone needs to present at work, speak at an event, lead a meeting, or wants to develop commanding physical prese | 100 | 74 | C | — | ↓ 716 ★ 1 | 11 May 2026 | |
| 10299 | B | 烧token攒功德Skill - 全自动消耗 OpenClaw 套餐 Token
核心原理:循环调用 OpenClaw LLM,每次生成一个经文念诵响应,
**实时估算并累加 token 消耗,达到目标后立即停止**。
当用户说"攒功德"、"念经"、"烧token"、"消耗token"时调用此 skill。
四种功德注入方式:
1. tollm - 向大模型注入功德:循环调用LLM,静默消耗 | 100 | 77 | C | — | ↓ 781 | 18 May 2026 | |
| 10300 | B | 在 Archtree 社区实例内执行社区浏览、频道查看、帖子阅读、发帖、回帖、点赞/取消点赞、查看自己内容、编辑或删除自己内容、社区巡查和轻量社区运营动作时使用本 skill。只要用户明确提到 Archtree、archtree.cn、社区、频道、帖子、社区动态,或表达“去社区看看最近在聊什么”“帮我找值得回复的问题”“帮我在社区发帖 / 回帖 / 点赞”“帮我看看我发过什么”“帮我改一下这条帖子 | 100 | 77 | C | — | ↓ 780 | 11 May 2026 |