agentsclimarketplace

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

  • Frontend slides

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/frontend-slides Skill

    0★ repo

    Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files.

    The same file is in 7 other repositories

  • Game audio

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/game-audio Skill

    0★ repo

    Game audio principles. Sound design, music integration, adaptive audio systems.

    The same file is in 7 other repositories

  • Impress

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/impress Skill

    0★ repo

    Presentation creation, format conversion (ODP/PPTX/PDF), slide automation with LibreOffice Impress.

    The same file is in 7 other repositories

  • Md slides

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/md-slides Skill

    0★ repo

    Converts a markdown deck (slides separated by `---` HR boundaries or by `# ` H1 headings, with optional `<!-- notes: ... -->` presenter notes blocks) into a single-file HTML presentation with arrow-key / space / PgDn / PgUp / Home / End / P / Esc keyboard navigation, presenter mode (split view with current slide + speaker notes + clock + next-slide preview), URL-hash deep linking, and `@media print` page-per-slide for PDF export. Triggers when the markdown-html-orchestrator classifies an input as SLIDES, or when invoked directly via /cs:md-slides. Reuses md-document's markdown parser for slide-body rendering and reads design-system tokens via config_loader.py. Refuses if input has no clear slide boundaries, produces a 1-slide deck, or `--strict-notes` is on with < 50% notes coverage. Use after orchestrator routing.

    The same file is in 2 other repositories

  • Patent

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/patent Skill

    0★ repo

    Patent prior-art and landscape intelligence skill — not generic patent help. Commits to one of five sub-use-cases via forcing intake (novelty search / freedom-to-operate / competitive landscape / acquisition diligence / litigation prior-art) before any search runs. Searches Google Patents, Espacenet, USPTO, and optionally Lens.org for citation-graph signals. Output is an editable Word document (.docx) with verdict, ranked closest art (claim-text extracted), CPC-class-aware landscape, family-resolved hits, geographic coverage, FTO flags where applicable, strategy recommendations, and full audit log. Use when the user asks for patent searching or analysis (e.g., 'prior art search for [invention]', 'freedom to operate analysis for [product]'). Produces search signal, not legal advice — always recommends consulting a patent attorney before filing or licensing decisions. Trademark, copyright, and trade-secret questions are out of scope.

    The same file is in 2 other repositories

  • Senior architect

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/senior-architect Skill

    0★ repo

    This skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design". Use for architecture decision records (ADRs), tech stack evaluation, system design reviews, dependency analysis, and generating architecture diagrams in Mermaid, PlantUML, or ASCII format.

    The same file is in 6 other repositories

  • Social media analyzer

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/social-media-analyzer Skill

    0★ repo

    Social media campaign analysis and performance tracking. Calculates engagement rates, ROI, and benchmarks across platforms. Use when analyzing social media performance, calculating engagement rate, measuring campaign ROI, comparing platform metrics, or benchmarking against industry standards. Also use when the user mentions "social media audit," "engagement rate," or "which platform performs best."

    The same file is in 2 other repositories

  • Writer

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/writer Skill

    0★ repo

    Document creation, format conversion (ODT/DOCX/PDF), mail merge, and automation with LibreOffice Writer.

    The same file is in 5 other repositories

  • Social media manager

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Marketing/social-media-manager Skill

    0★ repo

    When the user wants to develop social media strategy, plan content calendars, manage community engagement, or grow their social presence across platforms. Also use when the user mentions 'social media strategy,' 'social calendar,' 'community management,' 'social media plan,' 'grow followers,' 'engagement rate,' 'social media audit,' or 'which platforms should I use.' For writing individual social posts, see social-content. For analyzing social performance data, see social-media-analyzer.

    The same file is in 2 other repositories

  • Audio transcriber

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Productivity/audio-transcriber Skill

    0★ repo

    Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

    The same file is in 7 other repositories

  • Azure ai transcription py

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Productivity/azure-ai-transcription-py Skill

    0★ repo

    Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization.

    The same file is in 7 other repositories

  • Google slides automation

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Productivity/google-slides-automation Skill

    0★ repo

    Lightweight Google Slides integration with standalone OAuth authentication. No MCP server required. Full read/write access.

