Media & documents
9,936 rows, by stacks then stars
103 of these skill files have been read, by 99 distinct authors, and what they tell an agent counted. What Media & documents authors agree on, and what they forbid
knownasnaffy/prompthound/dataset/case_03388 Skill
no license0★ repoIntelligent multi-model router — automatically selects the best AI model based on task type (vision, image generation, video generation, audio, reasoning, code, general chat) via any OpenAI-compatible API endpoint. Supports 35+ models across 7 categories with @alias shortcuts. Use when: user sends an image for analysis, requests image/video/audio generation, needs deep reasoning or math proofs, wants to use a specific model, or prefixes message with @alias (e.g. @gpt52, @o3, @sora, @imagen).
knownasnaffy/prompthound/dataset/case_03409 Skill
no license0★ repoOpinionated creative production system for image/video generation, image editing, motion scenes, voiceovers, music, and Remotion assembly. Combines Freepik, fal.ai, Nano Banana 2 (Gemini 3.1 Flash Image Preview), and Remotion workflows for explainers, product marketing videos, social ads, and reusable asset pipelines. Use when users ask to create or edit visual assets, generate clips, produce narration/music, or deliver a polished final video from a brief.
knownasnaffy/prompthound/dataset/case_03422 Skill
no license0★ repoTranscribe audio files to text using OpenAI Whisper. Supports speech-to-text with auto language detection, multiple output formats (txt, srt, vtt, json), batch processing, and model selection (tiny to
knownasnaffy/prompthound/dataset/case_03428 Skill
no license0★ repoTeach composition, lighting, and storytelling for stunning travel shots with AI — generate travel photography videos covering golden hour technique, street photography ethics, landscape composition rules, phone camera mastery, and the visual storytelling that transforms tourist snapshots into portfolio-worthy images. NemoVideo produces travel photography videos where every technique is demonstrated with before-and-after comparisons, every location is scouted for optimal shooting conditions, every camera setting is explained for the specific scene, and the viewer returns from their next trip with photographs worth framing. Travel photography video, travel photo tips, photography tutorial, travel camera, photo composition, landscape photography, street photography, phone photography, golden hour, travel shots.
knownasnaffy/prompthound/dataset/case_03438 Skill
no license0★ repoTranscribe audio files to text using OpenAI Whisper. Supports speech-to-text with auto language detection, multiple output formats (txt, srt, vtt, json), batch processing, and model selection (tiny to large). Use when transcribing audio recordings, podcasts, voice messages, lectures, meetings, or any audio/video file to text. Handles mp3, wav, m4a, ogg, flac, webm, opus, aac formats.
knownasnaffy/prompthound/dataset/case_03443 Skill
no license0★ repoconvert audio or video files into shareable podcast videos with this skill. Works with MP3, MP4, WAV, MOV files up to 500MB. podcasters and content creators use it for converting podcast audio into captioned videos for YouTube or social media — processing takes 1-2 minutes on cloud GPUs and you get 1080p MP4 files.
knownasnaffy/prompthound/dataset/case_03444 Skill
no license0★ repoA comprehensive toolkit for Microsoft Office documents (Word, Excel, PowerPoint) and PDF files. Supports reading, writing, format conversion, and batch processing. Features: - DOCX: Read/write with styles, tables, images - PPTX: Read/write slides, extract text - XLSX: Read/write spreadsheets, formulas - PDF: Read text, create from documents - Convert: DOCX→PDF, PPTX→PDF
knownasnaffy/prompthound/dataset/case_03448 Skill
no license0★ repoUse when the user wants to change a video's aspect ratio or reformat it for a specific platform — e.g. "convert to vertical", "make it 9:16", "crop for TikTok/Reels/Shorts", "resize to square", "convert to landscape", "format for YouTube". Runs locally with ffmpeg, no API key required, no upload needed. For AI-powered smart cropping that intelligently follows subjects (not just center crop), escalate to the built-in AI Edit tool (requires SPARKI_API_KEY).
knownasnaffy/prompthound/dataset/case_03450 Skill
no license0★ repoCaption A/B variant writer for social media. Generate 5 caption variations for any post with different angles, tones, and CTAs — ready to split test across Instagram, LinkedIn, TikTok, and X. Triggers: caption writer, caption variants, A/B caption, social media caption, post caption, caption generator, write caption
knownasnaffy/prompthound/dataset/case_03460 Skill
no license0★ repoGenerate SVG images using text LLM instead of image generation APIs. Use when user wants to create illustrations, icons, cartoons, diagrams, or any visual content without DALL-E/Midjourney/Stable Diffusion. The LLM writes SVG code directly - works great for simple graphics, cartoons, icons, and stylized art.
