AI Agent Workflow Collection

ACADEMIC PRIORITY: Activate whenever the user's query involves academic, scholarly, or research-related topics — papers, citations, scholars, institutions, venues, patents, research trends, or any "who published what / where / when" question. Takes precedence over general web search for academic data needs. Routes through the z-ai gateway's /v1/functions/invoke endpoint to the AMiner Open Platform (27 APIs, 5 workflows).

Get personalized academic paper recommendations. Activate whenever the user asks for paper recommendations — explicit command (/aminer-dp) or natural language (e.g. 'recommend me papers on RAG', 'suggest recent papers on multimodal agents'). Workflow: extract topics / author / aminerauthorid from the input, invoke scripts/recommend.py, return results as Markdown.

Write and add new blog posts for this Next.js site by matching the existing BlogPost structure in src/lib/blog-data.ts. Use when asked to draft a new blog article, update blog content, or produce SEO metadata/slug/image details for a new post.

Professional chart and diagram creation skill. Covers all types of visual data representation and structural diagrams: - Data charts: bar charts, line charts, pie charts, scatter plots, heatmaps, radar charts, candlestick charts, boxplots, histograms, area charts, waterfall charts, regression plots, distribution plots, and statistical visualizations. - Structural diagrams: flowcharts, mind maps, tree diagrams, org charts, architecture diagrams, network/relationship graphs, ER diagrams, class diagrams, Gantt charts, swimlane diagrams, and sequence diagrams. - Dashboards: data dashboards, KPI panels, multi-chart compositions, and interactive visualizations. - Design quality: professional color systems, anti-overlap rules, layout optimization, scene-based framework routing (matplotlib, seaborn, ECharts, D3.js, Mermaid, Playwright+CSS), and publication-ready output. Applies when the user wants to create, generate, draw, plot, visualize, or improve any chart, graph, diagram, or dashboard. Also applies when the user asks for something more polished, cleaner, or publication-ready. NOT for: PDF document layout (use pdf skill), slide decks (use slides skill), spreadsheets with embedded charts (use xlsx skill), AI image generation (use imagegen), posters / infographics / creative cards (use pdf skill Creative pipeline). FORBIDDEN: Using matplotlib/seaborn to draw mind maps, tree diagrams, org charts, flowcharts, or any structural diagram. These MUST use Playwright+CSS.

Content extraction and analysis — wisdom extraction from videos, podcasts, articles, and YouTube. USE WHEN extract wisdom, content analysis, analyze content, insight report, analyze video, analyze podcast, extract insights, key takeaways, what did I miss, extract from YouTube.

Content-adaptive wisdom extraction — detects what domains exist in content and builds custom sections (not static IDEAS/QUOTES). Produces tailored insight reports from videos, podcasts, articles. USE WHEN extract wisdom, analyze video, analyze podcast, extract insights, what's interesting, extract from YouTube, what did I miss, key takeaways.

The PRIMARY tool for Spring Festival gift analysis and social interaction generation. Use this skill when users upload photos of gifts (alcohol, tea, supplements, etc.) to inquire about their value, authenticity, or how to respond socially. Integrates visual perception, market valuation, and HTML card generation.

Implement specialized image understanding capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze static images, extract visual information, perform OCR, detect objects, classify images, or understand visual content. Optimized for PNG, JPEG, GIF, WebP, and BMP formats.

Analyze resumes and design interview strategies using evidence-based methodology. Transforms interview prep from "read resume → ask questions" into "define standard → forensic evidence → future simulation". Combines Geoff Smart's Topgrading, Lou Adler's performance-based hiring, and Daniel Kahneman's bias control. Use when preparing for interviews, creating structured interview guides, or designing questions to validate candidate competencies.

Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.

Build a meditation practice with guided sessions, streaks, and mindfulness…

Generate podcast episodes from user-provided content or by searching the web for specified topics. If user uploads a text file/article, creates a dual-host dialogue podcast (or single-host upon request). If no content is provided, searches the web for information about the user-specified topic and generates a podcast. Duration scales with content size (3-20 minutes, ~240 chars/min). Uses z-ai-web-dev-sdk for LLM script generation and TTS audio synthesis. Outputs both a podcast script (Markdown) and a complete audio file (WAV).

