ryu1845/hyperframes

media-use

Agent Media OS for a HyperFrames project.

소스 보기

사용 방법

  1. 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
  2. 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
  3. 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/ryu1845/hyperframes --skill media-use

시작 전 확인

  • 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
  • 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 Skill 문서

원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.

Plugin installs: Before setup or freshness commands, follow plugin execution rules when this skill is inside a HyperFrames plugin. Standalone installs keep the update instructions below.

media-use

The media OS for HyperFrames: resolve · generate · operate · remember — every media type, one skill, zero context noise.

First run: verify the local setup with hyperframes media-use resolve --doctor (it checks ffmpeg, ffprobe, Node and the bundled SFX). Every generator is local-first and opt-in; providers, keys and installs: references/setup-providers.md.

Music and sound effects inside a host app: when the app you run in gives you its own music or sound-effect tools, use those. Otherwise music has no catalog: generate the bed with the audio engine (audio/references/bgm.md — Lyria with GEMINI_API_KEY, else local MusicGen) and resolve --type bgm records it with --from. resolve --type sfx searches Openverse (CC0 and CC BY only, no account) and falls back to its bundled library offline; credit CC BY sounds as audio/references/sfx.md says.

Before generating a voiceover, tell the person which engine will run: ElevenLabs when ELEVENLABS_API_KEY is set, otherwise local Kokoro (Gemini only when asked for). A missing key is their choice to make, not a silent fallback.

Resolve — the one verb

bash
hyperframes media-use resolve --type <type> --intent "<description>" --project <dir>

Returns one line: resolved <id> → <path> (<type>, <metadata>). All search noise stays on disk.

TypeOne-line intent
bgmbackground music: no catalog — generate it (audio engine), record with --from
sfxsound effects (Openverse CC0 / CC BY, bundled 21-file library offline)
imagephotos, backgrounds (generated: local mflux, codex upsell)
iconicons, symbols: no catalog — author an SVG, record with --from
logoofficial brand marks (theSVG → GitHub avatar → favicon; never redrawn)
voiceTTS voiceover (local Kokoro; the audio engine adds ElevenLabs and Gemini)
videogenerated clips (local LTX)
grademeasured correction candidate; broad polish/stylization follows Media Treatments
lutuser-provided or explicitly chosen reusable validated .cube file

Before resolving fresh, list reusable candidates with --candidates and judge fit yourself — reuse rules, all flags, ingest (--from), and adopt are in references/resolve.md.

Treat broad visual feedback as media intent

When a user explicitly asks to fix, polish, stylize, obscure, emphasize, or reveal photographic media, read references/media-treatments.md even if they do not name color grading or an effect. Inspect the real <img>/<video>, choose one primary intent, then use deterministic persistence and verification. Use a matching recipe as an optional tested seed, or inspect hyperframes media-treatment --capabilities --json, then request one relevant family/effect with --capability <id> and assemble a custom treatment from canonical controls. Never load --all for ordinary authoring. A treatment may compose correction, a preset, finishing, compatible shader effects, supported keyframes, and optional Registry overlays. Add only source-justified bounded tuning and compatible parts, never effects merely to make the result look more sophisticated. Persist the final combined payload with hyperframes media-treatment.

Use one progressively escalating workflow. For video, inspect one labeled early/middle/late contact sheet rather than reading frames separately. Apply one candidate and inspect one after-sheet for ordinary correction or polish. Escalate to individual frames or moving draft evidence only when the result is ambiguous, temporal, stylized, LUT-based, HDR/LOG-sensitive, private, or brand-critical.

For ordinary correction or polish, persist the final treatment's preset/adjustment JSON. Do not generate a .cube LUT merely to encode exposure, shadows, contrast, or warmth. Use a LUT only when the user supplies one or the selected treatment explicitly owns one. resolve --type grade --for ... --analyze is measurement evidence, not permission to replace the chosen treatment with a generated LUT. Do not recreate supported vignette, grain, blur, pixelate, color, or treatment effects with CSS/SVG overlays; that bypasses Studio controls and the canonical preview/render shader path.

