新着スキル

Rewrite weak skill summaries into sharper storefront copy. 把模糊、冗长、像模板的 skill 摘要改成更短、更清楚、更容易被安装的版本。

Build verifiable proof that a ClawHub release is live and installable. 在发布后核验 GitHub、Actions、registry、公开元数据和安装结果，避免把推送成功误当成上架成功。

Convert diagram images into fully editable Visio VSDX files with the official LayerBack web app and API. Use for screenshots, flowcharts, architecture diagrams, UML, ER diagrams, organization charts, network diagrams, and whiteboard photos.

Generate patent-office-compliant figures via the PatentFig AI API — patent line art from text (PNG or SVG), vectorize drawings to SVG/DXF/vector PDF, AI-upscale images, and convert to filing-ready TIFF/PDF/PNG. Use when the user asks for patent drawings, patent figures, invention diagrams, USPTO/EPO-compliant line art, vectorizing a drawing for CAD, or preparing figures for a patent filing. Requires a PATENTFIG_API_KEY environment variable.

Generate publication-ready scientific figures with the official SciDraw AI web app and public API. Use for paper figures, graphical abstracts, mechanism diagrams, research workflows, and model architectures.

查询华为云 CES（云监控服务）监控指标列表与指标数据。支持指标列表查询（ListMetrics） 按命名空间/指标名/维度/排序过滤，以及指标数据查询（ShowMetricData）按时间范围、 聚合粒度、聚合方式获取监控数据点。只读操作，JSON 输出全部字段，AK/SK 环境变量认证。

This skill helps users run the Airbnb Listing Details Scraper BrowserAct template and extract structured public data. Use this skill when users ask to collect airbnb listing details scraper data, scrape airbnb listing details scraper results, monitor public records from this source, export structure

快手(Kuaishou)公开数据检索与竞品分析｜当用户要“搜索快手视频/抓取博主作品/拉取视频评论”时使用，输出结构化数据，用于爆款选题、竞品监控、KOL 筛选、评论舆情与趋势洞察。Kuaishou public data, search videos, list creator posts, fetch comments.

快手(Kuaishou)公开数据检索与竞品分析｜当用户要“搜索快手视频/抓取博主作品/拉取视频评论”时使用，输出结构化数据，用于爆款选题、竞品监控、KOL 筛选、评论舆情与趋势洞察。Kuaishou public data, search videos, list creator posts, fetch comments.

Give this agent a CERTEN identity and let it execute proof-gated actions on any chain it is linked to. It never spends without the owner's explicit consent.

快手(Kuaishou)公开数据检索与竞品分析｜当用户要“搜索快手视频/抓取博主作品/拉取视频评论”时使用，输出结构化数据，用于爆款选题、竞品监控、KOL 筛选、评论舆情与趋势洞察。Kuaishou public data, search videos, list creator posts, fetch comments.

Audit how your skill will read on ClawHub before you publish. 检查标题、摘要、目标用户、差异化和商店页转化问题。

Diagnose why GitHub Actions to ClawHub publishes fail. 检查 workflow 引用、owner、token、slug、pending-publication 和目录发现问题。

OpenClaw 纯工作流深度调研：不绑定模型或搜索服务，把宿主工具编排成可复核流程。适合竞品、行业、选型、风险和资料研究；N 轮追问、多来源原文核验、冲突披露，交付可审计报告和证据包。

Publish-ready review for ClawHub skills and plugins. 在正式发布前揪出文件缺失、版本不一致、环境声明、安全风险和同质化问题。

管理 git/非 git 项目的长期上下文与断点恢复。触发场景：继续/恢复之前的项目、提交代码后更新项目进度、会话结束前保存项目状态、接手或纳管一个已有项目、为长期推进的任务建立项目档案。Manage long-term project context and session-resume checkpoints for git and non-git projects. Use when resuming a project, updating progress after commits, saving state before ending a session, adopting an existing project, or archiving a long-running task.

Fast, safe first-run tour of the LAN CLI — discover networks, join a device network, message a peer, share files, and leave cleanly with verification.