knownasnaffy/prompthound/dataset/case_03472 Skill
no license0★ repoExtract viral clips from long videos automatically with AI — NemoVideo analyzes podcasts, streams, lectures, interviews, and any long-form content to find the most shareable moments, then produces pol
knownasnaffy/prompthound/dataset/case_03473 Skill
no license0★ repoTranscribe audio via the self-hosted Whisper ASR instance running on Kubernetes. Use this skill whenever the user wants to transcribe audio files, convert speech to text, generate subtitles, or translate audio. Triggers on audio transcription, speech-to-text, whisper, voice-to-text, subtitle generation, or audio translation requests.
knownasnaffy/prompthound/dataset/case_03511 Skill
no license0★ repoLightweight document utility designed to convert files to Markdown (MD), built specifically for intelligent agents (e.g., OpenClaw, ClaudeCode) to read and process content. Requires no external dependencies and accurately preserves document structure and formatting. Supported formats include docx, doc, pdf, ppt, pptx, xls, xlsx, jpg, jpeg, png, ceb, teb, caj, odt, ofd, cebx, odp, ott, wps, ods, et, dps, epub, chm, sdc, sdd, sdw, mobi
knownasnaffy/prompthound/dataset/case_03515/reports Skill
no license0★ repo内容生成子技能,支持 PDF/DOCX/MARKDOWN/PPT/XMIND/PODCAST/VIDEO 七种产出类型的创建、状态查询和进度展示。
knownasnaffy/prompthound/dataset/case_03529 Skill
no license0★ repoTired of scrubbing through video files just to get the audio you actually need? This video-to-audio-converter skill pulls clean audio tracks directly from your video files — no editing software required. Upload mp4, mov, avi, webm, or mkv files and get back high-quality audio in seconds. Perfect for podcasters repurposing recorded sessions, musicians extracting stems, journalists pulling interview audio, or anyone who needs the sound without the screen. Fast, straightforward, and built for real workflows.
knownasnaffy/prompthound/dataset/case_03532 Skill
no license0★ repoView, extract, edit, and manipulate PDF files. Supports text extraction, text editing (overlay and replacement), merging, splitting, rotating pages, and getting PDF metadata. Use when working with PDF documents for reading content, adding/editing text, reorganizing pages, combining files, or extracting information.
knownasnaffy/prompthound/dataset/case_03538 Skill
no license0★ repoFree basic version that converts YouTube transcript into a structured blog draft. Reserves premium upgrade hooks for SEO optimization and multi-platform publishing formats.
knownasnaffy/prompthound/dataset/case_03545 Skill
no license0★ repoGenerate videos from text prompts or reference images using OpenAI Sora. ✅ USE WHEN: - Need AI-generated video from text description - Want image-to-video (animate a still image) - Creating cinematic/artistic video content - Need motion/animation without lip-sync ❌ DON'T USE WHEN: - Need lip-sync (person speaking) → use veed-ugc or ugc-manual - Just need image generation → use nano-banana-pro or morpheus - Editing existing videos → use Remotion - Need UGC-style talking head → use veed-ugc INPUT: Text prompt + optional reference image OUTPUT: MP4 video (various resolutions/durations)
knownasnaffy/prompthound/dataset/case_03577 Skill
no license0★ repoAnalyze video content to extract keyframes, identify themes, and generate representative screenshots with analysis reports. Use when: (1) User sends a video file and asks for analysis, (2) User wants to understand video content without watching, (3) User needs representative screenshots from a video, (4) User asks "what's in this video" or "analyze this video". Supports MP4, MOV, AVI and other common video formats.
knownasnaffy/prompthound/dataset/case_03582 Skill
no license0★ repoSend TTS audio as a proper playable audio message (not file attachment) to Feishu chats. Use when asked to send voice messages, TTS audio, speech announcements, or 语音报数 (voice roll calls) to a Feishu group or user. Activates on requests like "send voice message to Feishu", "TTS to Feishu chat", "语音发送", "语音报数", or any task combining text-to-speech with Feishu messaging.
