Agent skill

Hyperframes Media

by waker240 in waker240/FullVideoProductionSkill

Prepare Fish official-API narration, OpenAI word timestamps, and reviewed user-supplied local music/SFX for HyperFrames.

Apache-2.0Auto-check: notesMedia & Creative

Install Hyperframes Media

skills CLI
$ npx skills add waker240/FullVideoProductionSkill --skill hyperframes-media -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install waker240/FullVideoProductionSkill hyperframes-media --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/waker240/FullVideoProductionSkill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hyperframes-media .claude/skills/hyperframes-media && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hyperframes-media
GitHub stars
196
Token cost
~1.2k tokens
SKILL.md length
443 words
Files
23 (incl. scripts, references, assets)
Skills in repo
13
Repo updated
First seen
Licence
Apache-2.0

At a glance

Prepare Fish official-API narration, OpenAI word timestamps, and reviewed user-supplied local music/SFX for HyperFrames.

  • Tasks that involve Motion graphics
  • SKILL.md covers Requirements and scope, Shared engine, Discovery and approval and Reference guide
  • Calls node and npm; needs FISH_API_KEY and OPENAI_API_KEY
  • Tasks that involve Text to speech and voice

What it does

Hyperframes Media is an agent skill from waker240/FullVideoProductionSkill. Prepare Fish official-API narration, OpenAI word timestamps, and reviewed user-supplied local music/SFX for HyperFrames. Also covers captions, optional stock APIs and background removal. No private service, browser-session proxy, voice, or music library is bundled.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 26 other files, including scripts, reference files and assets (for example `assets/sfx/CREDITS.md`, `assets/sfx/manifest.json` and `references/audio-review-and-revision.md`).

It sits in Media & Creative, covering Motion graphics, Text to speech and voice and Image editing. It works with HeyGen and OpenAI. The repository describes itself as: 20亿Claude Opus 4.6-4.8的Token. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Motion graphics
  • Tasks that involve Text to speech and voice
  • Tasks that involve Image editing

Example prompts

  • “/hyperframes-media”

Requirements

  • A credential in FISH_API_KEY
  • A credential in OPENAI_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 0223baa. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • FISH_API_KEY
    • OPENAI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hyperframes Media loads about 1.2k tokens when it runs, and up to ~20k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 443 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~20k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:12
    n. The engine loads the video project's `.env`; existing environment values win. Fish uses its official API with `FISH_A

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from waker240/FullVideoProductionSkill at commit 0223baa, republished under its Apache-2.0 licence (© waker240). 443 words, ~1,197 tokens.

Download SKILL.mdSave it as .claude/skills/hyperframes-media/SKILL.md (or your agent's skills folder). This skill also uses 22 other files; get the full folder from GitHub.
name
hyperframes-media
description
Prepare Fish official-API narration, OpenAI word timestamps, and reviewed user-supplied local music/SFX for HyperFrames. Also covers captions, optional stock APIs and background removal. No private service, browser-session proxy, voice, or music library is bundled.

HyperFrames media

Use fish-audio-api for narration and media-use to ingest reviewed local assets. This package supplies workflows and code; users supply accounts, permitted voices, music, sound effects, images and video.

Requirements and scope

Node >=22.20 and FFmpeg/ffprobe must be on PATH. Read requirements before generation. The engine loads the video project's .env; existing environment values win. Fish uses its official API with FISH_API_KEY and FISH_REFERENCE_ID. Word timing uses OpenAI whisper-1 with OPENAI_API_KEY, or an explicitly configured OpenAI-compatible WHISPER_API.

The shared engine performs one POST per requested narration line and one transcription POST. Neither is automatically retried. It preflights both API configurations before creating voice audio. A whole --only tts rerun creates narration again; use the scaffolded paragraph pipeline for cached/surgical revisions. All generated audio needs listening review.

Shared engine

sh
node <MEDIA_DIR>/scripts/audio.mjs --request audio_request.json --hyperframes . --out audio_meta.json --only tts
node <MEDIA_DIR>/scripts/audio.mjs --request audio_request.json --hyperframes . --out audio_meta.json --only bgm,sfx

The second command needs no API credentials. It preserves and validates any existing voice metadata. Example request (all files shown must be supplied by the user):

json
{
  "lang": "zh",
  "fish": {
    "transport": "official-api",
    "request": { "normalize": true, "prosody": { "speed": 1 } }
  },
  "lines": [
    { "id": "s0", "text": "这是一段待审听的旁白。", "sfx": [
      { "name": "confirmation", "path": "library/confirmation.wav", "offset_s": 0.2 }
    ] }
  ],
  "bgm": { "path": "library/underscore.wav", "source": "reviewed-local", "volume": 0.18 }
}

fish.reference_id and fish.model are optional project overrides; no personal voice is supplied. fish.request uses official API fields, such as top-level temperature, top_p, normalize and prosody. The adapter owns text, reference ID and WAV format. It rejects credential-like fields and website backend configuration.

