PluginBench
Skill
Pass
Audit score 90

media-use

heygen-com/hyperframes

Unified media resolution, generation, and treatment for HyperFrames projects—music, voice, images, color grading, and effects in one skill.

What is media-use?

Agent Media OS handles every media need in HyperFrames: resolve assets (BGM, SFX, images, icons, logos, voices, color grades, LUTs) from catalogs or generate them via TTS/music/image models, produce voiceover/transcription/captions/background removal, and operate on media with cuts, reframes, and transforms. Use it when you need to source, create, or polish any media type or respond to vague feedback about visual appearance.

  • Resolve media assets (background music, sound effects, images, icons, logos, voices, color grades, LUTs) into frozen local files or reusable blocks with ledger records
  • Generate missing assets via TTS, music models, and image generation when catalog search doesn't match
  • Produce voiceover, transcription, captions, and background removal through a shared audio engine
  • Apply color grading, visual treatments, and stylization (retro, camcorder, print, ASCII, privacy masking, reveals) to footage
  • Operate on media with cuts, reframes, transforms, and upscaling
  • Reuse and adopt assets across projects with deterministic persistence

How to install media-use

npx skills add https://github.com/heygen-com/hyperframes --skill media-use
Prerequisites
  • HyperFrames project environment
  • heygen CLI installed and authenticated (free-usage path available)
  • Run `npx hyperframes media-use resolve --doctor` to verify setup
  • Provider configuration (see setup-providers.md for auth and RAM requirements)
Claude Code
Cursor
Windsurf
Cline

How to use media-use

  1. 1.Run `npx hyperframes media-use resolve --type <type> --intent "<description>" --project <dir>` to resolve any media asset (bgm, sfx, image, icon, logo, voice, grade, lut)
  2. 2.List reusable candidates with `--candidates` flag before resolving fresh to check for asset reuse
  3. 3.For visual feedback (dark, flat, boring, retro), read media-treatments.md and apply corrections with `hyperframes media-treatment --capability <id>`
  4. 4.Use the audio engine for voiceover, transcription, captions, and background removal via the shared audio interface
  5. 5.Persist color grades and treatments with deterministic payloads; inspect contact sheets for video before applying

Use cases

Good for
  • Quickly source background music and sound effects for video compositions without manual catalog browsing
  • Generate voiceover and captions from script text using TTS and the audio engine
  • Apply corrective color grading or creative visual treatments to footage based on user feedback (dark, flat, boring, retro)
  • Resolve brand logos, icons, and images from official sources or HyperFrames catalogs
  • Upscale or reframe existing media and maintain asset inventory across multiple projects
Who it's for
  • HyperFrames project developers and agents building video compositions
  • Content creators needing quick media sourcing and asset management
  • Developers automating voiceover, captioning, and audio production workflows
  • Teams managing brand assets and reusable media libraries

media-use FAQ

What is the main verb in this skill?

resolve — a single command that returns one line with the asset path, type, and metadata. All search noise stays on disk.

Can I generate media if the catalog doesn't have what I need?

Yes. The skill generates via TTS, music models, and image generation when catalog search misses. Specify your intent and it will create or find the asset.

How do I handle vague user feedback like 'the footage looks dark' or 'needs a retro feel'?

Read media-treatments.md, inspect the actual footage, choose one primary intent, and apply a matching recipe or custom treatment using `hyperframes media-treatment` with deterministic persistence.

Can I reuse assets across multiple projects?

Yes. The skill supports reuse rules, adoption, and inventory management. List candidates with `--candidates` before resolving fresh to judge fit and avoid duplication.

What audio capabilities does the skill include?

Voiceover (TTS via HyperFrames free path or local Kokoro), transcription, captions, and background removal all run through one shared audio engine.

Full instructions (SKILL.md)

Source of truth, from heygen-com/hyperframes.


name: media-use description: Agent Media OS, the single skill for every media need in 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.

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: 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.

Resolve — the one verb

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.

TypeOne-line intent
bgmbackground music (HeyGen catalog, 10k+ tracks)
sfxsound effects (bundled 19-file library + catalog)
imagephotos, backgrounds (HeyGen asset search, 75k+ vectors)
iconicons, symbols (transparent)
logoofficial brand marks (theSVG → GitHub avatar → favicon; never redrawn)
voiceTTS voiceover (HeyGen free-usage path; optional local Kokoro)
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 iconresolve real icons
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 bedbgm
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 + auth, provider table, RAM ladders, --local-only, --providerreferences/setup-providers.md
remembered preferences + frozen recipes (user memory)references/memory.md
ownership matrix, usage stats, telemetry, privacy (maintainer-facing)references/meta.md