knownasnaffy/prompthound/dataset/case_03594 Skill
no license0★ repoLocal text-to-speech using Piper voices via sherpa-onnx. 100% offline, no API keys required. Use when user asks for a voice reply, audio response, spoken answer, or wants to hear something read aloud. Supports multiple languages including German (thorsten) and English (ryan) voices. Outputs Telegram-compatible voice notes with [[audio_as_voice]] tag.
knownasnaffy/prompthound/dataset/case_03626 Skill
no license0★ repoUse when OCR-specialized extraction is needed with Alibaba Cloud Model Studio Qwen OCR models (`qwen-vl-ocr`, `qwen-vl-ocr-latest`, and snapshots), including document parsing, table parsing, multilingual OCR, formula recognition, and key information extraction.
knownasnaffy/prompthound/dataset/case_03627 Skill
no license0★ repoPlay scientifically-proven ambient sounds for focus, relaxation, meditation, and sleep. Perfect for programmers, office workers, students, and anyone needing concentration or rest. Use when user wants: white noise, pink noise, brown noise, rain sounds, singing bowl, binaural beats, brain wave tones (alpha/beta/gamma/theta). No copyright issues - all audio is algorithmically generated using ffmpeg.
knownasnaffy/prompthound/dataset/case_03630 Skill
no license0★ repoLocal text-to-speech using Piper for voice message delivery. Use when the user asks for voice responses, audio messages, TTS, text-to-speech, voice notes, or wants to hear something spoken aloud. Converts text to speech locally (no cloud APIs, no cost, no latency) and delivers as voice messages on Telegram, Discord, or any channel supporting audio.
knownasnaffy/prompthound/dataset/case_03645 Skill
no license0★ repoLocal text-to-speech using Piper for voice message delivery. Use when the user asks for voice responses, audio messages, TTS, text-to-speech, voice notes, or wants to hear something spoken aloud. Converts text to speech locally (no cloud APIs, no cost, no latency) and delivers as voice messages on Telegram, Discord, or any channel supporting audio.
knownasnaffy/prompthound/dataset/case_03656 Skill
no license0★ repoAI video editor for creators. Transform raw footage into polished vlogs, talking-head videos, or social media content (TikTok/Shorts/Reels). Control the workflow through chat or fully automate it via ClawBot. From cloning a reference style to natural language editing, simply describe your vision and let Sparki handle the rest.
knownasnaffy/prompthound/dataset/case_03672 Skill
no license0★ repoUse when the user wants to change a video's aspect ratio or reformat it for a specific platform — e.g. "convert to vertical", "make it 9:16", "crop for TikTok/Reels/Shorts", "resize to square", "convert to landscape", "format for YouTube". Runs locally with ffmpeg, no API key required, no upload needed. For AI-powered smart cropping that intelligently follows subjects (not just center crop), escalate to the built-in AI Edit tool (requires SPARKI_API_KEY).
knownasnaffy/prompthound/dataset/case_03706 Skill
no license0★ repoTurn a 45-minute raw podcast recording with two speakers into 1080p polished podcast videos just by typing what you need. Whether it's editing raw podcast recordings into publish-ready video episodes or quick social content, drop your raw podcast footage and describe the result you want. No timeline dragging, no export settings — 1-2 minutes from upload to download.
knownasnaffy/prompthound/dataset/case_03708 Skill
no license0★ repoSplit videos into clips, chapters, and scenes automatically with AI — detect topic changes, scene transitions, silence gaps, and speaker turns to divide any long video into individual segments. NemoVideo analyzes content structure and splits intelligently: podcasts into topic discussions, lectures into lesson modules, meetings into agenda items, streams into game sessions, interviews into Q&A pairs, and tutorials into step-by-step segments. Upload one long video and receive organized individual files. AI video splitter, split video into clips, auto scene detection, video chapter splitter, divide video into parts, clip extractor AI, smart video cutter.
knownasnaffy/prompthound/dataset/case_03721 Skill
no license0★ repoBibiGPT CLI for summarizing videos, audio, and podcasts directly in the terminal. Use when the user wants to summarize a URL (YouTube, Bilibili, podcast, etc.) or check their BibiGPT authentication status. Requires the BibiGPT desktop app installed with an active login session, or a BIBI_API_TOKEN environment variable set.
