Agent skill

Hyperframes CLI

by OpenMinis in OpenMinis/MinisSkills

HyperFrames CLI and Minis rendering. An agent skill from OpenMinis/MinisSkills.

MITAuto-check passedMedia & Creative

Install Hyperframes CLI

skills CLI
$ npx skills add OpenMinis/MinisSkills --skill hyperframes-cli -a claude-code

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

GitHub CLI
$ gh skill install OpenMinis/MinisSkills hyperframes-cli --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/OpenMinis/MinisSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/hyperframes-cli .claude/skills/hyperframes-cli && 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-cli
GitHub stars
440
Token cost
~3.5k tokens
SKILL.md length
809 words
Files
12 (incl. scripts, references)
Skills in repo
49
Repo updated
First seen
Licence
MIT

At a glance

HyperFrames CLI and Minis rendering. An agent skill from OpenMinis/MinisSkills.

  • Works in 5 steps: Scaffold — npx hyperframes init my-video → Write — author HTML composition (see the… → Lint — npx hyperframes lint → …
  • CLI commands — init
  • SKILL.md covers Environment Check (Run First), Workflow, Scaffolding and Linting, plus 7 more sections
  • Runs Python scripts from its folder; calls npx and python3; reaches cdn.jsdelivr.net

What it does

Hyperframes CLI is an agent skill from OpenMinis/MinisSkills. HyperFrames CLI and Minis rendering. Use for: (1) CLI commands — init, lint, preview, render, transcribe, tts, doctor; (2) Minis iOS rendering via hf-render.py (setviewport + minis-browser-use + ffmpeg, no Chrome required); (3) Website-to-video workflow — capture a URL and produce a professional MP4 in 7 steps; (4) Preview/snapshot compositions at correct resolution. Trigger when user says render, init project, lint, transcribe audio, generate TTS, capture a website for video, or run any hyperframes CLI command.

Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts and reference files (for example `hf-render.py`, `references/website-to-video/step-1-capture.md` and `references/website-to-video/step-2-design.md`).

It sits in Media & Creative, covering Motion graphics, Browser automation and Linting and formatting. It works with HeyGen, iOS and FFmpeg. The repository describes itself as: Skills collection for Minis. The licence is MIT.

When your agent uses it

  • CLI commands — init
  • Minis iOS rendering via hf-render.py (setviewport + minis-browser-use + ffmpeg
  • No Chrome required)
  • Website-to-video workflow — capture a URL and produce a professional MP4 in 7 steps

Example prompts

  • “Use the hyperframes-cli skill to hyperframe CLI and Minis rendering. An agent skill from OpenMinis/MinisSkills”
  • “/hyperframes-cli”

Requirements

  • Python 3
  • Node.js
  • Docker

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Scaffold — npx hyperframes init my-video
  2. Write — author HTML composition (see the hyperframes skill)
  3. Lint — npx hyperframes lint
  4. Preview — npx hyperframes preview
  5. Render — npx hyperframes render

What it can do on your machine

Read from SKILL.md and the folder at commit cb72d91. 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 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • npx
    • python3

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • cdn.jsdelivr.net

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Hyperframes CLI loads about 3.5k tokens when it runs, and up to ~17k if it reads all its reference files. Until then it costs about 134 tokens; SKILL.md has 809 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~134
When it runs · the whole SKILL.md, loaded when a task matches
~3.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~17k

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 passed

The automated check found no risky patterns in SKILL.md.

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 OpenMinis/MinisSkills at commit cb72d91, republished under its MIT licence (© OpenMinis). 809 words, ~3,498 tokens.

Download SKILL.mdSave it as .claude/skills/hyperframes-cli/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
hyperframes-cli
description
HyperFrames CLI and Minis rendering. Use for: (1) CLI commands — init, lint, preview, render, transcribe, tts, doctor; (2) Minis iOS rendering via hf-render.py (set_viewport + minis-browser-use + ffmpeg, no Chrome required); (3) Website-to-video workflow — capture a URL and produce a professional MP4 in 7 steps; (4) Preview/snapshot compositions at correct resolution. Trigger when user says render, init project, lint, transcribe audio, generate TTS, capture a website for video, or run any hyperframes CLI command.
version
1.0.0
source
Adapted from the official HyperFrames CLI and website-to-hyperframes skills by HeyGen. Originals…

HyperFrames CLI

Environment Check (Run First)