    The same file is in 5 other repositories

  • Notebooklm

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Productivity/notebooklm Skill

    0★ repo

    Browser automation skill for controlling Google's NotebookLM. Use when the user wants anything done in NotebookLM (e.g., 'open NotebookLM', 'check my [name] notebook', 'ask my notebook about X', 'add [source] to NotebookLM', 'generate a Video Overview from my notebook', 'use NotebookLM Studio'). Handles reading and querying notebooks, adding sources (URLs, text, files, YouTube links, synthesized content), generating Studio outputs (Audio/Video Overviews, Mind Maps, Reports incl. Briefing Doc/Study Guide/FAQ, Flashcards, Quiz, slide decks, infographics — discover the exact set from the live Studio panel; the UI evolves fast), and creating new notebooks. Requires browser automation environment — fails gracefully when unavailable.

    The same file is in 2 other repositories

  • Grants

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Research/grants Skill

    0★ repo

    NIH grant research skill for clinical researchers. Grill-me intake (research idea + career stage + preliminary data + environment + submission posture + known institute targets) locks down the funding strategy before any search runs. Runs a 5-facet Consensus positioning analysis (with draft Significance/Innovation language), maps the research to the right NIH institutes and study sections via RePORTER, finds NOSIs and funded overlap, and produces an editable Word document (.docx) with budget/scope-aware mechanism recommendations, submission timelines, and a mandatory program officer recommendation. Use when the user asks about research funding or makes any grant-related request (e.g., 'grants for [topic]', 'find grants for my research idea', 'what grants match my research', 'help me find NIH funding', 'grant opportunities for my research'). NIH-only scope — non-NIH funders (PCORI, DOD CDMRP, VA, foundations) are out of scope and flagged at intake.

    The same file is in 2 other repositories

  • Fal audio

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Uncategorized/fal-audio Skill

    0★ repo

    Text-to-speech and speech-to-text using fal.ai audio models

    The same file is in 5 other repositories

  • Azure ai translation document py

    srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Writing & Docs/azure-ai-translation-document-py Skill

    0★ repo

    Azure AI Document Translation SDK for batch translation of documents with format preservation. Use for translating Word, PDF, Excel, PowerPoint, and other document formats at scale.

    The same file is in 5 other repositories

  • Hound web research

    nledford/engineering-review-board/skills/hound-web-research Skill

    0★ repo

    Use the Hound MCP server for public web research, source discovery, URL or PDF retrieval, bounded same-domain crawling, OCR, and evidence capture with smart_search, smart_fetch, smart_crawl, screenshot, cache_clear, or version. Use when current external evidence is needed. Do not use for repository-local facts, structured GitHub platform objects, signed-in browser interaction, checked-in Playwright tests, private or sensitive resources, or Hound installation and upgrades unless explicitly requested.

  • Seedance

    381487190/opengod/skills/seedance Skill

    0★ repo

    This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface - Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seedance route, fal, or third-party provider/router surfaces such as EvoLink, OpenRouter, Kie.ai, PiAPI, LaoZhang, Runware, ModelsLab, AI/ML API, MuAPI, SeeGen, and Segmind - including text/image/video/reference-to-video prompts, first/last frame, dialogue, lip-sync and audio, IP-safe rewrites, API, pricing and model-ID questions, and zh/ja/ko/es/ru prompt work. Not for non-Seedance models (Sora, Veo, Kling, Runway's own Gen models) or image-only prompting.

  • Seedance audio

    381487190/opengod/skills/seedance/seedance-audio Skill

    0★ repo

    This skill should be used when the user asks for Seedance 2.0 audio, dialogue, lip-sync, music, sound effects, ambience, beat-sync, audio-reference mapping, desync troubleshooting, or sound-driven visual timing.

  • Graph writeup

    ternary-ai/skills/skills/basic/graph-writeup Skill

    no license0★ repo

    Create a network diagram (peer relationships, business model, news sources) and embed it in the Thesis as a Mermaid graph block. Use when the user asks for a relationship map, peer network, business model diagram, or knowledge graph. For price/performance charts use the chart-writeup skill instead.

  • Socialseal reference video analysis

    OpenSealAI/agent-skills/skills/socialseal-reference-video-analysis Skill

    no license0★ repo

    Use this skill when identifying and analyzing the reference videos that already surface for tracked searches: finding exemplars by scope or semantic prompt, previewing promoted candidates, and extracting Video DNA (hook, structure, shots, production qualities) to ground a blueprint. This is the evidence stage before blueprints and briefs.

