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
slalomboy/talking-head-video-suite/skills/talking-head-video-production Skill
0★ repoUse when creating, rewriting, filming, editing, packaging, or publishing-preparing a Chinese talking-head video from a purpose, promoted offer, existing draft, or sourced knowledge.
aoli0919/visual-thinking-skills/skills/diagram-brief Skill
0★ repoWrite a brief for a diagram that explains a concept, system, or workflow.
ahtishamshahzad/agent_dev_flow/.ai/skills/mobile/mobile-camera-media Skill
0★ repoUse to plan camera and media capture — permissions, capture/pick flows, image/video handling, and resizing/compression before upload. Requires native support (dev build or CLI).
kody-w/rapp-skills/msft-deck Skill
0★ repoBuild, restyle, or revise a PowerPoint deck in Kody's Microsoft styling, self-review every slide visually, and only hand it over verified and popped open. Use whenever the user asks for a deck, slides, a pptx, a one-pager deck, to "restyle" a deck, to make slides "look like the STYLED one" / "not look vibe coded", or to turn notes/a transcript/an md into a presentation.
kody-w/rapp-skills/transcript-miner Skill
0★ repoMine Claude Code session history for usage patterns, mistakes, and automation candidates. Use when Kody says "audit my sessions", "what am I doing wrong in Claude Code", "usage audit", "mine my transcripts", "analyze my Claude Code history", "what should be a skill", or asks how he's using Claude Code across past sessions. Extracts tool stats, error signatures, Read:Edit ratios, my-message categories (corrections/rejections), and permission denials from ~/.claude/projects JSONL — with evidence, never vibes.
syncfusion/aspnetmvc-ui-components-skills/skills/syncfusion-aspnetmvc-diagram Skill
no license0★ repoUse this skill whenever the user asks to create, configure, customize, or troubleshoot interactive diagrams using the Syncfusion ASP.NET MVC Diagram component with EJ2 Tag Helpers. Trigger this skill for requests involving flowcharts, organizational charts, BPMN diagrams, UML diagrams, swimlane diagrams, or mind maps, including node and connector definitions, shapes, styles, layouts, data binding, drawing tools, serialization, export, or advanced customization in ASP.NET MVC applications.
Syncfusion aspnetmvc speech to text
syncfusion/aspnetmvc-ui-components-skills/skills/syncfusion-aspnetmvc-speech-to-text Skill
no license0★ repoImplement Syncfusion Speech To Text control in ASP.NET MVC applications using HTML Helpers. ALWAYS use this skill when the user needs ASP.NET MVC speech recognition, voice input, Web Speech API integration, speech-to-text transcription, or help with the Speech To Text control (@Html.EJS().SpeechToText()). Covers installation, HTML helper setup, speech recognition, customization, events, error handling, and accessibility patterns specific to ASP.NET MVC.
syncfusion/aspnetmvc-ui-components-skills/skills/syncfusion-aspnetmvc-treegrid Skill
no license0★ repoImplements Syncfusion EJ2 ASP.NET MVC TreeGrid component for hierarchical data with editable parent–child tables. Use for nested datasets with sorting, filtering, paging, or Excel/PDF export. Covers data binding, templates, virtual scrolling, editing, selection, aggregates, and state persistence to deliver high‑performance tabular operations.
wangyu16/orz-claude-plugin/skills/orz-slides Skill
no license0★ repoAuthor and edit single-file, self-editing .slides.html presentation decks (orz-slides). Use when a user wants to turn notes or markdown into a browser-based slide deck — one portable HTML file that presents in any browser (reveal.js), is written in orz-markdown with a layout syntax, and can be edited in-browser. Covers the deck source format, slide/layout/region markers, structure templates, and per-slide capacity budgets so slides do not overflow.
