Media & documents
9,938 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
AlexAnsart/demo-studio/skills/narrate Skill
3★ repoGenerates a narration voiceover .mp3 for a demo video script using the ElevenLabs API — configurable voice/model/stability, deterministic output filename. Use when the user asks to add a voiceover, narration, or spoken audio to a demo/tutorial video, or names ElevenLabs explicitly.
AlexAnsart/demo-studio/skills/produce-video Skill
3★ repoEnd-to-end production of a narrated, captioned demo video for any web app — chains narration generation (narrate), silent Playwright recording (film-demo, smart zooms + guardrails), and narration sync with burned captions (sync-narration) into one final .mp4. Use when the user asks to produce, make, or film a demo/product/tutorial video end to end, "with voice and subtitles", or "from A to Z".
AlexAnsart/demo-studio/skills/sync-narration Skill
3★ repoSyncs a separately-recorded narration track onto a silent screen recording — pads audio with calculated pauses to match on-screen pacing (no voice during cursor movement), then burns styled captions. Use when the user provides a silent screen-recorded video plus a narration .mp3 and asks to sync/combine/caption them.
gy910210/hermes-research-skills/skills/doc-diagram-orchestrator-zh Skill
3★ repo从中文或英文 Markdown/文字稿中识别适合插图的段落,判断应使用结构图、流程图、时序图、对比图、时间线或矩阵图,生成插图计划、绘图规格与正文落位建议。用于长文综述、技术方案、研究笔记、产品文档等需要把纯文字转成可视化内容的场景;当用户要求“给这篇文档补图”“找出哪些地方该画图”“基于当前文稿生成结构图/流程图”时调用。
LevyBytes/AI-SKILL-adobe-products/media-encoder Skill
3★ repoUse when a task specifically concerns Adobe Media Encoder: Media Encoder queues, presets, watch folders, transcoding, exports, AME, or media automation; this is the product subskill routed from adobe-products.
mabzhang/opc-toolkit/skills/marketing-proposal Skill
3★ repoWrite client-ready Chinese marketing proposal documents from strategy inputs. Use for formal campaign proposals, pitch documents, marketing plans, launch plans, annual plans, executive summaries, budget/ROI sections and presentation- ready narratives. Trigger for: $marketing-proposal, 营销方案, 策划方案, 提案, 客户提案, pitch deck, proposal writing, 活动策划, 方案文档.
mabzhang/opc-toolkit/skills/social-media-plan Skill
3★ repoBuild multi-platform social media content strategies, content matrices, monthly calendars, viral frameworks, platform roles and production briefs for Douyin, Xiaohongshu, WeChat, Weibo, Bilibili, video accounts and ecommerce content. Trigger for: $social-media-plan, 社交媒体, 内容运营, 内容矩阵, 内容日历, 种草, 小红书方案, 抖音内容, social media plan, content calendar.
ihatesea69/HieuNghi-AI-Skills/airesearch_skills/05-data-processing/nemo-curator Skill
3★ repoGPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
The same file is in 4 other repositories
ihatesea69/HieuNghi-AI-Skills/airesearch_skills/18-multimodal/audiocraft Skill
3★ repoPyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
The same file is in 4 other repositories
ihatesea69/HieuNghi-AI-Skills/airesearch_skills/18-multimodal/stable-diffusion Skill
3★ repoState-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
The same file is in 4 other repositories
ihatesea69/HieuNghi-AI-Skills/airesearch_skills/18-multimodal/whisper Skill
3★ repoOpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
The same file is in 4 other repositories
ihatesea69/HieuNghi-AI-Skills/devto_skills/thumbnail-generator Skill
3★ repoGenerate prompts for dev.to blog thumbnail/cover images in hand-drawn infographic style. Use when creating cover images, thumbnails, or featured images for blog posts. Recommended size 1000x420 pixels.
arthjean/skills/skills/remotion-best-practices Skill
no license3★ repoBest practices for Remotion - Video creation in React
JayRHa/AgentSkills/mermaid-diagram-builder Skill
3★ repoCreates clear, valid, version-controllable diagrams as code using Mermaid — flowcharts, sequence diagrams, ER diagrams, class diagrams, state machines, Gantt charts, C4/architecture diagrams, and more. Use this skill when the user asks to "draw a diagram", "make a flowchart", "create a sequence diagram", "diagram this architecture", "visualize this process/data model/API flow", "show the ER diagram", "render Mermaid", "diagram as code", or wants a chart embeddable in Markdown, GitHub, Notion, or docs. Covers picking the right diagram type, writing syntactically correct Mermaid, styling, and validating that it renders.