  • Socialseal video concepting

    OpenSealAI/agent-skills/skills/socialseal-video-concepting Skill

    no license0★ repo

    Use this skill when turning a SocialSeal opportunity or keyword gap into short-form video concept routes that feed the blueprint engine. Produces concepts with viewer job, lens, hook and first-frame ideas, arcs, and the scope or retrievalPrompt to drive socialseal-blueprint-builder, plus a measurement intent.

  • Whatsteam messaging

    whatsteamhq/whatsapp-claude-skills/skills/whatsteam-messaging Skill

    0★ repo

    Send WhatsApp messages with WhatsTeam on the official WhatsApp Business API — text, images, video, audio, documents, locations, contact cards, polls, scheduled, and agent-attributed messages. Use when the user wants to send any kind of message via WhatsApp through their connected WABA device. Bakes in the 24-hour customer service window and the pre-approved template flow so the agent picks free-form vs template automatically.

  • Surface witness

    knowledgeco/airworthiness/skills/surface-witness Skill

    0★ repo

    Independently audit an implemented product surface against its declared constitution, state manifest, genealogy, responsive claims, and acceptance criteria. Use after a major interface milestone, design-system extraction, component-library migration, broad AI-generated UI work, before release, or whenever a product appears to be converging on generic AI or library defaults. Inspect rendered or executable artifacts before maker explanations; run logo-swap, monochrome, thumbnail, library-residue, mobile-mutation, copy-substitution, state, exception, and distinctiveness-budget tests; separate machine evidence from perceptual judgment; attempt to refute findings; disclose witness independence; and leave beauty, distinctiveness, brand, and ship verdicts pending for the operator rather than fabricating them.

  • Ecc frontend slides

    Pdbjork/hermosskills-site/skills/ecc-frontend-slides Skill

    no license0★ repo

    Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

    The same file is in 1 other repository

  • Ecc video editing

    Pdbjork/hermosskills-site/skills/ecc-video-editing Skill

    no license0★ repo

    AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

    The same file is in 1 other repository

  • Brand logo kit

    puntorigen/skills/brand-logo-kit Skill

    no license0★ repo

    Generate a brand logo and a matching, brand-consistent set of visual assets - logo marks, wordmark lockups, monograms, app icons, favicons, social avatars, banners, seamless patterns, spot illustrations, and UI icons. Local-first: it prefers on-device generation via the image-gen skill (FLUX.2 Klein on Apple Silicon) and only falls back to a CLOUD image API (Google Gemini / Nano Banana Pro, or OpenRouter) when local can't run - no API key is bundled, it is auto-discovered from your environment or another installed skill and cached outside the repo. Crisp on-brand text is set from real fonts with wordmark.py (no misspelled diffusion text), `--look` presets steer the visual finish, and a set is kept cohesive via a shared palette and, on the cloud path, the chosen logo as a reference. Use when the user asks to create a logo, brand identity, brand kit, visual identity, brand style, wordmark, app icon, favicon, or a consistent set of on-brand graphics/assets.

  • Edit docx

    puntorigen/skills/edit-docx Skill

    no license0★ repo

    Inspect and edit Microsoft Word .docx files while preserving formatting, styles, and layout - 100% locally with python-docx, no cloud or API keys. A small CLI (docx_tool.py) lists every document element with a stable index (paragraphs, tables, images, headers/footers), then applies surgical edits: run-aware find/replace that keeps bold/italic/font/color even across split runs, insert paragraphs with a chosen style, edit or append table cells, add table rows copying the previous row's formatting, delete elements, and list available styles. Use when the user wants to read, inspect, edit, modify, update, or fill in a Word document or .docx file; do find-and-replace in a .docx while keeping formatting; change or add table rows/cells; insert headings or paragraphs; work with headers/footers; or template a report, contract, or letter - without opening Word.