knownasnaffy/prompthound/dataset/case_03731 Skill
no license0★ repoAI video editor for creators. Transform raw footage into polished vlogs, talking-head videos, or social media content (TikTok/Shorts/Reels). Control the workflow through chat or fully automate it via ClawBot. From cloning a reference style to natural language editing, simply describe your vision and let Sparki handle the rest.
knownasnaffy/prompthound/dataset/case_03736 Skill
no license0★ repoAI-powered video upscaling with Real-ESRGAN and Waifu2x. Use when user asks to enhance, upscale, improve video quality, make HD/4K. Supports anime and real footage with progress tracking.
knownasnaffy/prompthound/dataset/case_03739 Skill
no license0★ repoOverlay text on photos for Instagram posts. Generates portrait (4:5) images with gradient overlays, titles, and optional numbered lists. Use when creating Instagram content that needs text on top of a photo — destination itineraries, top-5 lists, travel highlights, or any branded social image with text overlay.
knownasnaffy/prompthound/dataset/case_03756 Skill
no license0★ repoUse when OCR-specialized extraction is needed with Alibaba Cloud Model Studio Qwen OCR models (`qwen-vl-ocr`, `qwen-vl-ocr-latest`, and snapshots), including document parsing, table parsing, multilingual OCR, formula recognition, and key information extraction.
knownasnaffy/prompthound/dataset/case_03760 Skill
no license0★ repoIntelligent meeting recording and transcription assistant with automated minutes generation, action item extraction, and sentiment analysis. Supports audio transcription, speaker diarization, meeting summarization, and task extraction. Use when users need to record meetings, transcribe audio, generate meeting minutes, extract action items, or analyze meeting content.
knownasnaffy/prompthound/dataset/case_03761 Skill
no license0★ repoTranscribe audio files to text using OpenAI Whisper. Supports speech-to-text with auto language detection, multiple output formats (txt, srt, vtt, json), batch processing, and model selection (tiny to large). Use when transcribing audio recordings, podcasts, voice messages, lectures, meetings, or any audio/video file to text. Handles mp3, wav, m4a, ogg, flac, webm, opus, aac formats.
knownasnaffy/prompthound/dataset/case_03768 Skill
no license0★ repoGet transcripts from any YouTube video — for summarization, research, translation, quoting, or content analysis. Use when the user shares a video link or asks "what did they say", "get the transcript", "transcribe this video", "summarize this video", or wants to analyze spoken content.
knownasnaffy/prompthound/dataset/case_03770 Skill
no license0★ repoTranscribe audio via the self-hosted Whisper ASR instance running on Kubernetes. Use this skill whenever the user wants to transcribe audio files, convert speech to text, generate subtitles, or translate audio. Triggers on audio transcription, speech-to-text, whisper, voice-to-text, subtitle generation, or audio translation requests.
knownasnaffy/prompthound/dataset/case_03792 Skill
no license0★ repoGenerate narration for silent screen-recording videos. Extracts key frames, analyzes on-screen content, writes a presentation-style voiceover script, synthesizes natural-sounding speech with Microsoft Edge neural TTS, and merges the audio onto the original video. Outputs a narrated video and a companion voiceover script.
knownasnaffy/prompthound/dataset/case_03807 Skill
no license0★ repoPublic OpenClaw skill for generating reproducible PPTX decks from project notes, status bullets, and screenshots. Use when the user wants a stakeholder-ready deck from repo notes, release summaries, audit outputs, or screenshot evidence, and the deliverable should be a rebuildable `.pptx` rather than a freeform narrative.
knownasnaffy/prompthound/dataset/case_03821 Skill
no license0★ repoGet edited audio videos ready to post, without touching a single slider. Upload your audio files (MP3, WAV, AAC, M4A, up to 200MB), say something like "trim the silence at the start, boost the volume, and export as a clean audio-backed video", and download 1080p MP4 when it's done. Built for podcasters, musicians, content creators who move fast and want to edit audio and produce a video file without desktop software.
knownasnaffy/prompthound/dataset/case_03822 Skill
no license0★ repoSend and receive voice messages on Feishu (Lark) using ElevenLabs TTS and STT. Activate when user asks to send a voice message on Feishu, or when receiving a Feishu audio message (media attachment with .ogg/.opus file) that needs transcription. Supports smart reply mode — auto voice-reply to voice messages, text-reply to text messages.