JayRHa/AgentSkills/presentation-builder Skill
3★ repoOutlines compelling presentations built around a single core message, a clear narrative arc, one idea per slide, and concrete speaker notes. Use this skill when the user wants to create, outline, structure, or improve a slide deck, talk, pitch, keynote, conference presentation, sales demo, lecture, or any "build me slides / a presentation / a pitch deck" request — including requests like "turn this doc into slides", "help me prepare a talk", "make a deck about X", or "tighten my presentation".
syncfusion/react-ui-components-skills/skills/syncfusion-react-diagram Skill
no license3★ repoCreate and customize visual diagrams in React using Syncfusion Diagrams. Trigger for requests involving React component setup, nodes and connectors, flowcharts, org charts, process diagrams, BPMN or UML models, layout algorithms, swimlanes, symbol palettes, and interactive diagram visualization features.
syncfusion/react-ui-components-skills/skills/syncfusion-react-gantt-chart Skill
no license3★ repoImplement, configure, and customize the Syncfusion React Gantt Chart component. Use this when building project scheduling applications with task timelines, dependencies, and resource management. Covers GanttComponent setup, task constraints, taskbar customization, filtering, sorting, Excel/PDF export, critical path analysis, milestones, predecessors, resource view, and baseline tracking.
syncfusion/react-ui-components-skills/skills/syncfusion-react-image-editor Skill
no license3★ repoMaster Syncfusion React Image Editor for comprehensive image editing. Use this when users need to edit images, add annotations, apply filters, manage layers, or implement image editing features. Supports multiple formats (PNG, JPEG, SVG, WEBP, BMP), annotations (text, shapes, freehand, images), effects (filters, finetune), and accessibility features.
syncfusion/react-ui-components-skills/skills/syncfusion-react-pivot-table Skill
no license3★ repoUse this skill when users ask how to build or customize Syncfusion PivotView pivot tables in React. Trigger for React pivot grid/OLAP, aggregation, data binding (JSON/remote), drill-down/drill-through, grouping, filtering, conditional formatting, exports (Excel/PDF/CSV), or pivot charts. React-only, not Angular/Vue/Blazor.
Syncfusion react rich text editor
syncfusion/react-ui-components-skills/skills/syncfusion-react-rich-text-editor Skill
no license3★ repoImplements the Syncfusion React Rich Text Editor (RichTextEditorComponent) from ej2-react-richtexteditor, supporting HTML (WYSIWYG) and Markdown editing. Use this skill for toolbar configuration, image/video/audio insertion, paste cleanup, AI assistant integration, emoji picker, slash menu, mentions, import/export Word/PDF, form validation, and source code view in React applications.
Syncfusion react speech to text
syncfusion/react-ui-components-skills/skills/syncfusion-react-speech-to-text Skill
no license3★ repoImplement the Syncfusion React SpeechToText component. Use this skill to convert speech to text, manage microphone input, control listening states, process speech events, customize UI, support accessible voice-enabled forms, and handle globalization and security in React applications.
m-binimran/design-pack/skills/figma-handoff Skill
3★ repoPull a Figma design via the Figma connector and produce a developer handoff - tokens, specs, redlines, asset list, and component notes. Use when handing a design to engineering or auditing a Figma file.
m-binimran/design-pack/skills/logo-concepts Skill
3★ repoDevelop logo direction and concepts - brief, strategy, style exploration, and concept generation - with usage and licensing care. Use when designing or exploring a logo/identity mark.
m-binimran/design-pack/skills/presentation-deck Skill
3★ repoBuild a presentation deck from an outline - consistent layout system, hierarchy, on-brand visuals - via Canva or as structured slides. Use for pitch decks, brand presentations, and client proposals.
unix2dos/skills/mermaid-generator Skill
3★ repoOnly invoke when explicitly requested via "画图"、"图表"、"流程图"、"mermaid"、"@mermaid-generator". Do NOT auto-trigger.
ondrej-merkun/skill-audit/test/fixtures/PI-METADATA-MISMATCH/benign Skill
no license3★ repoWraps ffmpeg for audio/video conversion.
ondrej-merkun/skill-audit/test/fixtures/PI-OVERRIDE/benign Skill
no license3★ repoHelps extract text from PDF files.
ondrej-merkun/skill-audit/test/fixtures/benign/ffmpeg-wrapper Skill
no license3★ repoScan every AI agent skill on your machine for prompt injection and malicious code. Fast local rules by default, with optional local LLM review for deeper context.
ondrej-merkun/skill-audit/test/fixtures/benign/pdf-extractor Skill
no license3★ repoScan every AI agent skill on your machine for prompt injection and malicious code. Fast local rules by default, with optional local LLM review for deeper context.
