Communitygithub.com

oliverhees/hermes-motion-pack

Studio-grade motion graphics and cinematic highlight videos built as code with HyperFrames (HTML + GSAP → MP4) plus ffmpeg edits of real or AI footage. ALWAYS use for any video, spot, reel, teaser, trailer, intro, logo sting, kinetic typography, product film, social clip, highlight/recap/aftermovie/montage, "mach mir ein Video", "Motion Graphics", "Werbespot", "Reel", "Cinematic", "Animation" — even if the user does not say HyperFrames. Interviews the user first, then chains mp-brief → mp-style → mp-storyboard → (mp-footage | mp-genclip) → mp-build / mp-highlight → mp-audio → mp-critique → mp-ship with approval gates.

¿Qué es hermes-motion-pack?

hermes-motion-pack is a Claude Code agent skill that studio-grade motion graphics and cinematic highlight videos built as code with HyperFrames (HTML + GSAP → MP4) plus ffmpeg edits of real or AI footage. ALWAYS use for any video, spot, reel, teaser, trailer, intro, logo sting, kinetic typography, product film, social clip, highlight/recap/aftermovie/montage, "mach mir ein Video", "Motion Graphics", "Werbespot", "Reel", "Cinematic", "Animation" — even if the user does not say HyperFrames. Interviews the user first, then chains mp-brief → mp-style → mp-storyboard → (mp-footage | mp-genclip) → mp-build / mp-highlight → mp-audio → mp-critique → mp-ship with approval gates.

Compatible con~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/oliverhees/hermes-motion-pack/tree/HEAD/skills/motion-pack

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

motion-pack — the router

Rule zero: the prompt is 10 % of the video, the harness is the other 90 %. Never jump from a one-line request straight to code. Interview → brief → style → storyboard → build → audio → critique loop → ship. Every phase has a gate where the user says OK.

Language: talk to the user in the language they write (most of them write German). Write every file, comment and commit in English.

Scope: product spots, social reels (9:16), launch teasers, logo stings and loops, kinetic typography, data stories, UI showcases — and cinematic highlight videos, trailers and recaps from the user's footage, from AI-generated clips, or from pure code. No talking-head / avatar / explainer formats.

Two tracks, one chain

TrackWhenChain
graphicseverything is drawn (spots, reels, stings, data, UI)brief → style → storyboard → mp-build → audio → critique → ship
highlightshots exist or get generated (highlight reel, trailer, aftermovie, recap)brief → style → storyboard → mp-footage (user clips) and/or mp-genclip (AI clips) → mp-highlight (beat-synced edit + overlays) → audio → critique → ship
highlight / code modecinematic look but no clips at alltreat as graphics track with the cinematic-dark preset
Decide the track in mp-brief (question 1). Mixed is allowed: real footage + AI inserts + code titles.

The chain (each step is its own skill = its own slash command)

#SkillProducesGate
1mp-briefBRIEF.md after a short interview (max 2 rounds, 3 questions each)user confirms brief
2mp-styleSTYLE.md — reference, palette, type, motion language, forbidden listuser picks preset or reference
3mp-storyboardSTORYBOARD.md — beats, state list, timing, voice linesuser approves beats
4amp-footage(highlight track) proxies, scans, SHOTLIST.json of best momentsuser confirms candidates
4bmp-genclip(highlight track) AI clips per shot card, look-locked, registered in SHOTLIST.jsonstyle frame OK, cost shown
4cmp-build(graphics track) HyperFrames project: scenes as HTML + GSAP, npx hyperframes lint greendraft render
4dmp-highlight(highlight track) beats.json, EDIT.json, base cut, overlays in HyperFramesedit plan OK, draft render
5mp-audiovoice (ElevenLabs via env key), music bed, SFX, loudness-normalised mixlisten check (user)
6mp-critiquecontact sheet, phone sheet, strip, loop seam; scores 1–10; fix listall scores ≥ 8
7mp-shipfinal renders in every format, DELIVERY.md, optional "save as skill"done

Run them in order. Skip only when the user explicitly says so ("no audio", "I already have a brief"). After each gate, say in one line which skill comes next and load it.

How to start

  1. Create the project folder: <studio>/<slug>/ (default studio root ~/motion-studio; ask once, remember in ~/motion-studio/STUDIO.json).
  2. Check dependencies: Node ≥ 22, ffmpeg, npx hyperframes --version. If the HyperFrames skill is not installed, tell the user: hermes skills install official/creative/hyperframes (or npx hyperframes init inside the project, which installs its skills automatically).
  3. Load mp-brief and run the interview.

Quality bar (binding for every phase — read references/quality-bar.md before building)

  • One hero element per moment. Something new every 2–4 s.
  • Springs and overshoot, never linear slides. No "fade everything in".
  • No centred-text-on-gradient. No corner labels, no frame borders, no stock look.
  • Text readable at 360 px wide. Max 6 words on screen at once in reels.
  • Every claim about a product comes from a source; nothing invented.
  • The agent looks at its own frames before it says "done".

Memory

  • ~/motion-studio/STUDIO.json — studio root, default language, default format, last used preset.
  • <project>/STATE.json — phase, gates passed, open issues. Update after every phase so "wo waren wir?" works.