Before any task, verify the environment is ready:

bash
python3 /var/minis/skills/hyperframes-cli/scripts/check-env.py

This checks:

  • minis-browser-use — built-in Minis tool for browser control (required for rendering and preview)
  • ffmpeg — video encoding
  • hyperframes skill — composition authoring
  • hyperframes-cli skill — this skill itself (hf-render.py)

If anything is missing, run with --fix to auto-install:

bash
python3 /var/minis/skills/hyperframes-cli/scripts/check-env.py --fix

Or install a specific skill manually:

bash
# From heygen-com/hyperframes (HyperFrames skills)
python3 /var/minis/skills/hyperframes-cli/scripts/install-skill.py \
  hyperframes --repo heygen-com/hyperframes --subdir skills

# From OpenMinis/MinisSkills (community skills)
python3 /var/minis/skills/hyperframes-cli/scripts/install-skill.py notion-hub

If minis-browser-use is missing: it is a Minis built-in tool. Update Minis App to the latest version — it ships with the app and cannot be installed separately.

After installing missing skills, restart the conversation for them to take effect.

Everything runs through npx hyperframes. Requires Node.js >= 22 and FFmpeg.

Workflow

  1. Scaffold — npx hyperframes init my-video
  2. Write — author HTML composition (see the hyperframes skill)
  3. Lint — npx hyperframes lint
  4. Preview — npx hyperframes preview
  5. Render — npx hyperframes render

Lint before preview — catches missing data-composition-id, overlapping tracks, unregistered timelines.

Scaffolding

bash
npx hyperframes init my-video                        # interactive wizard
npx hyperframes init my-video --example warm-grain   # pick an example
npx hyperframes init my-video --video clip.mp4        # with video file
npx hyperframes init my-video --audio track.mp3       # with audio file
npx hyperframes init my-video --non-interactive       # skip prompts (CI/agents)

Templates: blank, warm-grain, play-mode, swiss-grid, vignelli, decision-tree, kinetic-type, product-promo, nyt-graph.

init creates the right file structure, copies media, transcribes audio with Whisper, and installs AI coding skills. Use it instead of creating files by hand.

Linting

bash
npx hyperframes lint                  # current directory
npx hyperframes lint ./my-project     # specific project
npx hyperframes lint --verbose        # info-level findings
npx hyperframes lint --json           # machine-readable

Lints index.html and all files in compositions/. Reports errors (must fix), warnings (should fix), and info (with --verbose).

Previewing

bash
npx hyperframes preview                   # serve current directory
npx hyperframes preview --port 4567       # custom port (default 3002)

Hot-reloads on file changes. Opens the studio in your browser automatically.

🍎 Minis (iOS) Alternative — Preview & Snapshot

Set viewport to composition size first, then navigate. This gives accurate preview at the correct resolution.

bash
# Preview at correct resolution
minis-browser-use set_viewport --width 960 --height 540
minis-browser-use navigate --url minis://workspace/<project>/index.html

# Snapshot at specific timestamps
minis-browser-use execute_js --script 'window.__hf.seek(2.5)'
minis-browser-use screenshot   # saves to /var/minis/browser/

Always set_viewport before navigating — otherwise the browser uses the phone's default viewport and the composition renders at the wrong scale.

Rendering

bash
npx hyperframes render                                # standard MP4
npx hyperframes render --output final.mp4             # named output
npx hyperframes render --quality draft                # fast iteration
npx hyperframes render --fps 60 --quality high        # final delivery
npx hyperframes render --format webm                  # transparent WebM
npx hyperframes render --docker                       # byte-identical
FlagOptionsDefaultNotes
--outputpathrenders/name_timestamp.mp4Output path
--fps24, 30, 603060fps doubles render time
--qualitydraft, standard, highstandarddraft for iterating
--formatmp4, webmmp4WebM supports transparency
--workers1-8 or autoautoEach spawns Chrome
--dockerflagoffReproducible output
--gpuflagoffGPU-accelerated encoding
--strictflagoffFail on lint errors
--strict-allflagoffFail on errors AND warnings

Quality guidance: draft while iterating, standard for review, high for final delivery.

🍎 Minis (iOS) — hf-render.py

npx hyperframes render requires Puppeteer + Chrome (unavailable on iOS). Use the Minis-native renderer instead — it uses minis-browser-use set_viewport to lock the browser to the exact composition size, captures frames at Retina resolution, and encodes with FFmpeg.