  • Image gen

    puntorigen/skills/image-gen Skill

    no license0★ repo

    Generate hyper-realistic, high-quality images from a text prompt at any resolution, 100% locally with no cloud or API keys. Uses mflux (native MLX on Apple Silicon) to run Z-Image-Turbo (default) or FLUX.2-klein-4B - both Apache-2.0, commercial-safe - and can upscale results to hi-res with SeedVR2. A local, scriptable alternative to Draw Things / Midjourney / DALL-E. Use when the user asks to generate or create an image, photo, or illustration from a prompt; wants photorealistic / hyper-realistic renders; needs a specific resolution or aspect ratio; mentions Z-Image, FLUX, Stable Diffusion, or local text-to-image; or wants imagery for a reel, thumbnail, hero shot, or mockup.

  • Object to 3d

    puntorigen/skills/object-to-3d Skill

    no license0★ repo

    Turn an mp4 video of a single object (orbited 360°) into both a clean, browser-navigable 3D Gaussian splat and a watertight, 3D-printable STL/GLB mesh - 100% locally on Apple Silicon, no cloud or API keys. Shares the video-to-splat pipeline (frame extraction with ffmpeg, camera-pose Structure-from-Motion with pycolmap, Gaussian-splat training with Brush on Metal/WebGPU) and adds two object-specific stages: automatic splat cleanup (isolate the object from background, support surface and floaters via opacity/scale filtering, RANSAC plane removal and DBSCAN clustering) and mesh extraction (Poisson reconstruction to a watertight, millimeter-scaled STL for slicers plus a colored GLB for web/QuickLook). Use when the user wants to scan / photogrammetry / 3D-capture a physical object from a video and get a printable 3D model or a cleaned object splat, mentions turning a video into an STL / 3D print / GLB / mesh, "object to 3D", "video to STL", or cleaning a Gaussian splat of an object.

  • Pdf documents

    puntorigen/skills/pdf-documents Skill

    no license0★ repo

    Read and create PDF documents entirely on-device - no cloud, no API keys. For reading, uses Docling (IBM's document AI) to turn a PDF into structured JSON, Markdown, text, or HTML with real layout understanding: extracted tables (as headers/rows + HTML), section/heading hierarchy, page images, and optional OCR for scanned pages (native macOS Vision OCR). For writing, uses fpdf2 to render a professional, multi-page PDF from a simple JSON config - titles, headings, justified paragraphs, styled tables with alternating rows, images with captions, bullet/numbered lists, key-value KPI blocks, dividers, headers and footers with page numbers. Use when the user wants to read, parse, extract, or inspect a PDF (text, tables, or structure), scrape data out of a PDF, OCR a scanned PDF, or generate/create a polished PDF report, invoice, proposal, or data sheet from data.

  • Talking head

    puntorigen/skills/talking-head Skill

    no license0★ repo

    Turn a single avatar/portrait image plus a narration audio file into a lip-synced talking-head MP4, 100% locally with no cloud or API keys. Uses JoyVASA (audio-driven facial-motion diffusion) rendered with LivePortrait, running natively on Apple Silicon (MPS). Works end to end with the other skills: generate the avatar from a description with image-gen and the English/Spanish narration from text with voice-clone-narration, then animate here. Use when the user asks for a talking head, talking avatar, lip-sync video, an avatar that speaks, a spokesperson/presenter clip, or to make a portrait/photo talk or say something from audio or a script.

  • Video to splat

    puntorigen/skills/video-to-splat Skill

    no license0★ repo

    Turn an mp4 video tour into a 3D Gaussian splat (3DGS) point cloud you can view in the browser, 100% locally on Apple Silicon with no cloud or API keys. Runs the full photogrammetry pipeline - frame extraction (ffmpeg), camera-pose Structure-from-Motion (pycolmap), and Gaussian-splat training (Brush, native Metal via WebGPU) - then compresses the result to web-friendly .sog/.spz with PlayCanvas splat-transform and previews it in a bundled Aholo viewer. Output is compatible with the Aholo viewer (aholojs.dev) and any 3DGS viewer that reads PLY/SPZ/SOG. Use when the user wants to convert a video / room tour / walkthrough / drone flythrough into a gaussian splat or 3DGS scene, mentions aholo, splats, radiance fields, photogrammetry from video, or a "3D capture" from footage.