Output freezes assets/voice/<id>.wav and returns voices[].words as {id,text,start,end}. voice_id, fish_model and fish_transport describe the resolved non-secret profile. API keys and error bodies are never persisted. A transcription failure stops delivery with the voice WAV still on disk; do not invent word timing or claim captions are synchronized.

BGM/SFX come only from explicit local paths or the user's project manifest. Missing/non-audio files produce anomalies and are skipped; they never trigger search, generation or a fallback library. Review every anomaly before final delivery. Frozen files have content hashes so repeated filenames do not overwrite unrelated sources.

Show full SKILL.md (152 more words)Show less

Discovery and approval

In a scaffolded project, use npm run audio:discover -- --type sfx --query "confirmation". No review catalogs are included. Install media-use in .agents/skills, or set MEDIA_USE_SKILL_DIR to that skill directory; set MEDIA_CATALOG or pass --catalog for your own workspace-local catalog. Empty search results mean the user must supply or select media. Catalog membership is not approval: audition, record source/license/hash and a review note, then ingest the exact bytes through media-use.

Reference guide

NeedRead
Accounts, environment and optional toolsrequirements
Fish request configurationtts
Words and timingtranscription, TTS to captions
Caption authoring and cleanupauthoring, transcript handling
Local music and sound effectsBGM, SFX
Audition, gain matching, revisionsaudio review
Optional stock APIsstock media
Optional background-removal toolingbackground removal

API credentials do not replace the user's authorization for generation. Stay within the requested scope, preview a short sample, preserve original audio and keep listening/review decisions distinct from technical validation.

© waker240, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 22 other files (scripts, references, assets) in skills/hyperframes-media of waker240/FullVideoProductionSkill.

  • SKILL.md
  • assets/sfx/CREDITS.md
  • assets/sfx/manifest.json
  • references/audio-review-and-revision.md
  • references/bgm.md
  • references/captions/authoring.md
  • references/captions/motion.md
  • references/captions/transcript-handling.md
  • references/remove-background.md
  • references/requirements.md
  • references/sfx-prompting.md
  • references/sfx.md
  • references/stock-media-apis.md
  • references/transcribe.md
  • references/tts-to-captions.md
  • references/tts.md
  • scripts
  • … and 6 more

Open the folder on GitHubat commit 0223baa

Compare with similar skills

Hyperframes Media next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hyperframes Media compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hyperframes Media this skillwaker240/FullVideoProductionSkill196—~1.2kAutomated safety check: NotesApache-2.0
Super Video MakerBomx/super-video-maker-skill305—~11kAutomated safety check: NotesNone
Motion Videobestagentkits/motion-video-skill113—~1.5kAutomated safety check: PassMIT
Hyperframes CLIaiskillstore/marketplace4301 repos~2.7kAutomated safety check: PassNone
Hyperframesscott-fryxell/brayness124—~3.2kAutomated safety check: PassMIT
Hyperframes Mediacosmicstack-labs/mercury-agent-skills476—~1.7kAutomated safety check: PassMIT

Similar skills

  • Super Video Maker

    Bomx/super-video-maker-skill

    End-to-end AI video production skill for agentic frameworks.

    305 GitHub stars~11k tokensUpdated 1 mo ago
    Media & CreativeAuto-check: notes
  • Motion Video

    bestagentkits/motion-video-skill

    Produce beat-synced 1080p motion-graphic videos in HyperFrames (HTML + GSAP) with an AI voice-over, Vietnamese karaoke captions, SFX and generated music, in one of two proven styles (glass keynote…

    113 GitHub stars~1.5k tokensUpdated 9 days ago
    Media & CreativeAuto-check passed
  • Hyperframes CLI

    aiskillstore/marketplace

    Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish…

    430 GitHub starsUsed in 1 repo~2.7k tokens
    Media & CreativeAuto-check passed
  • Hyperframes

    scott-fryxell/brayness

    Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML.