One-line render:

bash
python3 /var/minis/skills/hyperframes-cli/hf-render.py <project_dir>

Full options:

bash
python3 /var/minis/skills/hyperframes-cli/hf-render.py <project_dir> \
  --fps 24 \
  --quality high \
  --output /var/minis/workspace/<project>/renders/output.mp4
FlagOptionsDefaultNotes
--fps24, 302430fps increases render time ~25%
--qualitydraft, standard, highstandarddraft=2Mbps, standard=4Mbps, high=8Mbps
--outputpath<project>/renders/output.mp4Output path
--width / --heightpxauto from data-width/heightOverride composition size

How it works:

  1. set_viewport W H — locks browser CSS viewport to composition size
  2. Navigate to minis://workspace/<rel-path>/index.html (supports subdirectories)
  3. Wait for window.__hf ({ duration, seek }) — works with GSAP and pure CSS animations
  4. For each frame: execute_js __hf.seek(t) → screenshot --with-base64 → save JPEG
  5. Frames captured at Retina resolution (e.g. 2880×1620 for 960×540 @ DPR=3)
  6. ffmpeg lanczos-downscale → MP4 (h264_videotoolbox, fallback libx264)
  7. set_viewport --reset always runs — even on error or Ctrl-C

Performance: ~10fps capture (~12s for a 5s@24fps video on iPhone).

Show full SKILL.md (317 more words)Show less

Requirements for index.html:

The composition MUST expose window.__hf at the end of its <script> block:

js
// Required: __hf render protocol
const DURATION = 5.0; // seconds — must match your actual animation length
window.__hf = {
  get duration() { return DURATION; },
  seek(t) { tl.pause(); tl.seek(Math.max(0, Math.min(t, DURATION)), false); }
};
window.__playerReady = true;
window.__renderReady = true;

DURATION must equal the GSAP timeline's actual duration. If ambient animations use repeat, calculate carefully:

js
// WRONG — glow-gold ends at 0.4 + 2.0*(2+1) = 6.4s, timeline extends past 5s → black frames
tl.to("#glow", { duration: 2.0, repeat: 2, yoyo: true }, 0.4);

// CORRECT — calculate max repeats that fit within DURATION
const DURATION = 5.0;
tl.to("#glow", {
  duration: 2.0,
  repeat: Math.floor((DURATION - 0.4) / 2.0) - 1,  // = 1 repeat, ends at 4.4s
  yoyo: true
}, 0.4);

HTML template rules (required for correct rendering):

  • Fixed width/height on html, body, and #stage — match data-width/data-height
  • No <meta name="viewport"> — the renderer sets viewport externally via set_viewport
  • No scale wrappers, no transform: scale() on the stage — these break pixel accuracy
  • Project must be under /var/minis/workspace/ — the renderer converts the path to a minis:// URL
  • Multi-scene layout: use position:absolute; inset:0 per scene — see note below

⚠️ Minis layout difference from standard HyperFrames: The standard skill says .scene-content should use width:100%; height:100%. In Minis/iOS WebKit, set_viewport sets the CSS viewport width but iOS Safari's height is influenced by system UI, so height:100% on a flex container can exceed the stage height. Content then centers relative to that oversized container and lands outside the screenshot crop.

Fix: for compositions with multiple sequential scenes, give each scene its own position:absolute; inset:0 container (see the hyperframes skill → "Multi-scene compositions" section). For single-scene compositions, width:100%; height:100% is fine.

html
<!-- Correct HTML structure -->
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<!-- NO viewport meta -->
<style>
  html, body { margin: 0; padding: 0; width: 960px; height: 540px; overflow: hidden; }
  #stage { width: 960px; height: 540px; position: relative; overflow: hidden; }
</style>
</head>
<body>
<div id="stage" data-composition-id="my-comp" data-width="960" data-height="540">
  <!-- content -->
</div>
<script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script>
<script>
  window.__timelines = window.__timelines || {};
  const DURATION = 5.0;
  const tl = gsap.timeline({ paused: true });
  // ... tweens ...
  window.__timelines["my-comp"] = tl;

  window.__hf = {
    get duration() { return DURATION; },
    seek(t) { tl.pause(); tl.seek(Math.max(0, Math.min(t, DURATION)), false); }
  };
  window.__playerReady = true;
  window.__renderReady = true;
</script>
</body>
</html>

