.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/hyperframes/media-use
home/skills/heygen-com/hyperframes/media-use
heygen-com avatar

media-use

byheygen-com· 46 skills

Installs

179k

Stars

38k

Forks

3.6k

Category

Generative Media

View on GitHub

TL;DR

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.

How to install media-use?

heygen-com/hyperframes/media-use
$npx -y skills add heygen-com/hyperframes --skill media-use

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Use this skill

Run `npx skills use "https://github.com/heygen-com/hyperframes" --skill "heygen-com/hyperframes/media-use"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the whole pack

Use the skills in "https://github.com/heygen-com/hyperframes" that are relevant to the current task. Run `npx skills add "https://github.com/heygen-com/hyperframes"` and select the relevant skills, then follow their instructions.

Files · 1

View on GitHub
SKILL.md
1# media-use
2 
3The media OS for HyperFrames: resolve · generate · operate · remember — every media type, one skill, zero context noise.
4 
5First 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`.
6 
7## Resolve — the one verb
8 
9```bash
10node <SKILL_DIR>/scripts/resolve.mjs --type <type> --intent "<description>" --project <dir>
11```
12 
13Returns one line: `resolved <id> → <path> (<type>, <metadata>)`. All search noise stays on disk.
14 
15| Type | One-line intent |
16| ------- | ----------------------------------------------------------------------------------- |
17| `bgm` | background music (HeyGen catalog, 10k+ tracks) |
18| `sfx` | sound effects (bundled 19-file library + catalog) |
19| `image` | photos, backgrounds (HeyGen asset search, 75k+ vectors) |
20| `icon` | icons, symbols (transparent) |
21| `logo` | official brand marks (svgl → simple-icons → GitHub avatar → favicon; never redrawn) |
22| `voice` | TTS voiceover (HeyGen free-usage path; optional local Kokoro) |
23| `grade` | measured correction candidate; broad polish/stylization follows Media Treatments |
24| `lut` | user-provided or explicitly chosen reusable validated `.cube` file |
25 
26Before resolving fresh, list reusable candidates with `--candidates` and judge fit yourself — reuse rules, all flags, ingest (`--from`), and adopt are in `references/resolve.md`.
27 
28## Treat broad visual feedback as media intent
29 
30When a user explicitly asks to fix, polish, stylize, obscure, emphasize, or
31reveal photographic media, read `references/media-treatments.md` even if they
32do not name color grading or an effect. Inspect the real `<img>`/`<video>`,
33choose one primary intent, then use deterministic persistence and verification.
34Use a matching recipe as an optional tested seed, or inspect
35`hyperframes media-treatment --capabilities --json`, then request one relevant
36family/effect with `--capability <id>` and assemble a custom treatment from
37canonical controls. Never load `--all` for ordinary authoring. A treatment may
38compose correction, a preset, finishing, compatible shader effects, supported
39keyframes, and optional Registry overlays. Add only source-justified bounded
40tuning and compatible parts, never effects merely to make the result look more
41sophisticated. Persist the final combined payload with
42`hyperframes media-treatment`.
43 
44Use one progressively escalating workflow. For video, inspect one labeled
45early/middle/late contact sheet rather than reading frames separately. Apply one
46candidate and inspect one after-sheet for ordinary correction or polish.
47Escalate to individual frames or moving draft evidence only when the result is
48ambiguous, temporal, stylized, LUT-based, HDR/LOG-sensitive, private, or
49brand-critical.
50 
51For ordinary correction or polish, persist the final treatment's
52preset/adjustment JSON.
53Do not generate a `.cube` LUT merely to encode exposure, shadows, contrast, or
54warmth. Use a LUT only when the user supplies one or the selected treatment
55explicitly owns one. `resolve --type grade --for ... --analyze` is measurement
56evidence, not permission to replace the chosen treatment with a generated LUT.
57Do not recreate supported vignette, grain, blur, pixelate, color, or treatment
58effects with CSS/SVG overlays; that bypasses Studio controls and the canonical
59preview/render shader path.
60 
61## Be proactive — run a media opportunity pass
62 
63The 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.
64 
65Surface an opportunity only when a concrete signal is present:
66 
67| Signal detected | Offer |
68| -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ |
69| On-screen text / a script with no voiceover | TTS voiceover (audio engine) |
70| Emoji or a `<div>` styled as an icon | resolve real `icon`s |
71| Image that is a placeholder, tiny, or upscaled-looking | a better `image` (and/or upscale — see `references/operations.md`) |
72| Hard scene cuts / transitions with no sound | transition `sfx` |
73| A piece over ~10s with no music bed | `bgm` |
74| Footage that reads under/over-exposed or color-cast | a corrective grade (inspect it with `hyperframes media-treatment --selector '#hero' --analyze --json`) |
75| Photographic media that feels visually flat or off-topic | one specific source-appropriate preset or custom treatment, with the intended target named |
76| A meaningful media entrance/reveal that feels static | one supported seek-safe treatment animation; preserve color unless the request also justifies a preset |
77 
78Rules 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).
79 
80## Where to look — read only the file your task needs
81 
82| Task | Read |
83| ------------------------------------------------------------------------- | -------------------------------- |
84| resolve / reuse / adopt / ingest, flags, cascade, inventory | `references/resolve.md` |
85| color grading, LUTs, smart grade (`--for`), grade-compare | `references/grading.md` |
86| voiceover / TTS, music, SFX, captions, transcription (audio engine) | `references/audio.md` |
87| cut / reframe / transform existing media, exact error diffusion, HEVC | `references/operations.md` |
88| source-aware creative treatments, realtime effects, overlays, reveals | `references/media-treatments.md` |
89| install + auth, provider table, RAM ladders, `--local-only`, `--provider` | `references/setup-providers.md` |
90| remembered preferences + frozen recipes (user memory) | `references/memory.md` |
91| ownership matrix, usage stats, telemetry, privacy (maintainer-facing) | `references/meta.md` |

Security

Flagged

  • Gen Agent Trust Hubpass
  • Socketwarn
  • Snykfail

Preview

heygen-com/hyperframesheygen-com/hyperframes

$ npx -y skills add heygen-com/hyperframes --skill media-use

▸ installing to .claude/skills…

✓ media-use ready

Repoheygen-com/hyperframes
TypeSkills
CategoryGenerative Media
ForContent Creator
UpdatedJul 2026
License—
First seenJul 26, 2026

Tags

Skill

Related

6 picks
Type
  1. remotion-dev avatarremotion-best-practicesRouter for all Remotion skillsSkillsJul 2026451k4.1k
  2. 101-skills avatarai-image-generationGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI.SkillsJul 2026441k656
  3. heygen-com avatarhyperframes-cliUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes,…SkillsJul 2026296k38k
  4. heygen-com avatarhyperframesMandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or motion graphic, including a promo,…SkillsJul 2026291k38k
  5. heygen-com avatarremotion-to-hyperframesPort an existing Remotion (React) composition''s source to HyperFrames HTML.SkillsJul 2026198k38k
  6. heygen-com avatarhyperframes-coreThe HyperFrames composition contract — build one renderable project.SkillsJul 2026195k38k