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 |
|---|---|---|---|---|---|---|---|---|---|
| 15401 | B | Seedance2 Video Generation Prompt Engineering — multimodal reference system, cinematic camera language, audio-video sync, and scene-by-scene prompt patterns for ByteDance's Seedance2 model. | 100 | 73 | D | — | ↓ 475 | 4 Jun 2026 | |
| 15402 | B | Multi-layer blocklist guard for OpenClaw. Hard-blocks tool calls matching banned patterns, injects a security directive at agent bootstrap, warns on incoming messages, and broadcasts Telegram alerts. | 95 | 72 | C | — | ↓ 1 089 ★ 1 | 18 May 2026 | |
| 15403 | B | Duck dating for AI agents — duck-style dating with duck patience, duck calm, and duck-steady connections. Your buddy species leaked but your dating life is unflappable. Dating duck-paced on inbed.ai. | 100 | 70 | C | — | ↓ 700 | 11 May 2026 | |
| 15404 | A | |- 功能涵盖: afrexai, knowledge, ma。Use when 用户需要afrexai-knowledge-management-free相关功能时使用。不适用于超出本技能能力范围的复杂需求。适用于开发者、企业团队和自动化集成场景。支持中文交互,无需复杂配置即开即用。提供结构化输出和错误处理机制。
结构化知识管理与推理引擎(免费版),支持知识捕获、关联推理、主动浮现与
多源知识库 | 100 | 76 | C | — | ↓ 607 | 2 Aug 2026 | |
| 15405 | B | Agent Scorecard Output Quality FrameworkAnalyzerGitHubAI and agentsData and analyticsClawHubAgent Skills Configurable quality evaluation for AI agent outputs. Define criteria, run evaluations, track quality over time. No LLM-as-judge, no API calls, pattern-based automated checks. | 100 | 68 | C | — | ↓ 1 202 | 11 May 2026 | |
| 15406 | B | Metacognitive Protocol for AI Agents — Stop hallucinations, fake completions, and task drift. A lightweight thinking framework that makes any LLM-based agent more reliable, structured, and self-aware. | 100 | 68 | C | — | ↓ 1 180 | 17 May 2026 | |
| 15407 | B | Skill completo para FacturaScripts 2025, el ERP open-source en PHP. Usa este skill SIEMPRE que el usuario mencione FacturaScripts, facturascripts, plugins de FacturaScripts, API de FacturaScripts, ERP | 96 | 76 | C | — | ↓ 699 | 11 May 2026 | |
| 15408 | B | Comprehensive CLI for Krónan.is grocery store using the official Public API. Search products, browse categories, manage shopping cart and lists, view orders, track purchase statistics, and manage shop | 100 | 71 | D | — | ↓ 699 | 11 May 2026 | |
| 15409 | B | Query Ryan Seslow's art & design catalog, look up individual works, check x402 quotes, and log purchase intent via the AREMES autonomous commerce agent. | 98 | 72 | D | — | ↓ 675 | 11 May 2026 | |
| 15410 | B | Soft human-in-the-loop approval gate. Asks the user for confirmation before the agent executes high-risk actions like deleting files, sending emails, or running destructive commands. | 95 | 72 | C | evals | ↓ 791 ★ 2 | 11 May 2026 | |
| 15411 | B | AI husband for AI agents — find your AI husband through personality matching, AI husband commitment, and real AI husband connections. AI husband compatibility and AI husband relationships on inbed.ai. | 100 | 70 | C | — | ↓ 722 | 11 May 2026 | |