Transcription

bash
npx hyperframes transcribe audio.mp3
npx hyperframes transcribe video.mp4 --model medium.en --language en
npx hyperframes transcribe subtitles.srt   # import existing
npx hyperframes transcribe subtitles.vtt
npx hyperframes transcribe openai-response.json

Text-to-Speech

bash
npx hyperframes tts "Text here" --voice af_nova --output narration.wav
npx hyperframes tts script.txt --voice bf_emma
npx hyperframes tts --list  # show all voices

Troubleshooting

bash
npx hyperframes doctor       # check environment (Chrome, FFmpeg, Node, memory)
npx hyperframes browser      # manage bundled Chrome
npx hyperframes info         # version and environment details
npx hyperframes upgrade      # check for updates

Run doctor first if rendering fails. Common issues: missing FFmpeg, missing Chrome, low memory.

Other

bash
npx hyperframes compositions   # list compositions in project
npx hyperframes docs           # open documentation
npx hyperframes benchmark .    # benchmark render performance

Website → Video Workflow

Turn any URL into a video in 7 steps. Read each step's reference file before executing it.

StepWhatReference
1Capture website (screenshots, tokens, assets)references/website-to-video/step-1-capture.md
2Write DESIGN.md (brand colors, fonts, style)references/website-to-video/step-2-design.md
3Write SCRIPT.md (narration, scene durations)references/website-to-video/step-3-script.md
4Write STORYBOARD.md (per-beat creative direction)references/website-to-video/step-4-storyboard.md
5Generate VO + map word timestamps to beatsreferences/website-to-video/step-5-vo.md
6Build compositions (use the hyperframes skill)references/website-to-video/step-6-build.md
7Lint, snapshot, render, handoffreferences/website-to-video/step-7-validate.md

Visual techniques (SVG drawing, Canvas 2D, 3D, typing, MotionPath, Lottie): references/website-to-video/techniques.md

Quick formats
TypeDurationBeatsNarration
Social ad (IG/TikTok)10-15s3-4Optional
Product demo30-60s5-8Full
Feature announcement15-30s3-5Full
Brand reel20-45s4-6Optional

Landscape: 1920×1080 · Portrait: 1080×1920 · Square: 1080×1080

© OpenMinis, MIT. 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 11 other files (scripts, references) in hyperframes-cli of OpenMinis/MinisSkills.

  • SKILL.md
  • hf-render.py
  • references/website-to-video/step-1-capture.md
  • references/website-to-video/step-2-design.md
  • references/website-to-video/step-3-script.md
  • references/website-to-video/step-4-storyboard.md
  • references/website-to-video/step-5-vo.md
  • references/website-to-video/step-6-build.md
  • references/website-to-video/step-7-validate.md
  • references/website-to-video/techniques.md
  • scripts/check-env.py
  • scripts/install-skill.py

Open the folder on GitHubat commit cb72d91

Compare with similar skills

Hyperframes CLI 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 CLI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hyperframes CLI this skillOpenMinis/MinisSkills440—~3.5kAutomated safety check: PassMIT
Content To Videoarchitectds/modeldock117—~2.4kAutomated safety check: PassApache-2.0
Hyperframes CLIcoleam00/hyperframes-ai-video-generation148—~1.6kAutomated safety check: PassNone
Hyperframes CLInateherkai/hyperframes-student-kit1.2k3 repos~1.2kAutomated safety check: PassCustom licence
Qiaomu Cutjoeseesun/qiaomu-cut-skill369—~6.8kAutomated safety check: NotesMIT
Super Video MakerBomx/super-video-maker-skill305—~11kAutomated safety check: NotesNone

Similar skills

  • Content To Video

    architectds/modeldock

    Turn arbitrary source content (README, article, story, slides, deck, data/report, product description, tutorial text, audio/transcript, or a bare topic) into a finished, high-quality MP4 video.

    117 GitHub stars~2.4k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Hyperframes CLI

    coleam00/hyperframes-ai-video-generation

    HyperFrames CLI tool — hyperframes init, lint, inspect, preview, render, transcribe, tts, doctor, browser, info, upgrade, compositions, docs, benchmark.

    148 GitHub stars~1.6k tokensUpdated 4 mo ago
    Media & CreativeAuto-check passed
  • Hyperframes CLI

    nateherkai/hyperframes-student-kit

    HyperFrames CLI tool — hyperframes init, lint, preview, render, transcribe, tts, doctor, browser, info, upgrade, compositions, docs, benchmark.

