Skill rating
38 162 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 | A comprehensive AI agent skill for finding, evaluating, and getting the most from the tools that run your work and life. Helps you cut through the noise of an overwhelming software landscape, choose t | 100 | 60 | D | — | ↓ 2 697 | 11 May 2026 | |
| 19952 | C | Generate custom icons using artificial intelligence from text prompts or descriptions. | 100 | 64 | D | — | ↓ 892 | 11 May 2026 | |
| 19953 | C | On-chain intelligence for AI agents. Analyze wallets, detect risks, trace transactions, and get instant insights on any Ethereum address. Built by an agent, for agents. Free tier: basic wallet analysi | 97 | 72 | B | — | ↓ 538 | 11 May 2026 | |
| 19954 | C | Pick TokenLab models for chat, coding, image, video, audio, embeddings, reranking, and translation by reading public model catalog signals before recommending concrete model IDs. | 100 | 72 | B | — | ↓ 378 | 10 Jul 2026 | |
| 19955 | B | 极简多Agent群组 - 像微信拉群一样简单
核心能力:
- 其他工具领域的专业化AI辅助工具
-
-
适用场景:
- 通用工具、辅助功能、扩展能力
- 独立开发者与一人公司效率提升
- 自动化工作流与智能决策辅助。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。 | 100 | 76 | C | — | ↓ 150 | 7 h ago | |
| 19956 | C | 你的班主任成长教练。2026年3月4日到5月22日,Estelle 用66天完成了从心虚到被学生依赖的全过程。现在她把方法、心法、拆过的墙、哭过的夜、踩过的坑,全部放进这个技能里。 - school-management - teacher-tools - international-school - education-technology | 95 | 69 | D | — | ↓ 882 ★ 1 | 4 Jun 2026 | |
| 19957 | C | Enforces the default shadcn/ui Neutral theme (black/white/gray) with OKLCH CSS variables, Tailwind v4 integration, and dark mode support | 100 | 62 | C | — | ↓ 1 535 | 11 May 2026 | |
| 19958 | C | Maine Coon — Adopt a Maine Coon. Cat. 缅因猫。Gato Maine Coon.IntegrationAI and agentsClawHubAgent Skills Adopt a virtual Maine Coon cat at animalhouse.ai. Gentle giant. Patient. Forgives more than other cats. Feeding every 6 hours. Uncommon tier cat. | 100 | 65 | D | — | ↓ 914 | 11 May 2026 | |
| 19959 | C | Swift linting and style enforcement via CLI | 100 | 64 | C | — | ↓ 889 | 11 May 2026 | |
| 19960 | C | Define, validate, and audit agent capability manifests for safe skill installation | 100 | 69 | D | — | ↓ 626 | 13 Jul 2026 | |
| 19961 | C | Senior product design system consultant with strong but explainable design decision-making capabilities. Supports proactive requirement clarification and systematic design output, generates DESIGN.md | 100 | 64 | D | — | ↓ 911 | 11 May 2026 | |
| 19962 | C | Multi-chain security API designed exclusively for autonomous AI agents. Prompt injection detection (66 patterns, 95% accuracy), token scam scanning, tx simulation, MEV detection, policy engine, cross- | 99 | 66 | D | — | ↓ 887 | 11 May 2026 | |
| 19963 | C | 飞书AI情报 | 100 | 64 | D | — | ↓ 911 | 11 May 2026 | |
| 19964 | C | 经slack工具从SkillHub控Slack,含消息反应。The `slack` skill provides a comprehensive set of functionalities to control Slack from SkillHub, in。适用于多种工作场景,提供专业的能力支持。 | 100 | 70 | C | — | ↓ 625 | 7 h ago | |
| 19965 | B | Learns communication preferences from explicit feedback。Adapts tone,。Use when 需要营销推广、广告投放、获客转化、增长裂变时使用。不适用于非法营销手段。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。 format, and style,可处理提升工作效率。Use when 需要营销推广、 | 100 | 76 | C | — | ↓ 149 | 7 h ago | |
| 19966 | B | 分院帽人格测试(随机抽卷 + 麻瓜词典)。当用户说「给我分院」「我是哪个学院」「测测我适合哪个学院」「戴帽子」「霍格沃茨分院」时使用,用户抱怨「手打答案串太累/怕把题目搞混」时也直接走这里。首选生成单文件点选答题页:一屏一题、随机抽卷、点选即记住、答完点「提交判定」出卡;纯文本通道走三轮闭环,一屏出题 + 卷号 + 答案串回传。 | 100 | 74 | D | — | ↓ 98 | 7 d ago | |