knownasnaffy/prompthound/dataset/case_03823 Skill
no license0★ repoSummarize podcast episodes into concise, actionable insights. Use when users want to get the key points from a podcast episode without listening to the entire audio. Supports audio files, URLs, RSS feeds, and podcast platform links.
knownasnaffy/prompthound/dataset/case_03830 Skill
no license0★ repoGenerate a minimalist terrain-style animated driving route video (MP4) from a list of stops (cities/POIs) without Remotion. Uses OSRM for road-following geometry, OpenTopoMap terrain tiles for basemap, Matplotlib for frame rendering, and FFmpeg for encoding. Use when the user asks to create/export a dynamic self-driving route map video (fly-follow camera, route draw animation, labels) and wants it along roads/highways.
knownasnaffy/prompthound/dataset/case_03839 Skill
no license0★ repoGenerate videos from text prompts or reference images using OpenAI Sora. ✅ USE WHEN: - Need AI-generated video from text description - Want image-to-video (animate a still image) - Creating cinematic/artistic video content - Need motion/animation without lip-sync ❌ DON'T USE WHEN: - Need lip-sync (person speaking) → use veed-ugc or ugc-manual - Just need image generation → use nano-banana-pro or morpheus - Editing existing videos → use Remotion - Need UGC-style talking head → use veed-ugc INPUT: Text prompt + optional reference image OUTPUT: MP4 video (various resolutions/durations)
knownasnaffy/prompthound/dataset/case_03842 Skill
no license0★ repoTranscribe audio files to text using OpenAI Whisper. Supports speech-to-text with auto language detection, multiple output formats (txt, srt, vtt, json), batch processing, and model selection (tiny to large). Use when transcribing audio recordings, podcasts, voice messages, lectures, meetings, or any audio/video file to text. Handles mp3, wav, m4a, ogg, flac, webm, opus, aac formats.
knownasnaffy/prompthound/dataset/case_03856 Skill
no license0★ repo从网页抓取结构化数据并填写到任意 Excel 文件的通用技能。 触发场景: - 用户说"帮我把网页上的参数填到 Excel"、"从网站抓数据到表格"、 "网页参数录入 Excel"、"爬取数据并填写 Excel"、或任何类似表达 - 用户提供网址和 Excel 文件,要求自动抓取并填写 - 批量从多个网页抓取数据,填入 Excel 模板 使用时用户会提供:① 目标 Excel 文件路径 ② 目标 Sheet 名称 ③ 填写范围 ④ 数据来源 URL 本技能不硬编码任何具体网址、文件名或字段映射,全部信息由用户在使用时提供。
knownasnaffy/prompthound/dataset/case_03870 Skill
no license0★ repoSend and receive voice messages on Feishu (Lark) using ElevenLabs TTS and STT. Activate when user asks to send a voice message on Feishu, or when receiving a Feishu audio message (media attachment with .ogg/.opus file) that needs transcription. Supports smart reply mode — auto voice-reply to voice messages, text-reply to text messages.
knownasnaffy/prompthound/dataset/case_03872 Skill
no license0★ repoGenerate draw.io diagrams from Mermaid, XML, or CSV code. Use this skill when the user requests any visual diagram including flowcharts, UML diagrams, ERD, architecture diagrams, mind maps, timelines, org charts, network topology, wireframes, BPMN, or any other visual representation. The skill creates a markdown link that opens the diagram in draw.io.
knownasnaffy/prompthound/dataset/case_03889 Skill
no license0★ repoA comprehensive toolkit for Microsoft Office documents (Word, Excel, PowerPoint) and PDF files. Supports reading, writing, format conversion, and batch processing. Features: - DOCX: Read/write with styles, tables, images - PPTX: Read/write slides, extract text - XLSX: Read/write spreadsheets, formulas - PDF: Read text, create from documents - Convert: DOCX→PDF, PPTX→PDF
knownasnaffy/prompthound/dataset/case_03898 Skill
no license0★ repoDescribe your hike and NemoVideo creates the video. Day hike trail guides, multi-day backpacking trip documentation, summit push content, trail condition reports, gear breakdown videos, injury and decision-making content — narrate the trail, the terrain, the weather, the physical challenge, and the views, and get hiking content for the community that plans every trip by watching other people's ... Works by connecting to the NemoVideo AI backend at mega-api-prod.nemovideo.ai. Supports MP4, MOV, AVI, WebM.
