media-use · coco-research — Claude Code skill: media for HyperFrames
media-use is a skill for HyperFrames projects that finds music, sound effects, icons and logos, creates voiceover, and edits existing footage.
MIT ★ 328 updated 2026-10-29
npx skills add coco-research/coco --skill media-use -a claude-codeWhat media-use does
Inside a HyperFrames project the skill gives you a single call for media. You name a type (bgm, sfx, image, icon, logo, voice, grade, lut) with a plain-language intent, and get back one line pointing at a frozen local file; the search chatter stays on disk. Music beds and photos come from the HeyGen catalog, sound effects from a bundled library of 19 files. Brand marks are looked up through svgl, simple-icons, a GitHub avatar and a favicon in that order, never redrawn by hand.
When the catalog has nothing, generation kicks in with TTS, music or image models. Voiceover, transcription, captions and background removal share one audio engine, while cut, reframe and transform handle files you already have. --candidates surfaces assets from earlier projects so you can reuse them instead of fetching again.
The heygen CLI has to be installed and signed in before the first run, because resolve talks to it. Confirm the setup with node <SKILL_DIR>/scripts/resolve.mjs --doctor; providers are configured per references/setup-providers.md. Vague complaints about footage also count — dark, flat or boring, a request for a camcorder or print look, a privacy pass — and the skill routes them through references/media-treatments.md.
What it helps with
- pick a background track for a scene and get a ready file
- turn a script into a voiceover with captions
- find an official brand logo without redrawing it
- cut a clip and reframe it for another aspect ratio
- remove the background from a product photo
Example prompts for the agent
- Find
bgmfor the opening scene and drop the file into the project - Turn this script into a voiceover and caption it
- Replace the emoji in that block with real icons from the catalog
How to install media-use
1Skills CLI (Vercel)
npx skills add coco-research/coco --skill media-use -a claude-code2Manually: put the files in place
~/.claude/skills/media-use/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/media-use/
1Skills CLI (Vercel)
npx skills add coco-research/coco --skill media-use -a codex2Manually: put the files in place
.agents/skills/media-use/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add coco-research/coco --skill media-use -a cursor2Manually: put the files in place
.cursor/skills/media-use/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install coco-research/coco systems/hyperframes/skills/media-use2Manually: put the files in place
.github/skills/media-use/SKILL.md1Skills CLI (Vercel)
npx skills add coco-research/coco --skill media-use -a gemini-cli2Platform CLI
gemini skills install https://github.com/coco-research/coco --path systems/hyperframes/skills/media-useManually: put the files in place
.devin/skills/media-use/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about media-use
How do I install media-use in Claude Code?
Run npx skills add coco-research/coco --skill media-use -a claude-code. The skill file lands at ~/.claude/skills/media-use/SKILL.md.
What does media-use do?
It handles media for HyperFrames: resolves music, sound effects, images, icons, logos and voice through resolve, falls back to generation when the catalog misses, and edits or voices existing files.
What do I need before the first run?
Install the heygen CLI and sign in, then check the environment with node <SKILL_DIR>/scripts/resolve.mjs --doctor.
Source text
SKILL.md · MIT
--- 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. --- # 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 `node <SKILL_DIR>/scripts/resolve.mjs --doctor`. Setup and providers: `references/setup-providers.md`. ## Resolve — the one verb ```bash node <SKILL_DIR>/scripts/resolve.mjs --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, 10k+ tracks) | | `sfx` | sound effects (bundled 19-file library + catalog) | | `image` | photos, backgrounds (HeyGen asset search, 75k+ vectors) | | `icon` | icons, symbols (transparent) | | `logo` | official brand marks (svgl → simple-icons → 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`. ## 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 detected | Offer | | -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ | | On-screen text / a script with no voiceover | TTS voiceover (audio engine) | | Emoji or a `<div>` styled as an icon | resolve real `icon`s | | 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). ## Where to look — read only the file your task needs | 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` |
© coco-research · MIT · coco-research/coco
Similar skills
All skills for Design →media-use by other authors comes first.