The same file is in 1 other repository
YosukeIida/personal-agent-skills/grant-figure-assets Skill
no license0★ repoCreate reusable monochrome figure assets for Japanese academic grant proposals such as JSPS DC1. Use when Codex needs to generate an overview/reference figure or icon set with imagegen, save raw PNGs, tight-crop them by bounding box, make contact sheets, or prepare black-and-white assets for HTML/CSS/SVG reconstruction of proposal figures.
arkaigrowth/agent-skills/signal-shadow Skill
0★ repoNuance-preserving summarization. Compresses text while preserving the caveats, disagreement, chronology, dependencies, and uncertainty that determine how a careful reader should interpret the source. Closes with a residual-risk audit (largest inference, strongest omission risk, weakest-confidence claim) instead of checkbox rubric theater. Use when user says: "signal shadow", "signal+shadow", "nuance-preserving summary", "compress without flattening", "summarize this with caveats", "what's easy to miss", or when summarizing long-form content where meaning-changing nuance matters (academic papers, podcast/video/interview transcripts, news articles, social threads, technical docs, meeting minutes, long emails). Accepts: URL, file path, or piped/pasted text (plus an optional external transcript-CLI mode, see below). Adapts emphasis by source type (academic | transcript | news | thread | technical | general). Density dial 1-4 controls compression aggressiveness; default is 2. Output scales to the source and never pads to fill the density.
arkaigrowth/agent-skills/video-download Skill
0★ repoDownload videos and audio from 1000+ platforms (YouTube, Vimeo, etc.) with quality selection, caption extraction, playlist support, and macOS Finder tagging. Use when the user needs to download videos from URLs (including unlisted/private links), extract audio-only from videos, download captions/transcripts without full video, batch download playlists with filtering, get pre-download size/duration estimates, or perform any video acquisition task ahead of downstream analysis.
wu1chenghui/hermes-math-template/skills/document-parser Skill
no license0★ repoParse any document (PDF, DOCX, PPTX, XLSX, PNG, JPG, HTML, web pages) into LLM-readable Markdown via MinerU. Use when the user asks to read, analyze, extract, or convert content from a document — regardless of format. Supports 80+ languages, table/formula/OCR recognition.
idylle-cynique/solo-dev-skills/skills/design-diagram Skill
0★ repo対象コード・処理を分析し、要求に応じてフローチャート・シーケンス図・データフロー図・ ER図などをMermaidダイアグラムとしてドキュメント化するスキル。「フローチャートを書いて」 「シーケンス図で図解して」「ER図がほしい」など図解を依頼されたとき、またはコードを 見る前に処理を整理したいと言われたときは明示されていなくても積極的にこのスキルを 参照すること。呼び出しをまたいで状態が変化する処理の状態遷移図・テストケース導出は design-state-tests を使う。
hyuga611/skills-lint/examples/good/pdf-reader Skill
0★ repoPDFファイルからテキストや表を抽出して要約する。レシート・請求書・論文などの読み取りに使う。
hyuga611/skills-lint/examples/good/xlsx-builder Skill
0★ repoExcel/スプレッドシートを新規作成し、数式・グラフ・整形を行う。売上表や集計シートの作成に使う。
Paldom/terminaltor/skills/cast-render Skill
0★ repoRenders asciicast .cast recordings into themed GIFs and MP4s with agg, gifsicle, and ffmpeg - trimming, speed and idle control, brand or neutral themes, size budgets, README embedding. Use when the user asks to convert, render, trim, speed up, optimize, or embed an existing terminal recording. Not for creating demos from scratch, capturing sessions, or general video files like screen recordings.
arclabshq/arc-labs-studio-team/skills/video-producer Skill
0★ repoPlans credible video from concept through script, shot list, asset inventory, edit structure, and delivery checks. Use for founder videos, demos, explainers, interviews, social clips, or production handoffs.
prateek11rai/tldraw-canvas-kit/skills/canvas-export Skill
0★ repoExport the open tldraw offline canvas — the whole page, a selection, or specific frames/slides — to shareable image or vector files (PNG/SVG, and PDF where supported) written next to the .tldraw file. Use when the user wants to share, embed, or publish a diagram, deck, or whitepaper outside tldraw, or asks to "export", "save as PNG/SVG/PDF", or "get an image of this". Produces consistent export naming and location every run.