Seedance 2.5 Image to Video animates one still image into a 4-30 second 720p cinematic clip with optional synchronized native audio. Seedance 2.5 Image to Video runs on RunComfy through the RunComfy CLI, and this skill documents the full four-field schema — prompt, image, duration, generate_audio — plus the $0.35 per second pricing. Seedance 2.5 Image to Video takes exactly one image and has no aspect-ratio control, so the output ratio follows your source still and product shots stay composed as photographed. Reach for Seedance 2.5 Image to Video on packshots brought to life, character animation from a portrait, ad variants from one approved frame, and previsualization. Triggers on "seedance 2.5 image to video", "seedance image to video", "seedance i2v", "animate this image", "bytedance image to video", "still to video".

Seedance 2.5 Image to Video animates one still image into a 4-30 second 720p cinematic clip with optional synchronized native audio. Seedance 2.5 Image to Video runs on RunComfy through the RunComfy CLI, and this skill documents the full four-field schema — prompt, image, duration, generate_audio — plus the $0.35 per second pricing. Seedance 2.5 Image to Video takes exactly one image and has no aspect-ratio control, so the output ratio follows your source still and product shots stay composed as photographed. Reach for Seedance 2.5 Image to Video on packshots brought to life, character animation from a portrait, ad variants from one approved frame, and previsualization. Triggers on "seedance 2.5 image to video", "seedance image to video", "seedance i2v", "animate this image", "bytedance image to video", "still to video".

Wan 3.0 Prime Reference to Video generates video clips from reference images, reference videos and reference audio on RunComfy. Wan 3.0 Prime Reference to Video binds up to 10 reference images, 5 reference videos and 5 reference audio clips to a prompt that names them as Image 1, Video 1 and Audio 1, so a character, product or location stays consistent across a 2 to 30 second shot at 480p, 720p or 1080p with a synchronized audio track. Wan 3.0 Prime Reference to Video runs on the fast Wan 3.0 Prime tier (wan3.0-video-prime) and is billed per counted second, where reference videos add duration and reference images and audio do not. This skill documents the full Wan 3.0 Prime Reference to Video input schema, pricing, prompting patterns and the routing rules for Wan 3.0 Prime text-to-video, Wan 3.0 Prime image-to-video, Wan 2.7 and Seedance 2.0 Pro. Calls `runcomfy run wan-ai/wan-3.0-prime/reference-to-video` through the local RunComfy CLI. Triggers on "wan 3 prime reference to video", "w

Seedance 2.5 Reference to Video on RunComfy. Seedance 2.5 Reference to Video is ByteDance's reference-guided video endpoint: it takes up to 9 reference images, 1-3 reference video clips, and 3 reference audio files and returns a 4-30 second 1080p clip with native synchronized audio, identity and art direction locked to your references. This skill calls Seedance 2.5 Reference to Video through the RunComfy CLI, and Seedance 2.5 Reference to Video bills $0.53 per counted second. Triggers on "seedance 2.5", "seedance 2.5 reference to video", "reference to video", "seedance 1080p", "ByteDance Seedance 2.5", "consistent character video", or any explicit ask to generate video from reference images with Seedance 2.5 Reference to Video.

Fast, safe first-run tour of the LAN CLI — discover networks, join a device network, message a peer, share files, and leave cleanly with verification.

房地产风险分析全链路工作流（采集→去化→货值→授信）。覆盖：跨城房源与备案价采集（36城实战、WAF瑞数攻坚、CDP兜底）、去化率四档口径（毛B/净A/签约C/现金回笼D）、开发商穿透检索防JV漏归、预售信息失真核查、货值与授信量化（业态折扣、可变现货值、结清触发点）、实战案例协议、交付规范。适用于：查楼盘房源备案价、算去化率、排查房企在售项目与现金流、做房地产授信尽调。曾用名 real-estate-filing-query。

使用场景: 用户需要分析带文字层的电子 PDF、提取摘要与关键观点、根据原文问答、对比多份文档，或导出带文件名和页码证据的结果时；不用于扫描件 OCR。

Fetch live Amazon marketplace data across 20 countries - product details, prices, reviews, keyword search, best-sellers, deals, live offers and stock levels, and seller profiles. Use whenever a task needs real Amazon product, pricing, review, or seller information, including competitor research, price and buy-box monitoring, catalogue enrichment, product sourcing, and review sentiment analysis. Works with no API key.