Be proactive — run a media opportunity pass

The human usually can't tell which media would lift the piece. You can. When you build or review a composition, do one grounded scan and then ask once — don't silently add, and don't nag per asset.

Surface an opportunity only when a concrete signal is present:

Signal detectedOffer
On-screen text / a script with no voiceoverTTS voiceover (audio engine)
Emoji or a <div> styled as an iconreal icons (authored SVG, recorded with resolve --type icon --from)
Image that is a placeholder, tiny, or upscaled-lookinga better image (and/or upscale — see references/operations.md)
Hard scene cuts / transitions with no soundtransition sfx
A piece over ~10s with no music beda generated bgm bed (audio engine)
Footage that reads under/over-exposed or color-casta corrective grade (inspect it with hyperframes media-treatment --selector '#hero' --analyze --json)
Photographic media that feels visually flat or off-topicone specific source-appropriate preset or custom treatment, with the intended target named
A meaningful media entrance/reveal that feels staticone supported seek-safe treatment animation; preserve color unless the request also justifies a preset

Rules that keep this a help, not nagware: grounded, not generic (no signal → no suggestion); opinionated + concrete (propose the specific fix with defaults chosen — the human approves all / some / none); once per project (one consolidated ask; respect "leave it"); surface, never silently mutate (color grades especially: propose and preview — a gray-world "correction" ruins an intentional sunset or neon look).

Where to look — read only the file your task needs

TaskRead
resolve / reuse / adopt / ingest, flags, cascade, inventoryreferences/resolve.md
color grading, LUTs, smart grade (--for), grade-comparereferences/grading.md
voiceover / TTS, music, SFX, captions, transcription (audio engine)references/audio.md
cut / reframe / transform existing media, exact error diffusion, HEVCreferences/operations.md
source-aware creative treatments, realtime effects, overlays, revealsreferences/media-treatments.md
install + keys, provider table, RAM ladders, --local-only, --providerreferences/setup-providers.md
remembered preferences + frozen recipes (user memory)references/memory.md
ownership matrix, usage stats, privacy (maintainer-facing)references/meta.md

관련 작업

같은 저장소의 Skills

더 많은 Skills

모든 Skills
ryu1845
커뮤니티

hyperframes

Mandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or motion graphic, including a promo, explainer, captioned clip, title card, overlay, slideshow or interactive deck, Remotion port, or any HyperFrames HTML composition. Also use it to inspect, diagnose, validate, preview, or batch-render an existing HyperFrames project. Inputs may be a website URL, GitHub PR, Figma design or URL, text or brief, existing footage, or music. It resum

설치 수
2
GitHub Stars
0
업데이트
10월 20일
ryu1845
커뮤니티

hyperframes-animation

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography

설치 수
2
GitHub Stars
0
업데이트
10월 20일
ryu1845
커뮤니티

hyperframes-audio

Use when audio already placed in a HyperFrames composition needs to be mixed: fade-in/fade-out, crossfade, track gain or volume, volume automation, ducking, a music bed that fights a voiceover (voiceover carve), effects on a track (EQ, compressor, limiter, gate, saturation, delay, reverb, chorus, phaser, bitcrush), automation envelopes drawn on a track's volume or any effect parameter, or one submix bus carrying a chain, a fader and an automation clock for several tracks at once ( ). Don't use f

설치 수
2
GitHub Stars
0
업데이트
10월 20일
ryu1845
커뮤니티

hyperframes-cli

Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, cloudrun, lambda, doctor, browser, info, skills, compositions, timeline, history, clean, docs, benchmark, transcribe, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, AWS Lambda, and Google Cloud Run renderi

설치 수
2
GitHub Stars
0
업데이트
10월 20일