knownasnaffy/prompthound/dataset/case_03917 Skill
no license0★ repo深度调研一个主题,生成100页+书籍级PDF手册。模块化HTML片段架构 + 语义化版本管理 + 多Agent并行写作 + Playwright渲染PDF。 当用户需要制作完整的PDF手册、电子书、橙皮书、参考指南时触发。即使用户只是说「做一本书」「做个PDF手册」「做个完整指南」「做一本XX的手册」也应触发。 明确触发词:橙皮书、PDF手册、电子书、参考指南、完整手册、书籍级PDF、做一本。 与huashu-md-to-pdf的区别:md-to-pdf转换单个md文件;本skill从零开始(调研→规划→多agent并行写作→合并构建→版本管理)。
knownasnaffy/prompthound/dataset/case_03918 Skill
no license0★ repoLinkedIn and Instagram carousel script writer. Generate complete slide-by-slide carousel content with hooks, value slides, and CTAs that drive saves and shares. Triggers: carousel, carousel writer, LinkedIn carousel, Instagram carousel, slide deck, carousel script, swipe post, carousel post
knownasnaffy/prompthound/dataset/case_03933 Skill
no license0★ repoPerform bank reconciliation between bank statements and general ledger files. Supports bank statement PDF ingestion, conversion of PDF statements into structured Excel data, custom amount thresholds, ID/key matching, and semantic description matching. Use when the user wants to read a bank statement PDF or Excel file, convert statement activity into a workbook, reconcile bank activity to GL transactions, identify matched and unmatched items, and generate an Excel workbook with reconciliation results, a summary tab, and separate unreconciled-bank and unreconciled-GL tabs.
knownasnaffy/prompthound/dataset/case_03934 Skill
no license0★ repoGenerate animated videos from SVG frames using text LLM. Supports any subject (animals, humans, characters, scenes, abstract art), automatic duration calculation, and multi-scene story animations. Per
knownasnaffy/prompthound/dataset/case_03943 Skill
no license0★ repoWatch and transcribe YouTube videos using yt-dlp and Whisper CLI. Use when Blaze or Kai wants to watch a YouTube video together, get a video transcript, or summarize video content. Downloads audio with yt-dlp, transcribes with Whisper (OpenAI CLI), and saves everything to the workspace organized folder. Supports any YouTube URL. Trigger phrases: "watch this video", "transcribe this", "youtube", "what does this video say", "watch together".
knownasnaffy/prompthound/dataset/case_03949 Skill
no license0★ repoRender TikTok-style animated pill captions onto short-form videos using MoviePy + PIL. Takes a base MP4, a captions JSON, and optional background audio — outputs a final video with fade-in/out pill overlays. Fixes the PIL textbbox y-offset bug that causes text to sit outside pill boundaries. Use for TikTok ads, Reels, YouTube Shorts.
knownasnaffy/prompthound/dataset/case_03955 Skill
no license0★ repoTransform one piece of content into multiple formats for different platforms. Use when: "内容放大", "一鱼多吃", " repurposing content", "content distribution", "多平台分发", "写文章变视频", "博客转社媒", "内容复用", "content multiplier", "社交媒体矩阵", "cross-posting", "multi-channel content". Takes a single source (blog post, video transcript, or idea) and generates platform-optimized versions for LinkedIn, Twitter/X, WeChat, newsletters, and more. Part of UniqueClub founder toolkit. Learn more: https://uniqueclub.ai
knownasnaffy/prompthound/dataset/case_03959 Skill
no license0★ repoSummarize podcast episodes into concise, actionable insights. Use when users want to get the key points from a podcast episode without listening to the entire audio. Supports audio files, URLs, RSS feeds, and podcast platform links.
knownasnaffy/prompthound/dataset/case_03971 Skill
no license0★ repo深度调研一个主题,生成100页+书籍级PDF手册。模块化HTML片段架构 + 语义化版本管理 + 多Agent并行写作 + Playwright渲染PDF。 当用户需要制作完整的PDF手册、电子书、橙皮书、参考指南时触发。即使用户只是说「做一本书」「做个PDF手册」「做个完整指南」「做一本XX的手册」也应触发。 明确触发词:橙皮书、PDF手册、电子书、参考指南、完整手册、书籍级PDF、做一本。 与huashu-md-to-pdf的区别:md-to-pdf转换单个md文件;本skill从零开始(调研→规划→多agent并行写作→合并构建→版本管理)。