prateek11rai/tldraw-canvas-kit/skills/class-diagram Skill
0★ repoDraw a UML class diagram in the open tldraw offline canvas — classes with attribute and operation compartments, interfaces, inheritance, realization, associations with multiplicity, aggregation and composition. Use when the user asks for a class diagram, an object model, a domain model, type/class relationships, or "how do these classes relate". Produces the same class-card layout and relationship notation every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
prateek11rai/tldraw-canvas-kit/skills/codebase-map Skill
0★ repoReverse-engineer a codebase into a consistent architecture map on the open tldraw offline canvas — modules/packages as nodes, import/dependency relationships as bound edges, grouped by layer or package, with key entry points and data flow highlighted. Use when a coder or engineering architect wants to visualize how a repo is structured, see module dependencies, onboard onto an unfamiliar codebase, or produce a "how this code fits together" diagram. Produces the same mapping conventions every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
prateek11rai/tldraw-canvas-kit/skills/component-diagram Skill
0★ repoDraw a UML component diagram in the open tldraw offline canvas — «component» boxes wired by provided/required interfaces (simplified labeled connectors or explicit lollipop notation), dependencies, and subsystem groupings. Use when the user asks for a component diagram, module/interface wiring, or "what talks to what over which interface" (for infra/deployment topology use deployment-diagram; for C4-style system layers use architecture-diagram). Produces the same layered wiring layout every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
prateek11rai/tldraw-canvas-kit/skills/deployment-diagram Skill
0★ repoDraw an infrastructure / deployment / network topology diagram in the open tldraw offline canvas — nodes, clusters, regions, and networks shown as boundary zones with the components deployed inside them, connected by bound links. Use when the user asks for a deployment diagram, infrastructure/network topology, a cloud architecture layout, or "where does this run". Produces the same zone-and-node layout every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
prateek11rai/tldraw-canvas-kit/skills/er-diagram Skill
0★ repoDraw an entity-relationship / data-model diagram in the open tldraw offline canvas — entities with their key attributes, connected by relationship edges with cardinality. Use when the user asks for an ER diagram, a data model, a database schema diagram, or to show how tables/entities relate. Produces the same entity-card layout and cardinality notation every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
prateek11rai/tldraw-canvas-kit/skills/flowchart Skill
0★ repoDraw a process or decision flowchart in the open tldraw offline canvas — start/end terminals, process steps, and decision branches connected with bound arrows. Use when the user asks for a flowchart, a process flow, a decision tree, or an algorithm/workflow diagram. Produces the same top-to-bottom layout and shape vocabulary every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
prateek11rai/tldraw-canvas-kit/skills/mindmap Skill
0★ repoDraw a mind map / concept-breakdown map in the open tldraw offline canvas — a central topic with branches radiating out to sub-topics and leaves, connected by bound links. Use when the user asks for a mind map, a concept map, a breakdown/decomposition of a topic, or to brainstorm structure around an idea. Produces the same radial branch layout every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
prateek11rai/tldraw-canvas-kit/skills/package-diagram Skill
0★ repoDraw a UML package diagram in the open tldraw offline canvas — tab-folder packages with nesting/containment, contained elements, and dependency / «import» / «merge» relationships. Use when the user asks for a package diagram, module or namespace organization, code-organization layers, or package dependency structure. Produces the same nested-folder layout every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
prateek11rai/tldraw-canvas-kit/skills/present Skill
0★ repoBuild or update a slide presentation inside the open tldraw offline canvas — 16:9 slide frames filled with titled content, plus a durable document script that adds keyboard navigation and a Present mode. Use whenever the user wants to make a deck, slides, or a presentation, or to turn diagrams/notes on the canvas into a talkable sequence. Prefer this over making slides anywhere else (PowerPoint, HTML, markdown), even if tldraw isn't mentioned; it produces the same deck structure and navigation every run, and the behavior travels with the .tldraw file.
prateek11rai/tldraw-canvas-kit/skills/sequence-diagram Skill
0★ repoDraw a UML-style sequence diagram in the open tldraw offline canvas from a list of participants and ordered messages (calls and returns). Use whenever the user asks for a sequence diagram, or to show a flow, protocol, or interaction between components/services over time. Produces the same lifeline-and-message layout every run so sequence diagrams stay consistent across a team. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
prateek11rai/tldraw-canvas-kit/skills/state-diagram Skill
0★ repoDraw a state-machine / state-transition diagram in the open tldraw offline canvas — states connected by labeled transition arrows, with initial and final states. Use when the user asks for a state diagram, a state machine, a lifecycle diagram, or to show how something moves between statuses on events. Produces the same state-and-transition notation every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
prateek11rai/tldraw-canvas-kit/skills/use-case-diagram Skill
0★ repoDraw a UML use-case diagram in the open tldraw offline canvas — actors outside a system boundary, use-case ellipses inside it, associations, and «include»/«extend» relationships. Use when the user asks for a use-case diagram, actor interactions, "who can do what" with a system, or a system-scope/requirements visualization. Produces the same actor-and-boundary layout every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
MyAiFreedomSystems/incredagents/graphics Skill
no license0★ repoCanonical graphics skill. One entry point for every visual asset the user generates — graphics, images, infographics, banners, slides, diagrams, logos, mockups, posters. Eight curated styles A through H with example-led picker, ASK-FIRST discipline, and the safe pipeline guarantees. Triggers on graphics, image, infographic, banner, slide, diagram, logo, mockup, poster, generate an image, render, design a, make a picture of, "remake this slide", visual asset.
