MCPInstall

video-agent-skills

21 skills from melvynx/video-agent-skills · 3.8K installs

Install every skill in this repository:

npx skills add https://github.com/melvynx/video-agent-skills
  1. 1

    Edits a talking-head take end to end into a paper-style motion design short (1080x1920, also 1:1 and 16:9) with its own render engine (Node + Chrome + ffmpeg, free, offline). Use when the user says edit, cut, captions, subtitles, motion design, montage, "make it a short", render, or gives a recording from video-agent/takes/. Transcribes locally with word timings (whisper.cpp, or ElevenLabs when a key is set), cuts every silence, lays the boards on a textured paper above the camera card (counters, terminals, logos, trees, real screens, HTML motion components), word-by-word captions, a calm music bed, a few designed hits, -14 LUFS, and writes the mp4, an .srt and the post copy.

  2. 2

    Generates images with Codex (OpenAI's coding agent and its built-in image tool, included in a ChatGPT plan) - YouTube thumbnails, covers, B-roll stills, board images, profile pictures - one Codex job per image, several in parallel, with the creator's photos as reference when the face matters, then copies them into the project with a manifest. Use when the user says generate an image, a thumbnail, a cover, make me a visual, codex images, génère une image, miniature, or when publish or short-editing needs an image.

  3. 3

    The scriptwriter of the creator's videos - short-form scripts (YouTube Shorts, TikTok, Instagram Reels, 30 to 60 s) in their own voice from video-agent/voice.md, each on a concept proven by the niche's outliers, with 3 scored hooks from 22 formulas, a re-hook, triggers, offer proximity, quality gates, timing at their pace and visual notes, then a humanize pass (invisible characters, AI words in English and French, AI sentence shapes, facts kept). Modes - the week (default), one topic, a funnel or divisive script, a making-of, hook printer, rewrite, humanize, and viral (what over-performs in their niche, scored against each account's median, YouTube free with yt-dlp, TikTok and Instagram through Treg, into video-agent/swipe.md). Use when the user asks for scripts, ideas, this week's videos, a funnel or divisive (clivant) script, a making-of, a hook, a better hook, to rewrite a script, what goes viral, viral hooks, what works in my niche, competitor research, swipe file, outliers, or to

  4. 4

    Sets up the creator's video editing studio, for shorts and YouTube videos, on their computer and in their project - tools, the video-agent/ folder, the render engine, the creator's voice.md, their default editing style (an onboarding on their colors, paper, fonts, captions, sound, Instagram CTA, real tool logos, logo and end card, with a preview on their own footage), permissions, and the optional accounts (Treg for Instagram, TikTok and YouTube, an ElevenLabs key, Codex). Use when the user says setup, onboarding, install, "start here", configure, connect my account, Treg, first time using studio-script, short-editing, publish or any video skill, or wants to update their voice, niche, CTA, brand color, look, font, captions, sound effects, logo or tool logos (/studio-setup style). Checks Node, ffmpeg, yt-dlp and git with install commands for macOS, Windows and Linux, writes voice.md from their own videos or a short interview, pre-approves the tool commands in .claude/settings.json.

  5. 5

    Copies another creator's editing style into a named style that short-editing applies to your own takes. Use when the user says steal, "copy the style of", "edit like @x", "make a style from this reel", "vole le style de", or gives a reel or short as the model for a look. Downloads the reel (yt-dlp, or Treg for Instagram and TikTok), MEASURES the style with ffmpeg instead of eyeballing it (contact sheets, hard cuts per second, a spectrogram for the beat and the sound effects on the cuts, the music level under the voice, the face size and the zooms), writes video-agent/styles/ / (style.json for the engine + STYLE.md), then edits a test video with short-editing and compares it frame by frame with the original.

  6. 6

    Turns one long video (YouTube link, podcast, webinar, livestream, or a local file) into finished vertical shorts. Use when the user says long to short, repurpose, long video to shorts, clips from my video, podcast clips, cut my YouTube video into shorts, or gives a long video link. Finds clips that stand alone (one idea, 20 to 60 seconds), scores them, cuts them and edits each one with short-editing (split-screen paper look, captions, cuts, hook, boards, 1080x1920), and writes new scripts in the studio-script format from the ideas too spread out to clip. Reads YouTube captions and chapters with yt-dlp, or transcribes a local file with the short-editing engine (whisper.cpp, free, offline).