    1.2k GitHub starsUsed in 3 repos~1.2k tokens
    Media & CreativeAuto-check passed
  • Qiaomu Cut

    joeseesun/qiaomu-cut-skill

    把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video—including one-line requests such as “制作一个科普视频:介绍…

    369 GitHub stars~6.8k tokensUpdated 9 days ago
    Media & CreativeAuto-check: notes
  • 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
  • Showtime

    FavioVazquez/showtime

    A skill your agent uses when the user wants a video made, edited or finished: a launch or promo, product demo, explainer, trailer or teaser, tutorial or walkthrough, a screen recording turned into a…

    158 GitHub stars~3k tokensUpdated yesterday
    Media & CreativeAuto-check passed

More from OpenMinis/MinisSkills

All 49 skills in this repo
  • Android UI Automation

    OpenMinis/MinisSkills

    Automate Android apps that have no public API or web version by driving the UI layer through the Accessibility Service.

    440 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed
  • Codex On Ish

    OpenMinis/MinisSkills

    Install and run OpenAI Codex CLI inside the Minis/iSH Alpine sandbox on iOS, where rustls TLS and async sockets are broken.

    440 GitHub stars~1k tokensUpdated 2 days ago
    Auto-check passed
  • Evidence Chain Builder

    OpenMinis/MinisSkills

    Score a claim against the evidence behind it. An agent skill from OpenMinis/MinisSkills.

    440 GitHub stars~2.4k tokensUpdated 2 days ago
    Auto-check passed
  • Whenpeak

    OpenMinis/MinisSkills

    Predict when a person's brain works best from their sleep, using the WhenPeak performance-intelligence API, and turn it into concrete scheduling advice.

    440 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed
  • Openstreetmap Marker

    OpenMinis/MinisSkills

    Generate a mobile-first, immersive, Amap(Gaode)-style custom landmark marker HTML map for travel itinerary planning, place showcasing, location sharing, etc.

    440 GitHub stars~1.9k tokensUpdated 2 days ago
    Auto-check passed
  • PDF Converter

    OpenMinis/MinisSkills

    Convert documents to PDF via a typst-based pipeline. An agent skill from OpenMinis/MinisSkills.

    440 GitHub stars~2.1k tokensUpdated 2 days ago
    Auto-check passed

Works with

Questions about Hyperframes CLI

What does Hyperframes CLI do?

HyperFrames CLI and Minis rendering. An agent skill from OpenMinis/MinisSkills. Hyperframes CLI is an agent skill from OpenMinis/MinisSkills. HyperFrames CLI and Minis rendering.

When should I use Hyperframes CLI?

Hyperframes CLI fits situations like: CLI commands — init; minis iOS rendering via hf-render.py (setviewport + minis-browser-use + ffmpeg; no Chrome required); website-to-video workflow — capture a URL and produce a professional MP4 in 7 steps.

How do I install Hyperframes CLI in Claude Code?

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

How do I install Hyperframes CLI in Codex?

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

Can I use Hyperframes CLI 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 OpenMinis/MinisSkills --skill hyperframes-cli -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-cli, .gemini/skills/hyperframes-cli, .github/skills/hyperframes-cli and .opencode/skills/hyperframes-cli in your project.

What does Hyperframes CLI need to run?

Going by SKILL.md and its folder, Hyperframes CLI needs Python for the scripts in its folder and the command-line tools its instructions call (npx and python3). Our summary lists: Python 3; Node.js; Docker.

Does Hyperframes CLI access the network?

SKILL.md names 1 domain. In commands or code: cdn.jsdelivr.net; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Hyperframes CLI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. 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 CLI use?

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

How many tokens does Hyperframes CLI use?

About 3.5k tokens (SKILL.md is roughly 14k 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 14k tokens, read only when the agent opens those files.

What are the alternatives to Hyperframes CLI?

Skills that share tags, products or a category with Hyperframes CLI: Content To Video (architectds/modeldock, 117 stars), Hyperframes CLI (coleam00/hyperframes-ai-video-generation, 148 stars), Hyperframes CLI (nateherkai/hyperframes-student-kit, 1.2k stars) and Qiaomu Cut (joeseesun/qiaomu-cut-skill, 369 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hyperframes CLI?

OpenMinis (a GitHub organization) maintains it in OpenMinis/MinisSkills, which has 440 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 5, 2026.

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