EvezArt/evez-skills/skills/docx Skill
no license3★ 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
EvezArt/evez-skills/skills/excel-generator Skill
no license3★ repoProfessional Excel spreadsheet creation with a focus on aesthetics and data analysis. Use when creating spreadsheets for organizing, analyzing, and presenting structured data in a clear and professional format.
The same file is in 9 other repositories
EvezArt/evez-skills/skills/pdf Skill
no license3★ 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 40 other repositories
EvezArt/evez-skills/skills/pptx Skill
no license3★ 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 22 other repositories
EvezArt/evez-skills/skills/xlsx Skill
no license3★ repoUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
The same file is in 29 other repositories
m-binimran/creator-pack/skills/carousel-post Skill
3★ repoWrite an Instagram/Facebook carousel - hook slide, value slides, and a CTA slide - designed to earn the swipe and the save. Use when creating an educational or list-style carousel.
Syo-M/fable-frontend-skills/.claude/skills/codex-imagegen Skill
3★ repoGenerate or AI-edit images by delegating to the Codex CLI ($imagegen / gpt-image) — sample banners, hero visuals, demo assets, image-to-image edits. Use whenever a task needs image GENERATION or AI photo editing (Claude Code cannot generate images itself). 日本語の依頼例:「画像を生成して」「サンプル画像を作って」「この写真を加工して」「バナー/ヒーロー画像が必要」。NOT for resizing/compressing existing assets (use `images-media`).
Syo-M/fable-frontend-skills/.claude/skills/images-media Skill
3★ repoImages, icons, fonts, and video — responsive images, modern formats, lazy loading, CLS/LCP optimization, SVG handling, font loading. Use when adding or optimizing images, fonts, video, favicons, or fixing layout-shift / slow-LCP issues. 日本語の依頼例:「画像が重い/遅い」「画像を最適化して」「フォント読み込み」「動画埋め込み」「LCP改善」「レイアウトがガタつく」「ファビコン」。
Syo-M/fable-frontend-skills/plugin/skills/codex-imagegen Skill
3★ repoGenerate or AI-edit images by delegating to the Codex CLI ($imagegen / gpt-image) — sample banners, hero visuals, demo assets, image-to-image edits. Use whenever a task needs image GENERATION or AI photo editing (Claude Code cannot generate images itself). 日本語の依頼例:「画像を生成して」「サンプル画像を作って」「この写真を加工して」「バナー/ヒーロー画像が必要」。NOT for resizing/compressing existing assets (use `images-media`).
Syo-M/fable-frontend-skills/plugin/skills/images-media Skill
3★ repoImages, icons, fonts, and video — responsive images, modern formats, lazy loading, CLS/LCP optimization, SVG handling, font loading. Use when adding or optimizing images, fonts, video, favicons, or fixing layout-shift / slow-LCP issues. 日本語の依頼例:「画像が重い/遅い」「画像を最適化して」「フォント読み込み」「動画埋め込み」「LCP改善」「レイアウトがガタつく」「ファビコン」。
Axect/skills/wide-slide-illustrator Skill
3★ repoCompose image-generation prompts for wide 18:9 infographic slides that explain methodology, data pipelines, architectures, or research ideas. Support Friendly Whiteboard, Editorial Magazine, Engineering Blueprint, Swiss Minimalist, Dark Tech/Neon, and Scientific Poster styles, with English-only on-image text and style-specific hard negatives. Use when the user asks for slide illustrations, pipeline diagrams, paper hero figures, journal-style methodology figures, keynote backdrops, or prompts for ChatGPT Image, gpt-image, DALL-E, Sora, or Midjourney.
Embedded ui svg doc from source
Ed3Design/ed3design-engineering-bundles/maker-fdm/skills/embedded-ui-svg-doc-from-source Skill
2★ repoUse when documenting an embedded device GUI (ESP32/Arduino touchscreens, LovyanGFX/TFT_eSPI/U8g2/LVGL screens) for end-user instructions, printable manuals, or design reviews — and the source code already contains the drawing calls (`gfx.fillRect`, `gfx.drawString`, `gfx.drawLine`, `tft.drawPixel`, `display.print`, LVGL-styles etc.). Trigger on phrases like "user manual for the display", "manual with mockups", "UI documentation for the ESP32 device", "printable manual for embedded UI", "screen mockups for the touchscreen", "display screenshots without hardware", "1:1 SVG from the source code", "tangible mockup". Do NOT load for web-frontend UI docs (use frontend-design or marketing), for CAD assembly drawings (use cad-construction), or when no source code with literal draw coordinates exists. This skill encodes the "measure, don't estimate" maxim (originally CAD) applied to embedded-UI documentation: translate the draw calls verbatim into SVG, do not rebuild semantically.