    124 GitHub stars~3.2k tokensUpdated 9 days ago
    Media & CreativeAuto-check passed
  • Hyperframes Media

    cosmicstack-labs/mercury-agent-skills

    Asset preprocessing for HyperFrames compositions — local text-to-speech narration (Kokoro-82M, no API key), audio/video transcription (Whisper), and background removal for transparent overlays…

    476 GitHub stars~1.7k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Hyperframes Media

    boraoztunc/skills

    Asset preprocessing for HyperFrames compositions — text-to-speech narration (Kokoro), audio/video transcription (Whisper), and background removal for transparent overlays (u2net).

    393 GitHub starsUsed in 2 repos~3.7k tokens
    Media & CreativeAuto-check passed

More from waker240/FullVideoProductionSkill

All 13 skills in this repo
  • Hyperframes Animation

    waker240/FullVideoProductionSkill

    Build deterministic animation for HyperFrames using motion rules, transitions, scene blueprints, and runtime adapters.

    196 GitHub stars~2.4k tokensUpdated 11 days ago
    Auto-check passed
  • Hyperframes Creative

    waker240/FullVideoProductionSkill

    Develop video direction, typography, color, visual mechanisms, storyboards, and asset prompts.

    196 GitHub stars~3k tokensUpdated 11 days ago
    Auto-check passed
  • Media Use

    waker240/FullVideoProductionSkill

    Resolve reviewed local BGM, sound effects, images, icons, and brand assets into frozen project files plus a manifest.

    196 GitHub stars~2k tokensUpdated 11 days ago
    Auto-check: notes
  • Music To Video

    waker240/FullVideoProductionSkill

    Build a HyperFrames video around a supplied music track, using measured rhythm and editable visual concepts.

    196 GitHub stars~4.3k tokensUpdated 11 days ago
    Auto-check passed
  • Remotion To Hyperframes

    waker240/FullVideoProductionSkill

    Port an existing Remotion composition to HyperFrames HTML while preserving visible behavior.

    196 GitHub stars~2.4k tokensUpdated 11 days ago
    Auto-check passed
  • Hyperframes

    waker240/FullVideoProductionSkill

    Plan, author, review, and render HTML videos with HyperFrames.

    196 GitHub stars~1.9k tokensUpdated 11 days ago
    Auto-check passed

Works with

Questions about Hyperframes Media

What does Hyperframes Media do?

Prepare Fish official-API narration, OpenAI word timestamps, and reviewed user-supplied local music/SFX for HyperFrames. Hyperframes Media is an agent skill from waker240/FullVideoProductionSkill. Prepare Fish official-API narration, OpenAI word timestamps, and reviewed user-supplied local music/SFX for HyperFrames.

When should I use Hyperframes Media?

Hyperframes Media fits situations like: tasks that involve Motion graphics; tasks that involve Text to speech and voice; tasks that involve Image editing.

How do I install Hyperframes Media in Claude Code?

Run `npx skills add waker240/FullVideoProductionSkill --skill hyperframes-media -a claude-code`. Or copy the skill folder (skills/hyperframes-media in waker240/FullVideoProductionSkill) into .claude/skills/hyperframes-media in your project. Claude Code loads it when a task matches its description.

How do I install Hyperframes Media in Codex?

Run `npx skills add waker240/FullVideoProductionSkill --skill hyperframes-media -a codex`. Or copy the skill folder (skills/hyperframes-media in waker240/FullVideoProductionSkill) into .agents/skills/hyperframes-media in your project. Codex loads it when a task matches its description.

Can I use Hyperframes Media in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add waker240/FullVideoProductionSkill --skill hyperframes-media -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hyperframes-media, .gemini/skills/hyperframes-media, .github/skills/hyperframes-media and .opencode/skills/hyperframes-media in your project.

What does Hyperframes Media need to run?

Going by SKILL.md and its folder, Hyperframes Media needs the command-line tools its instructions call (node and npm) and credentials named FISH_API_KEY and OPENAI_API_KEY. Our summary lists: A credential in FISH_API_KEY; A credential in OPENAI_API_KEY.

Does Hyperframes Media access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Hyperframes Media safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Hyperframes Media use?

Hyperframes Media is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hyperframes Media use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 19k tokens, read only when the agent opens those files.

What are the alternatives to Hyperframes Media?

Skills that share tags, products or a category with Hyperframes Media: Super Video Maker (Bomx/super-video-maker-skill, 305 stars), Motion Video (bestagentkits/motion-video-skill, 113 stars), Hyperframes CLI (aiskillstore/marketplace, 430 stars) and Hyperframes (scott-fryxell/brayness, 124 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hyperframes Media?

waker240 (a GitHub user) maintains it in waker240/FullVideoProductionSkill, which has 196 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 26, 2026.

Source: waker240/FullVideoProductionSkill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.