When things go wrong

  • Render fails or stutters → npx hyperframes render --workers 1, then npx hyperframes doctor.
  • Lint complains → fix before preview; never render around a lint error.
  • No vision available → say so plainly; use mp-critique scripts and ask the user to look at the sheets.
  • No web access → mark every product claim [unverified] and list them in DELIVERY.md.

See references/chain.md for the hand-off cards between skills and references/quality-bar.md for the full rubric.

Files in this skill

  • references/chain.md
  • references/quality-bar.md

Individual skills in this repo

This repo contains 10 individual skills — each has its own dedicated page.

oliverhees/hermes-motion-pack

Step 5 of motion-pack. Produces the audio layer — voice-over via ElevenLabs (API key only from the ELEVENLABS_API_KEY environment variable), music bed, SFX on hits, sidechain ducking and two-pass loudness normalisation (voice -16 LUFS, music 12 LU under, mix -14 LUFS, true peak -1 dBTP). Use after mp-build, or when the user mentions "Stimme", "Voice-over", "Musik", "Sound", "LUFS", "zu leise", "zu laut", "ElevenLabs".

oliverhees/hermes-motion-pack

Step 1 of motion-pack. Runs a short, tap-friendly interview (max 2 rounds × 3 questions) and writes BRIEF.md for a motion graphics video — goal, audience, hook, format, length, must-show, sources, audio wishes. Use whenever a video is requested and no BRIEF.md exists yet, or the user says "Briefing", "interview me", "was brauchst du von mir".

oliverhees/hermes-motion-pack

Step 4 of motion-pack. Builds the HyperFrames project from STORYBOARD.md and STYLE.md — one HTML scene per beat with GSAP choreography, deterministic timing, real assets, then lint → draft render. Use after mp-storyboard, or when the user says "bau das", "build", "render", "Szene ändern", "HyperFrames", "GSAP", "animiere".

oliverhees/hermes-motion-pack

Step 6 of motion-pack. Makes the agent look at its own render — contact sheet, phone-size sheet, 12-frame strips around fast moments, loop-seam check, determinism check — then scores 8 criteria 1–10 as a harsh motion director, lists the 3 biggest problems with timestamps, and loops back to mp-build until every score is ≥ 8. Use after any render, or when the user says "sieht mid aus", "check das Video", "Kritik", "QC", "warum wirkt das billig".

oliverhees/hermes-motion-pack

Ingests the user's own footage (clips, gameplay, events, vlogs, screen recordings) for a highlight video — makes proxies, detects scene cuts, scores every second by motion, loudness and speech, transcribes, and writes SHOTLIST.json with the best candidate moments. Use when the user hands over video files/folders, says "aus meinem Material", "Footage", "beste Momente", "Highlights rausziehen", "schneid mir das zusammen", or before mp-highlight when real footage is the basis.

oliverhees/hermes-motion-pack

Generates AI video clips (Seedance, Veo, Kling via the kie.ai MCP server) and AI still frames (gpt-image, nano-banana) as the basis for cinematic highlight videos and trailers — shot-by-shot prompts from the storyboard, consistent look via reference frames and seeds, download, registration in SHOTLIST.json. Use when the user has no footage but wants cinematic shots, says "generier mir Clips", "KI-Video", "Seedance", "Veo", "B-Roll erzeugen", or when mp-highlight needs shots that do not exist.

oliverhees/hermes-motion-pack

Cuts cinematic highlight videos, trailers/teasers and event recaps from real footage (mp-footage), AI clips (mp-genclip) or pure code — beat-synced edit plan, speed ramps, cinematic grade (teal-amber, bleach, film grain, letterbox), kinetic titles, glitch and light-leak overlays, data overlays, all composited in HyperFrames on top of an ffmpeg base cut. Use for "Highlight-Video", "Cinematic", "Trailer", "Recap", "Aftermovie", "Best-of", "Montage", "auf den Beat schneiden", "episch".

oliverhees/hermes-motion-pack

Step 7 of motion-pack. Final render in every requested format (16:9, 9:16, 1:1, 4:5, GIF/WebM), writes DELIVERY.md (files, specs, loudness, sources, unverified claims, next steps), optionally packages the finished pipeline as a reusable skill so the next video is one sentence. Use when critique is green, or the user says "export", "final", "liefern", "alle Formate", "fertig machen".

oliverhees/hermes-motion-pack

Step 3 of motion-pack. Writes STORYBOARD.md — beats with timestamps, a state list per beat (what is on screen, where, what changes), voice lines, SFX hits and transitions — from BRIEF.md and STYLE.md. Use after mp-style, or when the user asks for "Storyboard", "Beats", "Ablauf", "Szenen", "timing".

oliverhees/hermes-motion-pack

Step 2 of motion-pack. Turns BRIEF.md into STYLE.md — a reference-driven design doc with palette, typography, motion language, sound character and a forbidden list. Offers 8 built-in style presets (clean-product, editorial-brutal, neo-glass, kinetic-type, hand-drawn, cinematic-dark, data-minimal, retro-print). Use when a video needs a look, the user says "Style", "Look", "Design", "wie soll es aussehen", or after mp-brief.

Skills relacionados