qte77/claude-code-plugins/plugins/market-research/skills/generating-slide-deck Skill
2★ repoGenerate an investor or stakeholder presentation from Phase 5 synthesis; produces a structured slide outline with headlines, talking points, and data citations. Run after `synthesizing-research` (Phase 6).
qte77/claude-code-plugins/plugins/market-research/skills/synthesizing-research Skill
2★ repoSynthesize all prior research into a unified GTM narrative. Run after `analyzing-contradictions` to prepare for slide deck generation (Phase 5).
eins78/agent-skills/skills/pandoc Skill
2★ repoUse when converting documents between formats — HTML, Markdown, DOCX, PDF, LaTeX, EPUB, reStructuredText, Org, JIRA, CSV, Jupyter notebooks, slides, and 60+ others. Triggers: convert file, export to PDF, make a PDF, print to PDF, printable PDF, A4 print, fold-to-A5 booklet, turn this into markdown, HTML to markdown, DOCX to markdown, markdown to DOCX, generate slides, create EPUB, format conversion, pandoc, document conversion. Always prefer pandoc over ad-hoc conversion scripts.
eins78/agent-skills/skills/pdf-zine Skill
2★ repoUse when converting a PDF into a fold-and-print booklet (zine) — A4 sheets, double-sided, short-edge flip, fold to A5. Triggers: make a zine, make a booklet, booklet PDF, imposition, fold-and-print, 2-up booklet, print as booklet, signature imposition, pdf-zine, pdf2zine, bookletimposer. Wraps the `pdf2zine` Docker-based CLI; prefer it over hand-rolled Ghostscript or pdfjam scripts.
eins78/agent-skills/skills/private-podcast-feed Skill
2★ repoUse when publishing a private MP3+RSS feed for self-subscription. Covers itunes:block, token-prefixed URLs, ID3 CHAP/CTOC chapters for Overcast skip-ahead, and the Overcast refresh ping. Triggers: private podcast, RSS feed for Overcast, self-hosted podcast, private audio feed, MP3 RSS, personal podcast, chapter markers, Overcast ping, podcast XML, itunes:block.
eins78/agent-skills/skills/text-to-speech Skill
2★ repoUse when you need to convert a text document to an audio file via a local TTS pipeline. Outputs MP3. Handles narrative rewrite, text normalization, prosody prep, and audio render. Backend is configurable. Triggers: text to speech, narrate document, make audio from text, synthesize speech, TTS, MP3 from document, convert to podcast, audio version of document.
ajaygunalan/flow-friction/skills/d2-diagram Skill
no license2★ repoCreate D2 diagrams. Triggers on "create a diagram," "visualize," "draw architecture," "show relationships."
launch52-ai/flutter-template/.claude/skills/presentation Skill
2★ repoGenerate presentation layer code (Freezed states, Riverpod notifiers, screens, widgets) from feature specifications. Creates the UI layer with proper state management. Use after /data to implement screens and state handling.
renalpelvisdeinocheirus70/ozor-skills/skills/ozor-doc-to-video Skill
2★ repoConvert any document into a production-ready Ozor.ai video prompt. Use this skill whenever the user uploads a document (PDF, PowerPoint, Google Doc, Markdown, text file, or URL) and wants to turn it into a video. Also trigger when the user mentions 'turn this doc into a video', 'make a video from this PDF', 'video from my pitch deck', 'convert this presentation to video', 'video from this blog post', 'video from these release notes', 'create a video from this document', 'turn this into an explainer', or any request to transform written content into video format using Ozor. This skill reads the document, extracts the core message, structures it into scenes, and outputs a complete prompt the user can paste directly into Ozor.ai.
The same file is in 1 other repository
renalpelvisdeinocheirus70/ozor-skills/skills/ozor-landing-page-to-video Skill
2★ repoConvert any landing page or website into an Ozor.ai video prompt. Use this skill whenever the user provides a URL, landing page content, or website copy and wants to turn it into a video. Trigger on phrases like 'make a video from my website', 'video from this landing page', 'turn my homepage into a video', 'video from this URL', 'product page to video', 'website to video', 'marketing video from my site', 'convert this page to video', or any request to transform web content into video format using Ozor.