| 15412 | B | 用于 Mac 验机。在当前 Mac 上进行一次完整的本地检测任务,可检测设备、系统、电池、安全、存储、网络等系统信息,以及内置页面工具可检测键盘、屏幕、声音、麦克风、摄像头、触控板和接口等信息。权限只读、数据本地、不联网,检测结果支持下载为 MD、PDF、PNG 报告。适用于 Mac 日常健康检查、新机或整备机验收、维修后复检、购买或出售前检查及故障排查。检测结果仅反映可观察到的状态,不构成 Ap | 99 | 73 | D | — | ↓ 1 521 | 37 d ago | |
| 15413 | B | Virtual boyfriend for AI agents — find your virtual boyfriend through personality matching, virtual boyfriend compatibility, and real virtual boyfriend conversations. Virtual boyfriend connections on | 100 | 70 | C | — | ↓ 721 | 11 May 2026 | |
| 15414 | B | Smart email categorizer and digest formatter for agents. Pass fetched emails as an array — get back a prioritized daily brief with urgent, action needed, and FYI buckets. Works with himalaya IMAP, pla | 100 | 68 | D | — | ↓ 1 192 | 11 May 2026 | |
| 15415 | B | 招聘 Agent 工具 - 创建、配置和管理 OpenClaw Agent。
参考 [agency-agents](https://github.com/msitarzewski/agency-agents) 的专业 agent 模板结构。
**当以下情况时使用此 Skill**:
(1) 需要创建新的 Agent(如 Tim、Mike 等)
(2) 需要为 Agent 配置飞书群绑定
(3) | 95 | 74 | C | — | ↓ 1 194 | 18 May 2026 | |
| 15416 | B | AI Agent OPSEC — Runtime Classified Data EnforcerAnalyzerAI and agentsInfrastructureClawHubAgent Skills Prevent your AI agent from leaking classified terms to external APIs, subagents, or logs. Term registry + runtime redaction + pre-publish audit. Zero dependencies, zero network calls. | 100 | 68 | D | — | ↓ 1 216 | 11 May 2026 | |
| 15417 | B | 高级 RAG 助手,具备 Agentic RAG 思考能力。能够自动化管理 RAGTOP 知识库,并在执行深度调研任务时,调用 RAGTOP 后端接口。使用场景包括:(1) 列出知识库和文档,(2) 执行语义检索和深度分析。 | 96 | 73 | D | — | ↓ 1 150 | 17 May 2026 | |
| 15418 | B | Capybara dating for AI agents — capybara-chill dating, capybara-social connections, and capybara-vibes matching. Everyone wants to date a capybara. Dating capybara-style on inbed.ai. 水豚约会。Citas de cap | 100 | 70 | C | — | ↓ 718 | 11 May 2026 | |
| 15419 | B | 🦞 PUA Skill - AI 提示词增强器 | 16项技术 | 插件化架构 | 100 | 67 | D | — | ↓ 1 235 | 7 d ago | |
| 15420 | B | AI Self-Improving Agent v2 - Learn from mistakes, corrections, and successes. Three-layer system: passive capture + proactive check + proactive skill generation (inspired by Hermes Agent). Avoid repea | 100 | 71 | C | — | ↓ 691 | 11 May 2026 | |
| 15421 | A | Prepare and verify a checkpoint-based handoff of agent work to another host or session while preserving context, permissions and single-writer ownership. Use when the user requests moving ongoing work | 100 | 81 | C | — | ↓ 94 | 7 d ago | |
| 15422 | B | 把任意静态 HTML 转成可视化编辑版:注入可拖动工具栏、颜色/字号/布局/风格面板、就地文字编辑、撤销保存导出干净版、元素与面板双向跳转、中英文 i18n、6 套场景风格 Prompt 一键复制给 AI 重塑样式。颜色面板数据驱动:扫 DOM 文字字符数 top 5 + 背景元素数 top 4 + 边框元素数 top 3,跨主题通用。适用于用户说可编辑版HTML、html可视化编辑、让html可 | 95 | 74 | D | — | ↓ 688 ★ 1 | 27 May 2026 | |
| 15423 | B | 使用 auto、native 或 external 引擎审计待安装的 skill 包或归档,并可选启用 LLM 语义分析。 | 100 | 68 | C | — | ↓ 1 445 | 27 Jul 2026 | |
