← All skills
media-use
65 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a media skill usually calls an AI service over the internet.
By heygen-com/hyperframes (GitHub) · media · 82,066 stars · scanned at commit b28bd2b
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
Works with any agent that supports SKILL.md skills.
What this skill can do
Downloads and installs other software
The author does not mention this.
Found in 140 places.
Show 17 more
- skills/media-use/SKILL.md, line 30
| Transcripts | `npx hyperframes transcribe` (Parakeet or whisper) | | | - skills/media-use/SKILL.md, line 31
| Cutouts | | Video: `--type cutout` | `npx hyperframes remove-background` | - skills/media-use/SKILL.md, line 32
| Grades, LUTs, looks | `npx hyperframes media-treatment` | | | - skills/media-use/SKILL.md, line 34
**Sign in.** Every time a request needs a HeyGen model or the catalog, run `npx hyperframes auth status` first. Not signed in: tell the person in one line that - skills/media-use/SKILL.md, line 38
**HeyGen.** `npx hyperframes media-use generate` makes images, shots, talking photos, voices and music on the sign-in alone. Helpers and direct recipes need the - skills/media-use/SKILL.md, line 44
Feedback that footage is dark, flat or dull, should feel retro or printed, needs a face hidden, or needs a reveal is media intent. Inspect the real `<img>`/`<vi - skills/media-use/audio/references/bgm.md, line 6
- **Local generation (Lyria → MusicGen) — the fallback when there is no credential** (or when asked for explicitly). Generate a WAV from a mood prompt. There is - skills/media-use/audio/references/bgm.md, line 8
> **Run the Preflight first — no credential is not a green light to silently generate locally.** Before generating, complete the sign-in **Preflight** (see `../ - skills/media-use/audio/references/bgm.md, line 72
| Neither Lyria nor MusicGen can run (generate) | `bgm` disabled with a `pip install …` hint. Voice + SFX still render. | - skills/media-use/audio/references/captions/authoring.md, line 5
**The live search is the source of truth for what the registry has.** The table(s) below are a hand-maintained sample and under-cover by design: run `npx hyperf - skills/media-use/audio/references/captions/authoring.md, line 120
Before building caption styles from scratch, check the registry — 15 ready-to-use caption components cover the most common styles. Install with `npx hyperframes - skills/media-use/audio/references/captions/authoring.md, line 123
npx hyperframes catalog --tag caption-style # list all caption components - skills/media-use/audio/references/captions/authoring.md, line 124
npx hyperframes add caption-highlight # install a specific one - skills/media-use/audio/references/captions/transcript-handling.md, line 39
npx hyperframes transcribe audio.mp3 --model medium.en - skills/media-use/audio/references/captions/transcript-handling.md, line 77
npx hyperframes transcribe transcript-openai.json - skills/media-use/audio/references/captions/transcript-handling.md, line 90
npx hyperframes transcribe transcript-groq.json - skills/media-use/audio/references/remove-background.md, line 6
npx hyperframes remove-background subject.mp4 -o transparent.webm # default: VP9 + alpha
and 120 more places
Runs commands on your computer
The author does not mention this.
Found in 85 places.
Show 17 more
- skills/media-use/audio/scripts/carve.mjs, line 27
import { execFileSync } from "node:child_process"; - skills/media-use/audio/scripts/carve.mjs, line 246
raw = execFileSync( - skills/media-use/audio/scripts/carve.test.mjs, line 3
import { execFileSync } from "node:child_process"; - skills/media-use/audio/scripts/carve.test.mjs, line 193
execFileSync(process.execPath, [join(link, "carve.mjs")], { encoding: "utf-8" }); - skills/media-use/audio/scripts/extract-audio-data.py, line 60
result = subprocess.run(cmd, capture_output=True) - skills/media-use/audio/scripts/gemini-pipeline.test.mjs, line 6
import { spawnSync } from "node:child_process"; - skills/media-use/audio/scripts/gemini-pipeline.test.mjs, line 78
const result = spawnSync( - skills/media-use/audio/scripts/heygen-tts.test.mjs, line 3
import { spawnSync } from "node:child_process"; - skills/media-use/audio/scripts/heygen-tts.test.mjs, line 17
const run = spawnSync( - skills/media-use/audio/scripts/lib/audio-meta.test.mjs, line 14
import { spawnSync } from "node:child_process"; - skills/media-use/audio/scripts/lib/audio-meta.test.mjs, line 110
const result = spawnSync( - skills/media-use/audio/scripts/lib/bgm.mjs, line 14
import { spawn, spawnSync } from "node:child_process"; - skills/media-use/audio/scripts/lib/bgm.mjs, line 35
return spawnSync(cmd, args, { stdio: "ignore" }).status === 0; - skills/media-use/audio/scripts/lib/bgm.mjs, line 45
return spawnSync(cmd, args, { stdio: "ignore" }).status === 0; - skills/media-use/audio/scripts/lib/gemini-auth.mjs, line 1
import { spawnSync } from "node:child_process"; - skills/media-use/audio/scripts/lib/gemini-auth.test.mjs, line 1
import { spawnSync } from "node:child_process"; - skills/media-use/audio/scripts/lib/gemini-auth.test.mjs, line 84
const result = spawnSync(cmd, args, { encoding: "utf8", timeout: 30_000 });
and 65 more places
Can call paid AI services billed to you
The author does not mention this. Expected for a media skill.
Found in 10 places.
Show 7 more
- skills/media-use/audio/scripts/gemini-pipeline.test.mjs, line 38
assert.equal(url, 'https://generativelanguage.googleapis.com/v1beta/interactions'); - skills/media-use/audio/scripts/lib/gemini-tts.mjs, line 42
"https://generativelanguage.googleapis.com/v1beta/interactions", - skills/media-use/audio/scripts/lib/gemini-tts.test.mjs, line 46
assert.equal(url, "https://generativelanguage.googleapis.com/v1beta/interactions"); - skills/media-use/audio/scripts/lib/tts.mjs, line 235
from elevenlabs.client import ElevenLabs - skills/media-use/audio/scripts/lib/tts.mjs, line 236
from elevenlabs import save - skills/media-use/audio/scripts/lyria-recipe.py, line 55
from google import genai - skills/media-use/audio/scripts/lyria-recipe.py, line 56
from google.genai import types
Sends data to these websites: generativelanguage.googleapis.com, api.openai.com, api.groq.com, api.elevenlabs.io
The author does not mention this. Expected for a media skill.
Found in 10 places.
Show 7 more
Safer alternatives
Low-risk skills in the same category (media) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'media-use' ] || [ -L ~/.agents/skills/'media-use' ]; then echo 'A skill folder named media-use already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/heygen-com/hyperframes' "$d" && git -C "$d" checkout --quiet 'b28bd2b3482a6bcb04d0d0ba0eaee74fbb965455' -- 'skills/media-use' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/media-use' ~/.agents/skills/'media-use' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'media-use' ~/.claude/skills/'media-use' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for heygen-com/hyperframes shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/heygen-com/hyperframes/)
Score history
| Date | Version | Score |
|---|
| 2026-11-10 | b28bd2b | 65 |
| 2026-11-08 | 0f5914d | 65 |
| 2026-11-06 | cfa0d0c | 45 |