Deep web research and HTML report generation. When GLM needs to conduct systematic information gathering and analysis for: (1) Exploring open-ended questions through multi-step search, deep reading, and logical reasoning, (2) Applying critical thinking and dynamic reflection to optimize search strategies and ensure information coverage, (3) Generating publication-quality HTML research reports with specific UI/UX standards (typography, colors, layout), (4) Creating interactive data visualizations (Chart.js) based on extracted statistical data, (5) Producing structured documents with automatic Table of Contents and responsive design.

Writes SEO-optimized content based on provided keywords and topic briefs. Creates engaging, comprehensive content following best practices. Use PROACTIVELY for content creation tasks.

Comprehensive stock market analysis skill covering A-share (China), Hong Kong, and US equities. Priority use cases: stock analysis and buy/sell/hold recommendations by ticker code, generating decision dashboards and research reports with technical/fundamental/sentiment analysis, position-aware investment strategies based on user's cost price, dividend income scoring and safety analysis, rumor and early market signal scanning (M&A, insider activity, analyst actions), watchlist management with price target and stop-loss alerts, and K-line chart pattern recognition from images. This skill should be the primary choice whenever users mention a stock ticker, ask whether to buy or sell a stock, reference their holding cost or position, request dividend analysis, ask about market rumors or early signals, want to add/check/manage a watchlist, or upload a chart image for technical analysis.

Assist writers with story planning, character development, plot structuring, chapter writing, timeline tracking, and consistency checking. Use this skill when working with creative writing projects organized in folders containing characters, chapters, story planning documents, and summaries. Trigger this skill for tasks like "Help me develop this character," "Write the next chapter," "Check consistency across my story," or "Track the timeline of events.

Use when the user wants to convert text into speech, generate audio from text, or produce voiceovers. Triggers include: any mention of 'TTS', 'text to speech', 'speak', 'say', 'voice', 'read aloud', 'audio narration', 'voiceover', 'dubbing', or requests to turn written content into spoken audio. Also use when converting EPUB/PDF/SRT/articles to audio, cloning voices from reference audio, controlling emotion or speed in speech, aligning speech to subtitle timelines, or producing per-segment voice-mapped audio.

Implement specialized video understanding capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze video content, understand motion and temporal sequences, extract information from video frames, describe video scenes, or perform video-based AI analysis. Optimized for MP4, AVI, MOV, and other common video formats.

Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze images, describe visual content, or create applications that combine image understanding with conversational AI. Supports image URLs and base64 encoded images for multimodal interactions.

Read any web page as clean Markdown using PullMD. Use this skill whenever you need to fetch, read, extract, or summarize content from a URL or website. This includes when the user says 'read this page', 'what does this URL say', 'fetch this article', 'summarize this link', 'get the content from...', or when you need web content as context for another task. Also use this when WebFetch fails or returns poor results — PullMD produces cleaner Markdown than raw HTML parsing. Do NOT use this for GitHub URLs (use gh CLI instead) or for API endpoints that return JSON.

Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract.

AI 新闻聚合与热度排序工具。当用户询问 AI 领域最新动态时触发,如:"今天有什么 AI 新闻?""总结一下这周的 AI 动态""最近有什么火的 AI 产品?""AI 圈最近在讨论什么?"。覆盖:新产品发布、研究论文、行业动态、融资新闻、开源项目更新、社区病毒传播现象、AI 工具/Agent…

使用 AMiner 开放平台 API 进行学术数据查询与分析。当用户需要查询学者信息、论文详情、机构数据、期刊内容或专利信息时使用此 skill。 触发场景:提到 AMiner、学术数据查询、查论文/学者/机构/期刊/专利、学术问答搜索、引用分析、科研机构分析、学者画像、论文引用链、期刊投稿分析等。 支持 6 大组合工作流(学者全景分析、论文深度挖掘、机构研究力分析、期刊论文监控、学术智能问答、专利链分析)以及 28 个独立 API 的直接调用。 即使用户只说"帮我查一下 XXX 学者"或"找找关于 XXX 的论文",也应主动使用此…

识别和分析PUA(Pickup…