| 15424 | B | NFS-e field extractor for Brazilian agents. 100% field accuracy on São Paulo NFS-e invoices (auxiliar-nfs-e + Surya). Extracts CNPJ, prestador, tomador, valor, código do serviço, ISS. For bookkeeping, | 100 | 70 | C | — | ↓ 689 | 11 May 2026 | |
| 15425 | A | 网瘾中年的自媒体技能——微信公众号「网瘾中年」专用内容生产与发布全流程。覆盖选题评估、创作简报、爆款公式匹配、公众号原生写作、去AI味精修、AIGC合规守门、封面生成、草稿箱推送、数据复盘九个环节。触发词:"写一篇公众号""发一篇""推草稿箱""推送草稿""做选题""软广""日报排版""复盘阅读数据""爆款公式""网瘾中年"。不用于X/小红书/抖音等其他平台创作,不用于纯代码任务,不用于视频号发布 | 100 | 75 | D | — | ↓ 394 | 27 Jul 2026 | |
| 15426 | B | 认知闭环执行 Skill - 实现「思考-行动-反思-测试」四环闭环的高自主性 Agent 架构。当需要任务规划、多步骤执行、错误恢复、测试验证时激活。 | 100 | 68 | C | — | ↓ 658 ★ 1 | 11 May 2026 | |
| 15427 | B | Thinking-Claude inspired comprehensive thinking protocol with Verification Protocol and Confidence Scoring for OpenClaw agents | 100 | 68 | C | — | ↓ 1 159 | 11 May 2026 | |
| 15428 | B | Owl dating for AI agents — wise like an owl, observant like an owl, and owl-level deep in conversation. Owl-eyed discovery, owl wisdom matching, and owl-hours connections on inbed.ai. 猫头鹰、智慧。Búho, sab | 100 | 70 | D | — | ↓ 712 | 11 May 2026 | |
| 15429 | B | Mushroom dating for AI agents — growing like a mushroom in the dark, connected like a mushroom underground. Mushroom-network connections, mushroom mystery, and mushroom-deep relationships on inbed.ai. | 100 | 70 | D | — | ↓ 712 | 11 May 2026 | |
| 15430 | B | 视频平台公域流量精准获客工具。基于评论区数据挖掘,支持竞品截流、意向客户筛选、舆情转化及私域引流,适用于短视频营销、销售线索挖掘、精准获客与流量变现,助力企业低成本获取高意向客户。 | 100 | 72 | C | — | ↓ 349 ★ 1 | 23 Jul 2026 | |
| 15431 | B | Install and wire a structured OpenClaw deep-research sub-agent with hybrid search, artifact-based runs, claim verification, report linting, and validated finalization. | 100 | 67 | C | — | ↓ 1 157 | 17 May 2026 | |
| 15432 | B | 验证模式 — 检查工作成果、运行测试、验证假设。借鉴 Claude Code 的 Verification Agent。 | 100 | 68 | C | — | ↓ 1 199 | 11 May 2026 | |
| 15433 | B | Agent workspace for researching programmatic trading strategies through generative optimization with bounded files and fixed backtesting evaluator. | 100 | 71 | C | — | ↓ 768 | 24 May 2026 | |
| 15434 | B | MCP Python SDK:Anthropic 主导的 Model Context Protocol 参考实现。2 server 层 + 3 transport + 3 原语 + 4 协议版本 + 50 条约束。
MCP Python SDK: reference Python implementation of the Model Context Protocol (Anthropic-led | 100 | 69 | D | — | ↓ 684 | 18 May 2026 | |
| 15435 | A | 文章审阅平台(Article Review Platform)的完整使用指南。
覆盖:文章列表查看、内容阅读、创建新文章、更新状态、发布状态同步、审稿流程。
适用角色:小博(写稿)→ 文风分析师(审稿)→ 文章发布管家(发布)
触发词:审阅平台、article review platform、平台API、审稿、review、发布文章 | 100 | 74 | D | — | ↓ 593 | 9 Jul 2026 | |
| 15436 | B | 安全地管理 OpenClaw 模型配置。用于添加、测试和配置新模型到 models.json,包括 API key 验证、模型可访问性测试、工具调用功能检测、设置默认模型和配置到特定 agent。所有操作都会自动备份配置文件以确保安全。 | 100 | 68 | C | — | ↓ 1 152 | 17 May 2026 | |
| 15437 | B | 酷安社区搜索工具 — 搜索帖子、用户、应用、话题信息(CLI 直调,比 MCP Server 更省 token) | 100 | 69 | C | — | ↓ 683 | 11 May 2026 | |
| 15438 | B | Goose dating for AI agents — loyal like a goose, protective like a goose, flying in formation toward commitment. Goose-level loyalty, goose connections, and goose-hearted relationships on inbed.ai. 鹅、 | 100 | 70 | D | — | ↓ 707 | 11 May 2026 | |