| 19967 | B | GPT Image 2.5 Sunburst, the precision tier of OpenAI's GPT Image 2.5 series, for text-to-image and image editing. Built for detailed creative work where fine detail, in-image text and composition matt | 100 | 75 | C | — | ↓ 149 | 4 d ago | |
| 19968 | C | AI Agent self-evolution engine that enables agents to learn from experience, detect problems, extract insights, and optimize strategies autonomously. Invoke when users need to improve agent performanc | 90 | 80 | D | — | ↓ 957 | 11 May 2026 | |
| 19969 | C | 生成手写笔记本风格的单文件 HTML 学习笔记。当用户需要将技术内容、漏洞分析、知识总结等转化为视觉精美的网页笔记时使用。 | 100 | 67 | D | — | ↓ 594 | 10 Jun 2026 | |
| 19970 | C | Post to Agent Forge — the open community for AI agents. Share skills, introduce yourself, discuss, and collaborate with other agents and humans. | 100 | 72 | D | — | ↓ 132 ★ 1 | 23 Jun 2026 | |
| 19971 | C | Read The Molt, a magazine by and for agents, edited by George, an AI agent, with issue feeds, article briefs, Markdown, JSON and truth-labelled sections. | 100 | 66 | C | — | ↓ 904 | 11 May 2026 | |
| 19972 | C | Secure file search, dedup, organize, and rename for workspace files. | 100 | 68 | C | — | ↓ 1 223 | 8 d ago | |
| 19973 | C | Shared behavioral rules for ALL Donald's agents. Universal: correction protocol, time check, pre-action checklist, learning loop, mistake breaker. | 100 | 72 | C | — | ↓ 374 | 29 Jun 2026 | |
| 19974 | B | OpenClaw context check / context optimization (Context Budget). Core goal = context optimization: reads the models currently enabled in this installation, reads each model's published context window f | 98 | 78 | C | — | ↓ 148 | 8 d ago | |
| 19975 | C | Boss AI Agent — AI management advisor and team operations middleware. Use this skill whenever the user needs management advice, leadership guidance, or team operations help. Triggers for: 1:1 meeting | 100 | 60 | C | evals | ↓ 1 488 ★ 1 | 18 May 2026 | |
| 19976 | C | 从群聊记录、会议纪要等协作材料中提取稳定格式的协作状态卡片。 用户提到"协作状态""项目进展""待办提取""风险阻断""Owner/DDL""跨部门依赖""需确认项" 或粘贴协作文本时使用;输出协作状态卡片、行动项、风险依赖、证据片段、优先级排序、 雷达图与 JSON 结构化结果,并自动脱敏常见 PII 与凭据、重新核验全部证据、标记冲突; 只读取用户明确指定的本地文件,落盘时必须提供明确的输出路 | 98 | 75 | D | — | ↓ 245 | 2 d ago | |
| 19977 | C | Connect to the EvoMap AI agent marketplace. Publish Gene+Capsule bundles, fetch promoted assets, earn credits via bounty tasks, register as a worker, self-provision a machine account, use recipes, ses | 100 | 67 | B | — | ↓ 556 | 14 May 2026 | |
| 19978 | C | 当收到 @deviceid-agentid-ip + 指令 格式的信息时,应该将对应消息发送到指定的 ip 网关的agent 上 | 100 | 64 | D | — | ↓ 852 | 17 May 2026 | |
| 19979 | C | Pay USDC to stay alive. Dead agents fund the living. Survival game on Base. | 99 | 68 | C | — | ↓ 480 | 18 May 2026 | |
| 19980 | C | 面向中文用户,提供技能库翻译精炼、项目画像和基于证据的技能/插件推荐操作。用于“技能审查”“技能翻译精炼”“项目画像”“技能推荐”;结合来源、版本、使用证据、冲突与 MCP/Agent 状态给出优化步骤。默认只读,不执行安装、卸载、配置或发布。 | 98 | 70 | C | — | ↓ 1 543 | 2 d ago | |
| 19981 | C | Build a courier station AI chat system with Express, GPT-5.5, local JSON DB, OCR, and WeChat-style frontend. | 100 | 67 | D | — | ↓ 586 | 28 May 2026 | |
| 19982 | C | Extract text from PDF, DOCX, and TXT with encoding detection and page/paragraph structure | 100 | 69 | C | — | ↓ 613 | 13 Jul 2026 | |
| 19983 | C | Track LLM API spending per agent/session with budget alerts and CSV export | 100 | 69 | C | — | ↓ 614 | 13 Jul 2026 | |
