发现 Skills

Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the user wants diverse viewpoints, needs help making a tough decision, asks for a council/panel/board discussion, wants to explore a problem from multiple angles, requests devil's advocate analysis, or says things like 'what would different experts think about this', 'help me think through this from all sides', 'council mode', 'mind council', or 'deliberate on this'. Also trigger when the user faces a dilemma, trade-off, or complex choice with no obvious answer.

All-in-one web toolkit powered by parallel-cli, with a strong emphasis on academic and scientific sources. Use this skill whenever the user needs to search the web, fetch/extract URL content, enrich data with web-sourced fields, or run deep research reports. Covers: web search (fast lookups, research, current info — prioritizing peer-reviewed papers, preprints, and scholarly databases), URL extraction (fetching pages, articles, academic PDFs), bulk data enrichment (adding fields to CSV/lists from the web), and deep research (exhaustive multi-source reports grounded in academic literature). Also handles setup, status checks, and result retrieval. Use this skill for ANY web-related task — even if the user doesn't mention 'parallel' or 'web' explicitly. If they want to look something up, fetch a page, enrich a dataset, investigate a topic, find academic papers, check citations, or review scientific literature, this is the skill to use.

Produce a .pptx file on disk (headless) instead of driving a live PowerPoint document — for managed-agent sessions with no open Office app.

When the user wants to optimize warehouse slot assignments, improve pick efficiency, or design warehouse layouts. Also use when the user mentions "slotting optimization," "slot assignment," "ABC slotting," "pick path optimization," "storage location assignment," "warehouse layout optimization," or "forward pick locations." For picker routing, see picker-routing-optimization. For warehouse design, see warehouse-design.

Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research

Guidance for building POV-Ray (Persistence of Vision Raytracer) from source, particularly legacy versions like 2.2. This skill should be used when tasked with downloading, compiling, and installing POV-Ray from source archives. It covers handling legacy C code, compressed archive formats, build system navigation, and verification strategies for successful compilation.

This skill provides guidance for implementing custom compression encoders that must be compatible with existing decoders (especially arithmetic coding). It should be used when the task requires writing a compressor/encoder that produces output compatible with a given decompressor/decoder, or when implementing arithmetic coding or similar bit-level compression schemes.

使用本项目MCP 提取 Axure 原型资产、生成主题/数据/文档、还原页面与生成业务文档的流程规范；当用户提供 Axure 原型链接或提出资产提取、原型还原、主题/数据模型/文档生成、交互引导需求时使用。

Create viral content frameworks with platform-specific patterns, psychological hooks, and daily schedules that maximize organic reach without paid promotion.

Process and extract information from PDF documents. Use this skill when the user asks to read, analyze, or extract data from PDF files.

Apply error handling and recovery patterns in JavaScript/TypeScript or Node.js. Use when implementing error handling, retry logic, or when the user mentions domain errors, error recovery, or error escalation.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Process and generate multimedia content using Google Gemini API. Capabilities include analyzing audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understanding images (captioning, object detection, OCR, visual Q&A, segmentation), processing videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extracting from documents (PDF tables, forms, charts, diagrams, multi-page), generating images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.

Use when working in Xu Zilong academic projects with Data/Program/Results/Manuscripts/Submissions and needing stable interfaces between generated results, hand-edited manuscript inserts, and submission artifacts.

Performs firmware image extraction and analysis using binwalk to identify embedded filesystems, compressed archives, bootloaders, kernel images, and cryptographic material. Covers entropy analysis for detecting encrypted or compressed regions, recursive extraction of nested archives, SquashFS/CramFS/JFFS2 filesystem mounting, and string analysis for credential and configuration discovery. Activates for requests involving firmware reverse engineering, IoT device analysis, embedded system security assessment, or router/camera firmware extraction.

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

Use when sending messages to Matrix rooms, interacting with Matrix chat, or automating team notifications via Matrix protocol.

Convert HTML to PowerPoint (PPTX) with excellent Hebrew/RTL support. Use when the user asks to "convert HTML to PowerPoint", "create presentation from HTML", "generate PPTX", "make slides from HTML", or needs to create PowerPoint presentations programmatically.

Run comprehensive validation and review checks including heading numbering, TODO/FIXME comments, Nextflow script conventions, orphaned files, admonition syntax, lesson structure, formatting, content accuracy, and teaching effectiveness. Use when validating, reviewing, or checking training materials quality, lesson quality, or before committing changes.

Analyze China's macroeconomic data, PBOC monetary policy, fiscal policy, and their impact on A-share and Hong Kong stock markets. Track GDP, CPI, PPI, PMI, social financing, and interpret policy signals. Use when the user asks about China's macroeconomy, central bank policy, economic data impact on markets, or needs to understand policy implications for investment.

Best practices and techniques for writing effective AI video-generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, and negative prompts. Use for improving video quality, getting consistent results, and crafting professional video prompts. Triggers: video prompt, how to prompt video, Veo prompts, video generation tips, better AI video, video prompt engineering, video prompt guide, video prompt template, AI video tips, video prompt best practices, video prompt examples, cinematography prompts.

Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code interpreter, file search, web search), integrating MCP servers, managing conversation threads, or implementing streaming responses. Covers function tools, structured outputs, and multi-tool agents.

> Input a room type, style & budget. Get a **complete interior design package** — trending styles researched from Pinterest & Instagram, mood boards generated, full product sourcing list with live ...

> Input any product. Get **fully produced UGC-style video ads** — competitor ads analyzed, winning scripts written, authentic-feeling videos produced with AI voiceover & real-world visuals, and exp...