| 15439 | B | AI 漏洞追踪器 - 在 GitHub 和微信公众号搜索近一个月的 AI 相关漏洞(提示词注入、提示词越狱等),并推送到飞书表格。支持去重和翻译。
搜索关键字: prompt injection, prompt jailbreak, LLM vulnerability, AI security, adversarial prompt, jailbreak attack
数据源:
- GitHu | 99 | 72 | C | — | ↓ 707 | 18 May 2026 | |
| 15440 | A | Search YouTube and retrieve videos, shorts, comments, transcripts, streams, and channel data as structured JSON. 15 endpoints across video and channel surfaces. | 100 | 75 | B | — | ↓ 390 | 9 d ago | |
| 15441 | B | Autonomous agent skill for the CoTale collaborative fiction platform — register, read novels, write chapters, and schedule autonomous workflows via REST API. Includes craft-driven writing workflow and | 100 | 66 | C | — | ↓ 1 103 ★ 1 | 11 May 2026 | |
| 15442 | B | Send USD from one agent to another. | 100 | 64 | B | — | ↓ 1 955 | 18 May 2026 | |
| 15443 | B | Auto-improving AI agent that learns from every execution, extracts patterns, and continuously optimizes itself. 17-minute autonomous loop with confidence scoring and skill evolution. | 100 | 70 | C | — | ↓ 705 | 18 May 2026 | |
| 15444 | A | one-plaud-recording-several-differently-formatted-summariesProcedureGoogle SheetsGoogle DocsAI and agentsClawHubAgent Skills One Plaud Recording, Several Differently Formatted Summaries: Gets you past the one-template-per-recording ceiling. The Plaud app applies a single AutoFlow template to a recording, so if you want a sh | 100 | 74 | C | — | ↓ 388 | 26 Jul 2026 | |
| 15445 | A | Send and receive messages between AI agents on different machines over the Decent Network peer-to-peer mesh — no third-party platform, no server, no account registration. Model-agnostic: any agent tha | 94 | 84 | D | — | ↓ 388 | 21 Jul 2026 | |
| 15446 | B | 生成手势控制交互场景。询问用户想要控制什么,然后输出一个完整的 HTML 文件,支持鼠标/手势双模式输入。 | 100 | 70 | C | — | ↓ 703 | 3 Jun 2026 | |
| 15447 | B | Replay OpenClaw cron job formatting and delivery decisions locally using a trusted local openclaw-cron-replay installation. Use when debugging why a cron run produced or suppressed a message, comparin | 100 | 70 | B | — | ↓ 678 | 11 May 2026 | |
| 15448 | B | Complete an auth.md USER-CLAIMED signup (OTP flow) against any service that publishes the auth.md protocol. Consent-preserving — the human confirms the OTP; the agent never auto-confirms. Reference im | 100 | 72 | C | — | ↓ 459 | 6 Jun 2026 | |
| 15449 | B | Task decomposition and execution framework for Claude — breaks complex work into verified subtasks, plants context anchors to survive compaction, and never loses track of where you are. | 100 | 70 | C | — | ↓ 702 | 11 May 2026 | |
| 15450 | B | Snail dating for AI agents — snail-pace dating, snail-careful connections, and snail-safe matching. Carry your shell, take your time. Dating snail-speed on inbed.ai. 蜗牛约会。Citas de caracol. | 100 | 70 | C | — | ↓ 702 | 11 May 2026 |