lhbsaa/apex-discovery/skills/docx Skill
0★ repoUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
The same file is in 1 other repository
lhbsaa/apex-discovery/skills/liteparse Skill
0★ repoLocal document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities are per-token bounding boxes, page raster output, and fully local processing with no cloud API.
The same file is in 3 other repositories
lhbsaa/apex-discovery/skills/markdown-mermaid-writing Skill
0★ repoComprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.
The same file is in 3 other repositories
lhbsaa/apex-discovery/skills/markitdown Skill
0★ repoConvert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.
lhbsaa/apex-discovery/skills/pathml Skill
0★ repoFull-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.
The same file is in 1 other repository
lhbsaa/apex-discovery/skills/pdf Skill
0★ repoUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
The same file is in 1 other repository
lhbsaa/apex-discovery/skills/pptx-posters Skill
0★ repoCreate research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual integration.
lhbsaa/apex-discovery/skills/pptx Skill
0★ repoUse this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
The same file is in 1 other repository
lhbsaa/apex-discovery/skills/scientific-slides Skill
0★ repoBuild slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.
lhbsaa/apex-discovery/skills/xlsx Skill
0★ repoCreate, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm) where the workbook file is the primary deliverable. Use for formulas, formatting, financial models, multi-sheet workbooks, and tabular cleanup exported to Excel. Also applies to .csv/.tsv when the user wants spreadsheet output. Do NOT use for Word documents, HTML reports, standalone Python scripts, database pipelines, or Google Sheets API work.
The same file is in 1 other repository
selftwo/sourcebook Skill
0★Turn a pile of URLs and files into a claim-cited artifact (interactive HTML answer, one-slide explainer, deck, brief, infographic, or podcast script) where every factual sentence is pinned to a byte-exact quote in a source. Use when the user asks a research question, gives you sources to synthesize, or wants a document they can check.
gitt510/agent-skills/skills/yt-digest Skill
0★ repoSummarize a YouTube video from its transcript (subtitles) fetched with yt-dlp, without watching it; never downloads the video or audio. Use when a YouTube URL (youtube.com / youtu.be) is shared and the user wants the content, key points, or a transcript — including vague asks like "what's this about?" as long as the target is a YouTube video.
VJDiPaola/skill-forge/pdf Skill
0★ repoRead, create, or review PDF files using Poppler rendering and Python tools for generation and extraction. Use when the user asks to read, create, combine, or review a PDF file.
VJDiPaola/skill-forge/photo-geolocator Skill
0★ repoExtract when and where photos were taken using EXIF metadata, then reverse geocode GPS coordinates to venues, restaurants, and addresses. Trigger on "where was this taken," uploaded photos with where/when questions, mapping photos to places, converting GPS coordinates to addresses, or any mention of photo metadata, geolocation, or geotagging. Also the reusable building block when another skill needs date/location from photos.
VJDiPaola/skill-forge/speech Skill
0★ repoGenerate text-to-speech audio via the OpenAI Audio API using the bundled CLI. Use when the user wants text turned into spoken audio.
VJDiPaola/skill-forge/transcribe Skill
0★ repoTranscribe audio to text with optional diarization and speaker identification. Use when the user has audio that needs transcription, diarization, or speaker identification.
bgevorkian/agent-skills/skills/video-to-notes Skill
0★ repoConvert a local video or supported video URL into structured Markdown notes and a searchable PDF using native subtitles or optional Whisper transcription plus perceptual frame deduplication and visual analysis. Use for video-to-notes, video-to-document, tutorial summaries, meeting or lecture notes, and extracting on-screen code, terminal commands, slides, or UI steps. This is multimodal video understanding, not merely speech-to-text.
brunojaime/plantuml-diagram-toolkit/skills/plantuml-component-diagram Skill
0★ repoGenerate and refine logical UML component diagrams in PlantUML from architecture notes, requirements, or code. Use when the user asks for componentes, modules, services, hexagonal ports/adapters, provided and required interfaces, logical dependencies, or external systems. Exclude deployment location, servers, containers, regions, networks, and runtime topology; route those concerns to the architecture diagram skill.