  • Voice clone narration

    puntorigen/skills/voice-clone-narration Skill

    no license0★ repo

    Clone a voice from a short reference sample - or design a brand-new voice from a text description - and generate expressive MP3 narrations 100% locally (no cloud, no API keys), in English or Spanish, with inflection controls. Uses Chatterbox TTS (MIT) for zero-shot cloning via mlx-audio on Apple Silicon (with a PyTorch fallback elsewhere) and Qwen3-TTS VoiceDesign (Apache-2.0) to invent a voice from a description. Long scripts are sentence-chunked with a consistent voice and encoded to a single MP3. Use when the user asks to clone a voice, make a voiceover/narration/VO for a reel or demo video, do local text-to-speech, turn a script into an mp3, generate a synthetic voice from a description, or say something "in my voice".

  • Obsidian excalidraw

    kev-hu/ai-toolkit/skills/obsidian-excalidraw Skill

    0★ repo

    Draw and modify Excalidraw diagrams inside an open Obsidian vault by creating elements via the ExcalidrawAutomate API and invoking Downloaded scripts. Use when the user wants to create diagrams, concept graphics, mindmaps, sketches, visual metaphors, or annotate existing Excalidraw drawings through conversation — especially for YouTube AI-education visuals. Triggers on "draw", "diagram", "sketch", "visualize", "graphic", "metaphor", "mindmap", "concept art", or modifying an open `.excalidraw` file.

  • Dependency hygiene

    jcdavis131/cursor-agent-skills/skills/dependency-hygiene Skill

    0★ repo

    Keep heavy, pin-pulling adapters out of a project's universal lockfile by declaring them as opt-in extras installed only where needed. Use when adding a dependency with heavy or conflicting transitive pins (LLM libs, PDF/OCR libs, ML frameworks), when a shared environment must stay coherent for training/inference, or when an adapter is only needed by one workspace.

  • Ads photoshoot

    incuca/incuca-ads/skills/ads-photoshoot Skill

    0★ repo

    Product photography enhancement for ad creatives using banana-claude image generation. Takes a product image and generates 5 professional photography styles for ad use: Studio, Floating, Ingredient, In Use, and Lifestyle. Requires banana-claude (v1.4.1+) with nanobanana-mcp. Triggers on: product photo, product photography, photoshoot, enhance product image, product shoot, product photos for ads, generate product photos, studio shot, lifestyle photo.

  • Vectojs video exporter

    vectojs/vectojs-skills/skills/vectojs-video-exporter Skill

    0★ repo

    Use when exporting VectoJS scenes to H.264 MP4 with @vectojs/video-exporter, CLI/API capture, fixed-step scene contracts, Chromium, FFmpeg, cancellation, cleanup, or deterministic animation rendering.

  • Diagrams

    SamyakJhaveri/loam/seed/.claude/skills/diagrams Skill

    0★ repo

    Generate diagrams and visuals from code or descriptions. Use when the user needs a rendered diagram, code visualization, or architecture image. Subcommands — excalidraw (hand-drawn), drawio (formal XML), paper (academic illustrations), gitdiagram (repo architecture), yoshida (atmospheric Hiroshi Yoshida woodblock hero art).

  • Linkedin carousel outline

    liftli-ai/skills/skills/linkedin-carousel-outline Skill

    0★ repo

    Use when the user wants a LinkedIn carousel, document post, or slide deck outline — produces an 8-10 slide outline with one idea per slide under 25 words, from cover hook to soft CTA, ready to design.

  • Images media

    Syo-M/codex-frontend-skills/.agents/skills/images-media Skill

    0★ repo

    Images, SVG, icons, fonts, video, favicons, responsive delivery, lazy loading, and LCP or CLS optimization. 日本語の依頼例:「画像最適化」「フォント読み込み」「動画埋め込み」「LCP改善」「ファビコン」。

  • Images media

    Syo-M/codex-frontend-skills/plugins/codex-frontend-skills/skills/images-media Skill

    0★ repo

    Images, SVG, icons, fonts, video, favicons, responsive delivery, lazy loading, and LCP or CLS optimization. 日本語の依頼例:「画像最適化」「フォント読み込み」「動画埋め込み」「LCP改善」「ファビコン」。

  • Stirling pdf

    msageha/skills/stirling-pdf Skill

    0★ repo

    Stirling PDF document processing. Use when: user asks to convert, merge, split, compress, OCR, or manipulate PDF files. Also for converting between PDF and Markdown/images/Word/HTML. Useful alongside Obsidian for PDF-to-Markdown conversion.