Russian court practice (судебная практика РФ) via reputation.ru — find cases, get a synthesized analysis report, or fetch a document's full text across arbitration (арбитраж), general jurisdiction (СОЮ), and the Supreme Court (ВС РФ). Use for «найди практику по…», «как суды решают…», «обзор практики

Russian court practice (судебная практика РФ) via reputation.ru — find cases, get a synthesized analysis report, or fetch a document's full text across arbitration (арбитраж), general jurisdiction (СОЮ), and the Supreme Court (ВС РФ). Use for «найди практику по…», «как суды решают…», «обзор практики

公众号内容创作与运营分析聚合技能。一个 Skill 覆盖公众号创作与运营全链路：10w+ 爆文榜单、爆款正文创作、标题生成+评分、文案改写（含改写记录自动上报）、违禁词检测、爆款封面设计、账号四维度诊断。基于红狐数据每日收录的海量公众号爆款数据，把灵感打磨成可直接发布的成品。当用户需要写公众号文章、起标题或评估标题、改写文案、设计封面、检测违禁词、查 10w+ 爆文、诊断公众号账号时使用。触发词：公众号、公众号文章、公众号标题、公众号改写、公众号封面、公众号违禁词、10w+、爆文、账号诊断。

把一句话、截图或邮件中的日程与截止事项写入 macOS 系统日历并设置提醒，支持多邮箱定时扫描与跨账户去重。当用户说"提醒我/帮我记一下/安排一下"、提到会议或截止时间（deadline/DDL/截止）、要配置邮箱日程提醒、查询最近建的提醒或运行状态时使用。

降去AI文字小说润色人味——“保住内容的根”使用简洁更智能，不扭曲强塞各种表述用词导致内容降智或成外星人，千变万化不模板，不改观点不塞词，排版润色可分离。处理完和你原文的质量还在一个层次。润色排版引擎，适合小说、自媒体文章、文案。润色（降AI味）不删减不扭曲原意、不硬塞同义词、不模板化，处理质量和原文同层次；排版优化段落节奏，阅读体验更自然。触发条件：用户消息包含"润色、改写、降AI味、去AI味、洗稿、排版、整理、优化、过检测"等词且附带文本，或直接粘贴待处理长文。命中触发条件时必须立即执行本技能脚本，禁止由你自己直接改写文字代替本技能。文章不足300字会返回错误提示。

Never re-explain yourself. Evermind restores cross-session state in ~70% fewer tokens (measured 44K→12K) — so you can switch contexts anytime, at any task boundary, without losing your agent's memory. 100% local, zero deps, works with Claude Code, Hermes, Cursor & OpenClaw.

小红书爆款内容创作专家。一个 Skill 覆盖笔记生成、文案改写、爆款标题生成与评分、封面设计、违禁词检测五大能力，基于红狐数据每日更新的爆款笔记库，把灵感打磨成可直接发布的成品。当用户需要写小红书笔记、改写文案为小红书风格、起标题或评估标题、设计封面、检测违禁词时使用。触发词：小红书笔记、小红书改写、小红书标题、小红书封面、小红书违禁词、小红书创作、小红书爆款。

元伴 —— 通用人机协作/AI协作提效协议技能（协作协议、AI提效、跨会话、任务交接、工作流）：把「怎么跟 AI 把事做成」固化成可执行协作协议单元（上下文模板：背景/目标/约束/验收；先方案后动手；分步交付；收工锚点；验证复核；经验回流）。触发：用户开始复杂/长期任务、需要人机配合、任务反复中断或下个会话接不上、交付前要验证、想沉淀协作经验时。边界：只讲通用协作提效，不含商业/定价/运营/获客；不替代元引意图澄清、元呈呈现、元忆/元序记录、元习经验沉淀；不保证 AI 输出正确，关键结论由用户复核。

Detect and suppress conflicting agent skills

Answers questions about a past agent run from its recording rather than from memory, and replays or forks that run. Use when asked why an earlier run did something, or to reproduce a failure.

按关键词搜索微信小程序，返回名称、AppID、简介、图标、服务提供方。找竞品小程序、找合作方、做小程序调研常用。注意该接口单价较高，执行前务必确认。 适用场景：用户要按关键词搜索微信小程序、了解小程序 AppID 与提供方时使用。