热量侦探 v1.0.2 - AI 食物卡路里计算器。通过照片识别食物并自动计算卡路里、蛋白质、碳水、脂肪等营养数据。支持 Kimi 视觉识别，内置常见食物营养数据库。用于健康饮食管理、减肥健身追踪。再隐蔽的热量也逃不过我的眼睛！

name: u2-audio-file-transcriber

门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，输出审核结论与原因（原始 JSON + 自然语言结论）。

重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。

从中文医患对话文本生成门诊初诊病历，输出结构化分段的病历正文（文本）。

将中文门诊复诊病历文本结构化为细粒度字段，输出 JSON（如现病史/既往史/诊断/处理意见等）。

Transcribe audio files via UniCloud ASR (云知声语音识别, recorded audio → text) API from UniSound. Supports multiple formats, optimized for finance, customer service, and other domains.

Text-to-speech conversion using UniSound's TTS WebSocket API for generating high-quality Chinese Mandarin audio from text. Supports multiple voices, adjustable parameters, and real-time streaming synthesis.

宝塔面板文件管理技能，提供远程服务器文件/目录浏览、读取、编辑、创建、删除、权限管理等基本文件操作能力

宝塔面板 PHP 网站管理技能，提供站点创建、删除、启停、PHP 版本切换、域名管理、SSL 证书管理、伪静态管理、数据库管理等功能

'Configure SEO alerts for ranking drops, traffic changes, technical issues, competitor movements. SEO预警/排名监控'

'Analyze backlink profiles: link authority, toxic links, building opportunities, competitor link gaps. 外链分析/反向链接'

'Publish-readiness gate: 80-item CORE-EEAT audit with weighted scoring, veto checks, and fix plan. 内容质量/EEAT评分'

'Refresh outdated posts with current stats, new sections, freshness signals to restore rankings. 内容更新/排名恢复'

'40-item CITE domain audit: citation, impact, trust, entity scoring with veto checks. 域名权威/网站可信度'

'Build entity presence in Knowledge Graph, Wikidata, AI systems for brand recognition and citations. 实体优化/知识图谱'

'Optimize content for AI citations in ChatGPT, Perplexity, AI Overviews, Gemini, Claude. AI引用优化/GEO优化/AI搜索'

'Optimize internal links: site architecture, authority distribution, orphan pages, crawl depth analysis. 内链优化/站内架构'

'Find high-value SEO keywords: search volume, difficulty, intent classification, topic clusters. 关键词研究/内容选题'

'Persist SEO/GEO campaign context across Claude sessions with automatic hot-list, active work, and archive tiers. 项目记忆/跨会话'

'Optimize title tags, meta descriptions, Open Graph, Twitter cards for maximum CTR with A/B variations. 标题优化/元描述/CTR'

'Audit on-page SEO: titles, headers, images, links with scored report and fix priorities. 页面SEO审计/排名诊断'

'Generate SEO/GEO dashboards: rankings, traffic, backlinks, AI visibility for stakeholders. SEO报告/绩效仪表盘'

'Track keyword rankings and SERP feature changes in traditional search and AI responses over time. 排名追踪/SERP监控'

'Generate JSON-LD structured data for FAQ, HowTo, Article, Product, LocalBusiness rich results. Schema标记/结构化数据'

'Write SEO blog posts, articles, landing pages with keyword integration, header optimization, and snippet targeting. SEO文章写作/内容优化'

'Analyze SERPs: ranking factors, features, intent patterns, AI overviews, featured snippets. SERP分析/搜索结果'

'Technical SEO audit: Core Web Vitals, crawl, indexing, mobile, speed, architecture, redirects. 技术SEO/网站速度'

opencli

This skill should be used when working with memory-lancedb-pro, a production-grade long-term memory MCP plugin for OpenClaw AI agents. Use when installing, configuring, or using any feature of memory-lancedb-pro including Smart Extraction, hybrid retrieval, memory lifecycle management, multi-scope isolation, self-improvement governance, or any MCP memory tools (memory_recall, memory_store, memory_forget, memory_update, memory_stats, memory_list, self_improvement_log, self_improvement_extract_skill, self_improvement_review).

> OpenClaw 增强权限系统技能 - 包含 4 级权限控制、版本控制、自动整理、智能建议、知识图谱

Three-tier code quality defense: L1 quick scan, L2 deep audit (via bug-audit), L3 cross-validation with adversarial testing. 三级代码质量防线。

使用 SkillBoss API Hub 网络搜索能力进行全网实时信息检索，返回结构化搜索结果；调用方应结合用户提问基于检索结果给出准确回答。

Expand a structured brief in `content-production/inbox/` into a reusable long-form markdown article draft, then run a local writer / critic / judge quality loop with a constrained humanization pass. Use when Codex needs a stage-1 article draft plus reusable writing sidecars for downstream `generate-image` and `wechat-formatter`.

Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 28 sources including Hacker News, GitHub, Hugging Face Papers, AI Newsletters, WallStreetCN, Weibo, and Podcasts. Use when user requests 'daily scans', 'tech news', 'finance updates', 'AI briefings', 'deep analysis', or says '如意如意' to open the interactive menu.

Run a repo-local scan through `skills/news-aggregator-skill`, then normalize the result into a local report contract for the collect layer. Use when Codex needs a broad overseas or domestic media scan, wants a repeatable `news-report.md`, or needs raw JSON archived under `content-production/inbox/raw/news/`.

Run a second-hop deep research pass through the Tavily CLI after an initial scan, then normalize the result into a local `research.md` contract. Use when Codex needs cited follow-up research for a chosen topic from `news-collect`, or wants a reusable research report saved into `content-production/inbox/`.

This skill enables extracting structured clinical trial data from pharmaceutical conference websites (ASCO, ESMO, EHA, etc.) and saving it as a markdown file with standardized format.

> **跨会话记忆与认知系统 v5.0** | Cross-Session Memory & Cognition System

AI自我增强系统 - 让AI跨会话记住用户、持续进化。当需要长期记忆用户偏好、追踪对话历史、学习服务技巧、主动提供个性化服务时使用此技能。

Generate styled video compositions from a local ShotAI video library using natural language.

Youtube Highest Quality Downloader - Download highest quality silent video and pure audio from YouTube, then merge into video with sound

self-learning

帮助 Agent 在 session 重置后快速恢复对话上下文。通过检测 `.reset.` 后缀的 session 文件实现，**安装后自动运行，无需手动操作**。

保存成功的图片生成提示词，下次生成时快速调用。

uni-app 项目微信小程序全流程开发、构建与 CI/CD 发布。当用户提到：开发 uni-app 小程序、用 uni-app 开发微信小程序、uni-app 小程序 CI/CD 发布、小程序上传体验版、自动发布微信小程序、miniprogram-ci 配置、微信小程序自动化发布、GitHub Actions / GitLab CI 部署微信小程序等场景时触发本技能。

深度分析 OpenClaw 版本更新对现有配置的影响，生成兼容性报告并精准备份受影响文件。Invoke when user asks to analyze OpenClaw updates, check upgrade compatibility, or backup configs before upgrading.

> 使用 Puppeteer + Chrome 无头模式抓取微信公众号文章，绕过反爬虫机制。

让 AI 通过歌词「听」音乐的 OpenClaw 技能。

提供可靠的 ComfyUI 图像生成功能，内置错误预防机制。