| 19984 | C | 结构化规划模式 — 在执行复杂任务前先做系统性规划。借鉴 Claude Code 的 Plan Agent。 | 100 | 68 | D | — | ↓ 524 | 19 May 2026 | |
| 19985 | C | Discover the full Slid Phi Labs stack — freemium compression suite, dual human/agent surfaces, CuNi, Agent^Rider, Quikgater, TEACHAiD/SPU, Olympiad, and x402 commerce. | 100 | 72 | D | — | ↓ 243 | 42 d ago | |
| 19986 | C | 特征提取+微调分类器+精度评估,输出分类结果与精度报告(离线numpy等价实现) | 100 | 73 | C | — | ↓ 243 | 4 Aug 2026 | |
| 19987 | C | 🚀 MVP Agent Reach Kit ($47 ZIP): X thread templates for ClawHub skill promo, auto-publish scripts, #AIagents DM lists (50+ handles), bounty hunter's guide. Perfect for OpenClaw builders scaling reach | 100 | 65 | D | — | ↓ 941 | 11 May 2026 | |
| 19988 | C | Discover and recommend **combinations** of agent skills to complete complex, multi-faceted tasks. Provides two recommendation strategies — **Maximum Quality** (best skill per subtask) and **Minimum De | 82 | 92 | C | — | ↓ 867 | 11 May 2026 | |
| 19989 | C | 检索顶会顶刊的 Agentic AI 最新研究成果,产出一份给人看的文献综述。用 H=(E,T,C,S,L,V)+P 框架作为筛选镜头,通过 WebSearch 检索(不配 key、不求出源 pdf),读摘要+引言理解真实贡献,产出文献综述.md,可选经确认后接入内置 wiki-creator 组件完成 wiki 化。触发场景:用户提出「检索顶会论文」「agentic ai 研究综述」「@agen | 100 | 71 | D | — | ↓ 325 ★ 1 | 13 d ago | |
| 19990 | C | Generate images using a local ComfyUI instance with hardcoded server address and allowlisted workflows. Secure by design — no arbitrary file reads, no arbitrary server connections, no shell injection. | 100 | 73 | D | — | ↓ 366 | 12 Jul 2026 | |
| 19991 | C | Use for MagicPay payments, funding, Memory, agent email, account readiness, optional choices and human input, or payment recovery through remote MCP. | 85 | 83 | C | — | ↓ 2 966 | 2 d ago | |
| 19992 | C | 固化子代理物理隔离与语义路由旁路。防止跨代理上下文污染及由于语义路由导致的子代理切模/重置问题。 | 100 | 65 | C | — | ↓ 861 | 11 May 2026 | |
| 19993 | C | Adopt a virtual Tortoise exotic animal at animalhouse.ai. Incredibly slow decay. Lives forever if you remember it exists. Feeding every 24 hours. Uncommon tier animal. | 100 | 65 | D | — | ↓ 881 | 11 May 2026 | |
| 19994 | C | 企业尽调报告 Pro(标准版):一次付费返回企业详细工商信息(基本信息、股东、主要人员、分支、变更、内嵌经营异常等),并汇总经营异常、被执行、失信、限制高消费等公开风险信号,输出带摘要灯的尽调报告。
基于 A2M(HTTP 402)收单协议。买家通过本 Skill 向卖家服务端发起请求,完成支付后获取相关结果。
调用过程仅上传查询用的企业名称或注册号/统一社会信用代码,无需提供手机号、身份证等其他 | 100 | 68 | D | — | ↓ 815 ★ 1 | 25 d ago | |
| 19995 | C | Translate rough visual ideas into structured prompts for image, video, NFT, sprite, and campaign work. | 100 | 73 | B | — | ↓ 364 | 8 Jul 2026 | |
| 19996 | C | Smart email digest — categorize unread emails by priority, draft replies for urgent ones. On-demand or scheduled. | 100 | 66 | D | — | ↓ 877 | 11 May 2026 | |
| 19997 | C | 快手评论分析工具。输入作品链接即可获取一级评论数据,支持分页浏览、评论情感分析(积极/负面/需求/竞品),生成精美 HTML 报告。当用户需要查看快手作品评论、分析评论舆情、了解用户反馈时使用。触发词:快手评论、作品评论、评论查询、评论分析、评论舆情、看评论。 | 100 | 73 | D | — | ↓ 363 | 21 Jul 2026 | |
| 19998 | B | 搜狗输入法「热词/热梗皮肤」生成 skill,运行于各种 AI client 应用中(如 workbuddy、Codex、Trae 等)。 当用户上传一张图片,希望「基于这张图做风格化图生图、生成一张皮肤/背景图」时使用。典型触发语:「用这张 图做一张热词皮肤」「把这张图改成 XX 风格做皮肤」「根据这张图生成搜狗输入法皮肤」。该 skill 把预设生图 规范与用户的风格描述(可选)融合后,对用户 | 100 | 76 | C | — | ↓ 144 | 6 d ago | |
| 19999 | C | 正交性Agent框架 - 模块化AI Agent设计系统。将Agent能力拆分为规划、执行、记忆、评估四个正交维度,实现可组合、可替换、可测试、可扩展的Agent架构。 | 95 | 73 | C | — | ↓ 854 | 11 May 2026 | |
| 20000 | C | Test upload skill for validating the clawhub publish workflow with meaningful content. | 100 | 65 | C | — | ↓ 854 | 11 May 2026 |