  7. 7

    Entry point for every video job - routes to studio-setup, insta-audit, studio-script, outliers, short-editing, broll, steal, clips, short-translate, codex-images, vox or publish, and continues the project already in progress. Use when the user says /editing, edit, montage, take, short, reel, video, script, audit, publish, or is not sure which video skill to use.

  8. 8

    Audits an Instagram account through Treg. By default the creator's own account, free - installs Treg if needed, connects their Instagram, pulls the last 30 to 50 reels with their real stats (views, reach, average watch time, saves, shares, comments) and the account's reach over 28 days, finds what over-performs against their own median, looks at the first seconds of the best and worst reels, and writes video-agent/audit.md with the 3 changes to make. With a handle or competitors, a full report - outliers, up to 5 relevant competitors and a sourced HTML report, with the cost said first. Use when the user says audit, audit my Instagram, analyse my account, my stats, why my reels don't work, my best reels, Instagram insights, connect my Instagram, audit @someone, or competitor analysis.

  9. 9

    Translates a talking-head take (or a finished video) into another language with the creator's own cloned voice through ElevenLabs Dubbing, using their ElevenLabs API key - sets the key up, trims the take first so no stutter is paid for, estimates the minutes, sends it after a yes, waits, lays the dubbed voice back on the image, then hands the translated take to short-editing for captions in the new language. Use when the user says translate, dub, dubbing, English version, Spanish version, traduis, version anglaise, doublage, ElevenLabs, or wants a second account in another language.

  10. 10

    The creator's own B-roll (their clips, screen recordings, photos) turned into a library any agent can search in one grep - scanned once with ffprobe and ffmpeg (length, orientation, date, GPS, one contact sheet per clip), tagged by cheap Haiku sub-agents (title, description, mood, keywords, creator on screen), then placed full screen in a short by short-editing. Use for /broll setup, /broll add, /broll use, /broll search, or when the user says "my B-roll", "add these clips", "put my B-roll on this short", "find me a sunset shot".

  11. 11

    Gets a finished video out on YouTube (Shorts or long), Instagram Reels and TikTok - picks the video, makes the light export for Instagram and TikTok, the cover, the caption and the YouTube title, sets the time, shows the plan, then after the creator's yes publishes through Treg on their own connected accounts (setup included), or hands a ready-to-post kit when Treg isn't set up. Use when the user says publish, post it, schedule, upload to YouTube, put it on Instagram, TikTok, publier, poster, programmer, mets-le en ligne.

  12. 12

    Turns one photo into a cinematic paper-collage animation in the style of Vox explainer documentaries (halftone cut-outs with a white scissor border, torn paper, aged paper grain, stop-motion moves, slow camera push-in). Codex generates the paper layers with the user's ChatGPT plan, the real photo is cut out and printed as halftone by code, an HTML page animates everything and is captured to an MP4 (1080x1920 by default). Use when the user says vox, Vox style, "anime cette photo", "animate this photo", paper collage animation, documentary collage, or sends a photo and an animation idea; also to change an animation already made ("do it with Napoleon", "add a train", "make it night").

  13. 13

    Finds the outlier reels of Instagram accounts or videos of TikTok accounts (3x their own account's median views or more) through Treg and turns the 5 best into remake scripts in the creator's voice. Two modes - /outliers @handle digs one account; /outliers with no account starts from the creator's own reels, uses and grows a competitor watchlist (video-agent/competitors.json, 70 % main language / 30 % second language when they watch two), ranks every account's outliers against its own median and writes 5 scripts into video-agent/scripts/. Use when the user says outliers, find outliers, what blew up for my competitors, what works in my niche, find me videos to remake, ideas from @someone, what blew up on TikTok.

  14. 14

    Edits a complete talking-head video end to end with free tools (Remotion, whisper.cpp, ffmpeg) - a vertical short (1080x1920) or a full horizontal YouTube video (1920x1080). Use when the user says edit, cut, captions, subtitles, motion design, montage, "make it a short", "edit my YouTube video", render, or gives a recording from video-agent/takes/. Transcribes locally with word timings, cuts silences and retakes against the script, adds punch-in zooms, word-by-word captions in the creator's accent color, a hook card, callouts and a progress bar, levels the voice to -14 LUFS, and writes an .srt, a cut list for CapCut or Premiere, chapters for a long video, and the post copy.