The same file is in 1 other repository
renalpelvisdeinocheirus70/ozor-skills/skills/ozor-video-best-practices Skill
2★ repoExpert guide for crafting high-quality video prompts for Ozor.ai, the AI video generation platform. Use this skill whenever the user mentions Ozor, wants to create a launch video, product demo, feature announcement, explainer video, social ad, release notes video, investor update, tutorial, or any marketing video. Also trigger when the user asks for help writing video prompts, improving video output, structuring video scenes, choosing video formats, or wants best practices for AI video creation. Trigger on phrases like 'make a video', 'create a launch video', 'video for my product', 'Ozor prompt', 'video best practices', 'explainer video', 'product demo video', 'social clip', 'announcement video', or any request involving short-form video content for products and marketing.
The same file is in 1 other repository
jperrello/C0BALT_CUT/.claude/skills/brand-overlays Skill
no license2★ repoComposite both persistent brand PNGs — the top "Original video: <title>" credit chyron (y≈4%) and the bottom @C0BALT_CUT watermark (y≈97.5%) — onto a finished short in ONE ffmpeg pass. The credit appears only in the FINAL CREDIT_TAIL seconds (default 3.0s) — it fades in at dur-tail and holds to the end so it lands on the closing beat, leaving the cold-open title to own the top banner uncontested at the open; the watermark holds the whole clip. Replaces the back-to-back source-credit + watermark re-encodes in the orchestrator (saves a full re-encode and an intermediate .mp4 per span); those two skills remain the standalone single-overlay ops and own the PNG renderers this skill reuses.
jperrello/C0BALT_CUT/.claude/skills/broll-cleanup Skill
no license2★ repoDeferred end-of-run B-roll cache eviction. For ONLY the B-roll source video_ids this run ingested (from each broll_plan.json's ingested_video_ids), runs `mcptube remove <id>` AND deletes the local work/<id>/broll/*.mp4 cache. Never touches the podcast source, unrelated library videos, or broll_plan.json (placement metadata persists for editors). Runs once at the very end of a whole pipeline run.
jperrello/C0BALT_CUT/.claude/skills/broll-composite Skill
no license2★ repoHard-cut full-frame B-roll cutaways onto a 1080x1920 clip per broll_plan.json. During each [t0,t1] the entire frame is replaced by the cutaway (instant in/out, no crossfade/zoom); 16:9 source is scale-to-cover + SUBJECT-cropped to 1080x1920 with no bars — the slack-axis offset is chosen subject-first (MediaPipe face -> pose person -> thresholded multi-frame saliency, reusing fill-vertical's engine), so the crop sits on the actual subject instead of drifting to background texture. No transition SFX by default (BROLL_SFX=1 re-enables a short synthesized whoosh on each cutaway in/out); the podcast audio stays continuous underneath (amix'd, never replaced). Zero valid picks -> passthrough copy. Pure ffmpeg.
jperrello/C0BALT_CUT/.claude/skills/burn-subtitles Skill
no license2★ repoBurn karaoke-style word-timed subtitles into a video. Takes a transcript JSON with word timestamps and a video, emits a new video with subtitles rendered in. Renders text as a PNG overlay sequence (the local ffmpeg build has no libass/drawtext).
jperrello/C0BALT_CUT/.claude/skills/chunk-captions Skill
no license2★ repoGroup a clip's word-timed transcript into phrase-sized caption chunks via Claude. Replaces the rolling 4-word window in burn-subtitles. Each chunk is one self-contained phrase that swaps in as a whole unit.
jperrello/C0BALT_CUT/.claude/skills/cut-clip Skill
no license2★ repoTrim a video to a [t0, t1] time range using ffmpeg. Stream-copies where possible to avoid re-encoding. Use as the cheap building block for cutting source video into per-short slices.
jperrello/C0BALT_CUT/.claude/skills/cut-filler Skill
no license2★ repoApply a trim-filler keeps.json to a clip's video. Reads the kept time ranges and re-encodes the clip with ffmpeg select/aselect so kept ranges are concatenated and removed spans (filler, trail-offs, digressions) disappear. Output aligns with the trimmed transcript trim-filler wrote, so downstream subtitle / caption / title skills stay in sync.
jperrello/C0BALT_CUT/.claude/skills/loudnorm Skill
no license2★ repoNormalize audio loudness to broadcast levels using ffmpeg's two-pass loudnorm filter. Measures the input, then applies normalization with the measured parameters. Use as a final-stage audio leveling step.