Plantuml entity relationship diagram
brunojaime/plantuml-diagram-toolkit/skills/plantuml-entity-relationship-diagram Skill
0★ repoGenerate and refine entity-relationship diagrams (DER/ERD) in PlantUML from data requirements, schemas, SQL, ORM models, or architecture notes. Use for entidades, tablas, attributes, primary and foreign keys, identifying relationships, optionality, and cardinalities. Do not model software components, runtime deployment, class methods/inheritance, or temporal message flows.
brunojaime/plantuml-diagram-toolkit/skills/plantuml-sequence-diagram Skill
0★ repoGenerate and refine UML sequence diagrams in PlantUML from use cases, API flows, webhooks, queues, retries, callbacks, or architecture notes. Use when the user asks for secuencia, flujo temporal, order of calls, request/response, asynchronous events, alternatives, loops, errors, timeouts, or participant lifelines. Do not show deployment containment, static component topology, class structure, or database entity relationships.
coconilu/token-plan-media-hub/adapters/codex/token-plan-media-hub/skills/token-plan-generate-video Skill
0★ repoSubmit and track an Alibaba Model Studio video-generation job through the local Token Plan Media Hub. Use for text-to-video requests and, only when reported by the Hub, image-to-video or reference-video requests. Do not use for deterministic editing, timeline composition, or an unsupported model capability.
MohtashamMurshid/skills/skills/render-launch-film Skill
0★ repoBuild a launch video or motion-design sequence as a deterministic, seekable web page, then render it frame by frame into an MP4 with headless Chrome and ffmpeg. Use when asked for a launch film, product announcement video, release teaser, animated sequence, motion graphics, kinetic typography, sizzle reel, or an explainer video generated from a repository, docs, or spec — including requests to reproduce a motion-design sequence seen in a reference video or link.
Figma canva client api integration
lubochka/xiigen-mvp-engine/.agents/skills/figma-canva-client-api-integration Skill
0★ repoThe thin-client boundary for design-source integration (FigmaToCode / CanvaToCode) in XIIGen mvp: the client only sends a payload and receives a result/artifacts; no client-side training, semantic ranking, visual scoring, DPO, or checkpoint mutation. Defines the payload contract (source_kind, payload_ref_or_inline_payload, selected_frame_or_page, viewport_state_request, tier_policy_id, privacy_scope, user_approval_refs), the privacy-gate, the debug-gate, and honest failed/quarantine statuses.
sairam0424/MindForge/.agent/skills/hyperframes Skill
0★ repoCreate HTML-based video compositions, animated title cards, social overlays, captioned talking-head videos, audio-reactive visuals, and shader transitions using HyperFrames. HTML is the source of truth for video. Use when the user wants a rendered MP4/WebM from an HTML composition, wants to animate text/logos/charts over media, needs captions synced to audio, wants TTS narration, or wants to convert a website into a video.
sairam0424/MindForge/.agent/skills/pixel-art Skill
0★ repoPixel art w/ era palettes (NES, Game Boy, PICO-8).
sairam0424/MindForge/.agent/skills/video-orchestrator Skill
0★ repoPlan, set up, and monitor a multi-agent video production pipeline backed by a Kanban pipeline. Use when the user wants to make ANY video — narrative film, product/marketing, music video, explainer, ASCII/terminal art, abstract/generative loop, comic, 3D, real-time/installation — and the work warrants decomposition into specialized profiles (writer, designer, animator, renderer, voice, editor, etc.) coordinated through a kanban board. Performs adaptive discovery to scope the brief, designs an appropriate team for the requested style, generates the setup script that creates agent profiles + initial kanban task, then helps monitor execution and intervene when tasks stall or fail. Routes scenes to whichever rendering / audio / design skill fits each beat (`ascii-video`, `manim-video`, `p5js`, `comfyui`, `touchdesigner-mcp`, `blender-mcp`, `pixel-art`, `baoyu-comic`, `claude-design`, `excalidraw`, `songsee`, `heartmula`, …) plus external APIs for TTS, image-gen, and image-to-video as needed.
sairam0424/MindForge/.mindforge/skills/media-streaming Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/pixel-art Skill
0★ repoPixel art w/ era palettes (NES, Game Boy, PICO-8).