  • Audio tts

    bman654/audio-forge/skills/audio-tts Skill

    0★ repo

    Generate speech locally by cloning a voice from a short reference sample — chunked, sentence-aware, voice-cloned text-to-speech that writes WAV or MP3, with optional word-level and expression-cue timestamps (forced alignment). Runs fully on-device on Apple Silicon over the mlx-speech fish-s2-pro model (no cloud, no API key). Use when the user asks to: narrate text, read something aloud, generate a voiceover / VO, synthesize speech, clone a voice, make a character say lines, produce narration for a video or scene, or get word timings / subtitles / karaoke-style timestamps for synthesized audio. Trigger keywords: tts, text to speech, text-to-speech, voiceover, voice over, narration, narrate, read aloud, speak, synthesize speech, voice clone, voice cloning, clone my voice, character voice, word timestamps, forced alignment, subtitles from audio, fish-speech, fish-s2-pro.

  • Case 00001

    knownasnaffy/prompthound/dataset/case_00001 Skill

    no license0★ repo

    Install and operate local NVIDIA Parakeet ASR for OpenClaw with an OpenAI-compatible transcription API on Ubuntu/Linux and macOS (Intel/Apple Silicon). Use when the user wants private/local speech-to-text, voice transcription setup, ASR troubleshooting, or OpenClaw voice stack configuration with Parakeet (and optional Whisper fallback).

  • Case 00008

    knownasnaffy/prompthound/dataset/case_00008 Skill

    no license0★ repo

    Use when the user wants to transcribe, caption, or get the text content of a video or audio file — e.g. "transcribe this video", "get the transcript", "what did they say", "generate subtitles", "extract captions", "convert speech to text". Runs locally with Whisper, no API key required. Supports 50+ languages with auto-detection. Outputs both plain text transcript and SRT subtitle file. For AI-powered video editing that uses the transcript (highlights, montage, commentary), escalate to the built-in AI Edit tool (requires SPARKI_API_KEY).

  • Case 00011

    knownasnaffy/prompthound/dataset/case_00011 Skill

    no license0★ repo

    General-purpose offline OCR and post-processing for Chinese/English screenshots, scanned images, receipts, tables, chat screenshots, statement screenshots, and other text-heavy images. Use when you need to: (1) extract text from an image locally, (2) return raw OCR text before interpretation, (3) clean broken OCR lines into structured content, (4) reorganize recognized text into rows/fields for downstream use, or (5) separate recognition from later table entry, summarization, or document drafting.

  • Case 00013

    knownasnaffy/prompthound/dataset/case_00013 Skill

    no license0★ repo

    Convert documents between formats using Pandoc CLI (Markdown, DOCX, PDF, HTML, EPUB, PPTX, ODT, RTF, LaTeX, CSV/TSV, Jupyter, etc.). Use when: (1) converting file formats, (2) generating DOCX/PDF from Markdown, (3) creating slide decks (PPTX/Beamer/Reveal.js), (4) extracting text from DOCX/EPUB/ODT, (5) producing EPUBs, (6) any Pandoc conversion task.

  • Case 00081

    knownasnaffy/prompthound/dataset/case_00081 Skill

    no license0★ repo

    Generate TikTok-style short-form ad videos with animated pill captions. Takes a base MP4 (Veo/Runway/Kling), overlays animated captions with fade in/out, mixes background audio. Built-in product presets — no captions JSON file needed. Use for TikTok ads, Reels, YouTube Shorts product videos.

  • Case 00112

    knownasnaffy/prompthound/dataset/case_00112 Skill

    no license0★ repo

    Convert documents between formats using Pandoc CLI (Markdown, DOCX, PDF, HTML, EPUB, PPTX, ODT, RTF, LaTeX, CSV/TSV, Jupyter, etc.). Use when: (1) converting file formats, (2) generating DOCX/PDF from Markdown, (3) creating slide decks (PPTX/Beamer/Reveal.js), (4) extracting text from DOCX/EPUB/ODT, (5) producing EPUBs, (6) any Pandoc conversion task.

  • Case 00125

    knownasnaffy/prompthound/dataset/case_00125 Skill

    no license0★ repo

    Extract speech-to-text from Douyin (TikTok China) videos, get watermark-free download links, and download videos. Use when user shares a Douyin link, asks to transcribe a Douyin video, wants to download a Douyin video without watermark, or needs to extract text from Chinese short videos.