  15. 15

    Writes short-form video scripts (YouTube Shorts, TikTok, Instagram Reels, 30 to 60 s) in the creator's own voice from video-agent/voice.md (who they talk to, how they sound, their myths, their offer ladder), with optimized hooks and a humanize pass so nothing sounds like AI. Use when the user asks for scripts, script ideas, "write my shorts", this week's videos, a hook, a better hook, to rewrite or tighten a script, or to humanize any text (humanize, sounds like AI, sounds robotic, make it sound like me, a caption or description before posting). Starts from what happened in their week, writes 3 hooks per script from 22 formulas (or 20 with the hook printer), scores them, adds a re-hook, places psychological triggers, maps offer proximity across the week, rejects generic, structureless or interchangeable scripts, checks timing at their pace, adds visual notes, removes AI tells (invisible characters, AI words in English and French, AI sentence shapes) while keeping every fact, and saves

  16. 16

    First run of the video agent skills - sets up video editing on the creator's computer and in their project - tools, the video-agent/ folder, the Remotion studio, the creator's voice.md, permissions, and the optional accounts (Treg for Instagram, TikTok and YouTube, an ElevenLabs key, Codex). Use when the user says setup, onboarding, install, "start here", configure, connect my account, Treg, first time using video-script, video-edit, video-publish or any video skill, or wants to update their voice, niche, CTA or brand color. Checks Node, ffmpeg, yt-dlp and git with install commands for macOS, Windows and Linux, writes voice.md from their own videos or a short interview, pre-approves the tool commands in .claude/settings.json.

  17. 17

    Finds what over-performs in the creator's niche and writes it to video-agent/swipe.md. Use when the user asks what goes viral, viral hooks, what works in my niche, competitor research, swipe file, outliers, my best videos, my stats, or "find hooks that work". Scores recent Shorts of 10 to 12 accounts against each account's median (YouTube free with yt-dlp; TikTok, Instagram and their own stats through Treg), pulls the first 3 seconds of each outlier and tags the hook formula so video-script reuses the shape, never the words.

  18. 18

    Turns one long video (YouTube link, podcast, webinar, livestream, or a local file) into finished vertical shorts. Use when the user says long to short, repurpose, long video to shorts, clips from my video, podcast clips, cut my YouTube video into shorts, or gives a long video link. Finds clips that stand alone (one idea, 20 to 60 seconds), scores them, cuts them and edits each one with video-edit (captions, cuts, hook card, callouts, 1080x1920), and writes new scripts in the video-script format from the ideas too spread out to clip. Reads YouTube captions and chapters with yt-dlp, or transcribes a local file with the video-edit studio.

  19. 19

    Audits the creator's own Instagram account through Treg - installs Treg if needed, connects their Instagram, pulls the profile, the last 30 to 50 reels with their real stats (views, reach, average watch time, saves, shares, comments), and the account's reach over 28 days, finds what over-performs against their own median, looks at the first seconds of the best and worst reels, and writes video-agent/audit.md with what works, what doesn't and the 3 changes to make. Use when the user says audit, audit my Instagram, analyse my account, my stats, why my reels don't work, what works on my account, my best reels, Instagram insights, or connect my Instagram.

  20. 20

    Gets a finished video out on YouTube (Shorts or long), Instagram Reels and TikTok - picks the video, makes the light export for Instagram and TikTok, the cover, the caption and the YouTube title, sets the time, shows the plan, then after the creator's yes publishes through Treg on their own connected accounts (setup included), or hands a ready-to-post kit when Treg isn't set up. Use when the user says publish, post it, schedule, upload to YouTube, put it on Instagram, TikTok, publier, poster, programmer, mets-le en ligne.

  21. 21

    Translates a talking-head take (or a finished video) into another language with the creator's own cloned voice through ElevenLabs Dubbing, using their ElevenLabs API key - sets the key up, trims the take first so no stutter is paid for, estimates the minutes, sends it after a yes, waits, lays the dubbed voice back on the image, then hands the translated take to video-edit for captions in the new language. Use when the user says translate, dub, dubbing, English version, Spanish version, traduis, version anglaise, doublage, ElevenLabs, or wants a second account in another language.