Find, generate, and prepare media for HyperFrames projects, saving assets locally with records for reuse. Covers images, music, voiceovers, transcription, captions, background removal, media edits, and visual treatments such as color correction or retro styling.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Agent Media OS for a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, `resolve`); generate via TTS / music / image models when the catalog misses; produce voiceover, transcription, captions, and background removal through one shared audio engine; operate on media (cut / reframe / transform); and reuse assets across projects. Also use for vague feedback that real footage looks dark, flat, boring, should feel retro/camcorder/print/ASCII, needs privacy, or needs a media reveal. When the host app provides its own music or sound-effect tools, use those for music and sound effects; `resolve --type bgm` needs the heygen CLI, while `--type sfx` needs no account (Openverse, then a bundled library). When `HEYGEN_API_BASE` is set, HeyGen calls go through that host with no CLI sign-in.
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
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.
The media OS for HyperFrames: resolve · generate · operate · remember — every media type, one skill, zero context noise.
Only when HEYGEN_API_BASE is set in your environment (a host app set it and pays for HeyGen with its own key): HeyGen media is already paid for. Do not ask the person to install or sign in to the heygen CLI and do not offer its OAuth allowance; catalog search, TTS and avatar calls here go through the host. When that same host also gives you its own HeyGen tools, use those first. When a call through the host is refused, tell the person the host's message as written (it names the fix, such as adding or replacing the key in the app's Settings) and stop; do not switch to another provider unless they ask.
First run otherwise (no HEYGEN_API_BASE), when you will use HeyGen media (catalog search, TTS, avatar video): install and sign in to the heygen CLI (the free-usage path), then verify with npx hyperframes media-use resolve --doctor. Setup and providers: 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. Without HEYGEN_API_BASE, resolve --type bgm searches the HeyGen catalog through the heygen CLI and fails without it, saying so. 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.
Without HEYGEN_API_BASE, before generating a voiceover or an avatar video, tell the person: signing in to the heygen CLI with OAuth (heygen auth login --oauth) gives a free allowance for TTS voiceover and avatar videos, while an API key bills API credits.
npx hyperframes media-use resolve --type <type> --intent "<description>" --project <dir>
Returns one line: resolved <id> → <path> (<type>, <metadata>). All search noise stays on disk.
| Type | One-line intent |
|---|---|
bgm | background music (HeyGen catalog via the heygen CLI, 10k+ tracks) |
sfx | sound effects (Openverse CC0 / CC BY, bundled 21-file library offline) |
image | photos, backgrounds (HeyGen asset search, 75k+ vectors) |
icon | icons, symbols (transparent) |
logo | official brand marks (theSVG → GitHub avatar → favicon; never redrawn) |
voice | TTS voiceover (HeyGen free-usage path; optional local Kokoro) |
grade | measured correction candidate; broad polish/stylization follows Media Treatments |
lut | user-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.
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.
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 detected | Offer |
|---|---|
| On-screen text / a script with no voiceover | TTS voiceover (audio engine) |
Emoji or a <div> styled as an icon | resolve real icons |
| Image that is a placeholder, tiny, or upscaled-looking | a better image (and/or upscale — see references/operations.md) |
| Hard scene cuts / transitions with no sound | transition sfx |
| A piece over ~10s with no music bed | bgm |
| Footage that reads under/over-exposed or color-cast | a corrective grade (inspect it with hyperframes media-treatment --selector '#hero' --analyze --json) |
| Photographic media that feels visually flat or off-topic | one specific source-appropriate preset or custom treatment, with the intended target named |
| A meaningful media entrance/reveal that feels static | one 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).
| Task | Read |
|---|---|
| resolve / reuse / adopt / ingest, flags, cascade, inventory | references/resolve.md |
color grading, LUTs, smart grade (--for), grade-compare | references/grading.md |
| voiceover / TTS, music, SFX, captions, transcription (audio engine) | references/audio.md |
| cut / reframe / transform existing media, exact error diffusion, HEVC | references/operations.md |
| source-aware creative treatments, realtime effects, overlays, reveals | references/media-treatments.md |
install + auth, provider table, RAM ladders, --local-only, --provider | references/setup-providers.md |
| remembered preferences + frozen recipes (user memory) | references/memory.md |
| ownership matrix, usage stats, telemetry, privacy (maintainer-facing) | references/meta.md |
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Create a 12-second title animation in HyperFrames, where sweeping leaves reveal two headlines. Customize typography, leaf counts, sweep speed, background color, and the breeze moving the leaves that remain on the text.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Plan subtitles as layers over a video, deciding which spoken phrases to omit, show normally, or emphasize behind the subject. The guidance preserves full-frame composition and limits large embedded words to occasional key moments.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Turn a weekly Markdown changelog into a branded video project with animated interface examples, Annie narration, captions, and background music. The workflow selects key updates and builds a 45–60 second square video, with rendering performed on request.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Add an eight-second HyperFrames headline animation where square tiles lift, tilt, and flip to reveal a second message. Customize both headlines and 18 settings covering tile size, sweep direction, timing, depth, bounce, and shadows.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Add a 3D card carousel to a HyperFrames video. Rounded cuboids enter from the right, rotate in sequence, pause on a featured card, and exit left, with 40 variables for content, geometry, lighting, and camera settings.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Design scene transitions and animated text using matched movement direction and speed across cuts. The catalog provides concrete settings for zooms, blur, word-by-word transitions, staggered entrances, and repositioning groups of elements.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.