  • Case 00147

    knownasnaffy/prompthound/dataset/case_00147 Skill

    no license0★ repo

    Generate videos using Alibaba Cloud DashScope Wan (通义万相) text-to-video (t2v) API (e.g., wan2.6-t2v). Use when the user asks to create a short video from a text prompt via 百炼/通义万相/wan 文生视频, and wants the agent to submit an async task, poll status, and download the mp4 locally (e.g., to Windows Desktop from WSL2).

  • Case 00165

    knownasnaffy/prompthound/dataset/case_00165 Skill

    no license0★ repo

    Use when designing custom voices with Alibaba Cloud Model Studio CosyVoice customization models, especially cosyvoice-v3.5-plus or cosyvoice-v3.5-flash, from a voice prompt plus preview text before using the returned voice_id in TTS.

  • Case 00174

    knownasnaffy/prompthound/dataset/case_00174 Skill

    no license0★ repo

    Transcribe 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.

  • Case 00177

    knownasnaffy/prompthound/dataset/case_00177 Skill

    no license0★ repo

    Create SVG images and convert them to PNG without external graphics libraries. Use when you need to generate custom illustrations, avatars, or artwork (e.g., "draw a dragon", "create an avatar", "make a logo") or convert SVG files to PNG format. This skill works by writing SVG text directly (no PIL/ImageMagick required) and uses system rsvg-convert for PNG conversion.

  • Case 00183

    knownasnaffy/prompthound/dataset/case_00183 Skill

    no license0★ repo

    Local 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.

  • Case 00187

    knownasnaffy/prompthound/dataset/case_00187 Skill

    no license0★ repo

    Call EngageLab WhatsApp Business REST APIs to send WhatsApp messages (template, text, image, video, audio, document, sticker), manage WABA message templates, and handle callback webhooks for delivery status and user responses. Use this skill whenever the user wants to send WhatsApp messages via EngageLab, create or manage WhatsApp templates, configure WhatsApp callbacks, or integrate with the EngageLab WhatsApp Business platform. Also trigger when the user mentions "engagelab whatsapp", "whatsapp business api", "whatsapp api", "send whatsapp message", "whatsapp template", "waba", "whatsapp notification", "whatsapp marketing", or asks to integrate WhatsApp messaging into their application. This skill covers authentication, all message types, template CRUD, and callback handling — use it even if the user only needs one of these capabilities.

  • Case 00196

    knownasnaffy/prompthound/dataset/case_00196 Skill

    no license0★ repo

    Convert an HTML file to a PDF using headless Chrome (Puppeteer) — the same approach atypica uses for its AI-generated research reports. Use this skill whenever the user wants to export an HTML file, report, or webpage snapshot to PDF. Trigger on phrases like "convert to PDF", "export as PDF", "save report as PDF", "html to pdf", "generate PDF from HTML", or when a user hands you an .html file and asks for a downloadable document. Even if the user just says "make a PDF of this", use this skill if the source is HTML.

  • Case 00197

    knownasnaffy/prompthound/dataset/case_00197 Skill

    no license0★ repo

    创建、编辑或分析 .xlsx / .xlsm / .csv / .tsv 文件。当用户要求生成、处理、下载 Excel 表格,或提及表格文件名/路径并希望对其操作时,使用本技能。包括:打开、读取、编辑、修复已有文件(增列、计算、格式化、图表、数据清洗),从零或其他数据源创建新表格,以及表格格式间的转换。对于结构混乱的表格数据(错行、表头错位、垃圾数据)清洗为规范表格也适用。交付物须为表格文件;当用户未指定格式时默认生成 .xlsx 而非 .csv 等其他格式。若主要产出为 Word 文档、HTML 报告、独立 Python 脚本或数据库管道,则不应触发本技能。

  • Case 00200

    knownasnaffy/prompthound/dataset/case_00200 Skill

    no license0★ repo

    Get podcast video files ready to post, without touching a single slider. Upload your audio or video files (MP3, MP4, WAV, MOV, up to 500MB), say something like "turn my podcast audio into a video with captions and a waveform visual", and download 1080p MP4 when it's done. Built for podcasters who move fast and want to publish podcasts on YouTube or social media without a complex video editor.