Agent skill

Minimax H3 Colab

by killkli in killkli/minimax-h3-colab-skill

Create short MiniMax H3 reference-to-video clips from one or more local images through Google Colab CLI.

No licenceAuto-check passedMedia & Creative

Install Minimax H3 Colab

skills CLI
$ npx skills add killkli/minimax-h3-colab-skill --skill minimax-h3-colab -a claude-code

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

GitHub CLI
$ gh skill install killkli/minimax-h3-colab-skill minimax-h3-colab --agent claude-code

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

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

Facts

Skill name
minimax-h3-colab
GitHub stars
110
Token cost
~743 tokens
SKILL.md length
342 words
Files
10 (incl. scripts, assets)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Create short MiniMax H3 reference-to-video clips from one or more local images through Google Colab CLI.

  • Works in 5 steps: Inspect the requested images and any… → If the user supplied a prompt file, pass… → Check Colab access and balance with… → …
  • A user asks for image-guided H3 video generation
  • SKILL.md covers Workflow and Operational limits
  • Runs Shell and Python scripts from its folder; calls python3

What it does

Minimax H3 Colab is an agent skill from killkli/minimax-h3-colab-skill. Create short MiniMax H3 reference-to-video clips from one or more local images through Google Colab CLI. Use when a user asks for image-guided H3 video generation or a sequential batch of clips.

Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including scripts and assets (for example `README.en.md`, `README.md` and `README.zh-TW.md`).

It sits in Media & Creative, covering Jupyter notebooks and AI video generation. It works with MiniMax. The repository describes itself as: Standalone Codex skill for MiniMax H3 Colab reference-to-video generation.

When your agent uses it

  • A user asks for image-guided H3 video generation
  • A sequential batch of clips

Example prompts

  • “/minimax-h3-colab”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

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

  1. Inspect the requested images and any supplied prompt file. Keep image order stable: image 1 maps to , image 2 to , through image 9.
  2. If the user supplied a prompt file, pass it through unchanged. Otherwise write a complete Ref2VA prompt with subject_definitions, summary…
  3. Check Colab access and balance with python3 scripts/runner.py usage --json. Sufficient compute units do not guarantee that Colab will…
  4. Put the jobs in a UTF-8 JSON manifest and run one batch. The runner uploads each job's images and prompt, executes the bundled notebook…
  5. Confirm each output exists and report its local path. Preserve completed clips if a later job fails.

What it can do on your machine

Read from SKILL.md and the folder at commit 7768ebf. 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/ (Shell and Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

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

  • Network

    No URLs in SKILL.md.

    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

Minimax H3 Colab loads about 743 tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 342 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~743

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 342 words (~743 tokens).

“Use the bundled notebook and scripts/runner.py to generate Ref2VA video from local reference images. The Colab CLI must be installed and authenticated with an available compute-unit balance and GPU allocation.”

— opening of SKILL.md by killkli
name
minimax-h3-colab

Read the full SKILL.md on GitHub

Files

SKILL.md and 9 other files (scripts, assets) in the repository root of killkli/minimax-h3-colab-skill.

  • SKILL.md
  • .gitignore
  • README.en.md
  • README.md
  • README.zh-TW.md
  • assets/MiniMax_H3_Turbo_Colab.ipynb
  • install.sh
  • run_colab_inference.sh
  • scripts/runner.py
  • tests/test_runner.py

Open the folder on GitHubat commit 7768ebf

Compare with similar skills

Minimax H3 Colab 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.

Minimax H3 Colab compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Minimax H3 Colab this skillkillkli/minimax-h3-colab-skill110—~743Automated safety check: PassNone
Minimax H3 Video Reversegnipbao/minimax-h3-video-reverse-skill230—~2.2kAutomated safety check: PassMIT
H3 Prompt Writingvllm-project/vllm-omni7.1k6 repos~744Automated safety check: PassApache-2.0
Handdrawn Live Video Generatortl2012tl/comfyUI-llama-TE2414 repos~1.5kAutomated safety check: PassNone
ComfyUI Local DriverSlavaSexton/ComfyUI-Agent-Kit105—~12kAutomated safety check: PassApache-2.0
Minimax H3 Text Video Promptunknowlei/minimax-h3-opencode-skills122—~2.3kAutomated safety check: PassMIT

Similar skills

  • Minimax H3 Video Reverse

    gnipbao/minimax-h3-video-reverse-skill

    先复述参考视频内容与叙事逻辑,和用户确认理解后,再反推 MiniMax H3 文生视频或逐镜图生视频提示词。Use when the user asks to reverse-engineer a video into prompts, reconstruct shots, extract first/end-frame prompts, adapt a reference to H3, or…

    230 GitHub stars~2.2k tokensUpdated 8 days ago
    Media & CreativeAuto-check passed
  • H3 Prompt Writing

    vllm-project/vllm-omni

    Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA.

    7.1k GitHub starsUsed in 6 repos~744 tokens
    Media & CreativeAuto-check passed
  • Handdrawn Live Video Generator

    tl2012tl/comfyUI-llama-TE

    For creators making surreal short videos that blend rough glowing hand-drawn animation with live-action spaces.

    241 GitHub starsUsed in 4 repos~1.5k tokens
    Media & CreativeAuto-check passed
  • ComfyUI Local Driver

    SlavaSexton/ComfyUI-Agent-Kit

    Drives a local ComfyUI install over its HTTP API to generate and edit images, video and audio, with per-model prompt recipes and workflow guidance.

    105 GitHub stars~12k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Minimax H3 Text Video Prompt

    unknowlei/minimax-h3-opencode-skills

    Downstream MiniMax H3 specialist for professional text-to-video (T2VA) prompts using the official three-field format.

    122 GitHub stars~2.3k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Long-Form H3 Director

    karuvanan/MiniMax-H3-Director-Cut-Studio

    Plans long-form MiniMax H3 video productions as Sequence, Shot, and Segment contracts that stay continuous across generation windows.

    131 GitHub stars~1.5k tokensUpdated yesterday
    Media & CreativeAuto-check passed

Works with

Questions about Minimax H3 Colab

What does Minimax H3 Colab do?

Create short MiniMax H3 reference-to-video clips from one or more local images through Google Colab CLI. Minimax H3 Colab is an agent skill from killkli/minimax-h3-colab-skill. Create short MiniMax H3 reference-to-video clips from one or more local images through Google Colab CLI.

When should I use Minimax H3 Colab?

Minimax H3 Colab fits situations like: A user asks for image-guided H3 video generation; A sequential batch of clips.

How do I install Minimax H3 Colab in Claude Code?

Run `npx skills add killkli/minimax-h3-colab-skill --skill minimax-h3-colab -a claude-code`. Or copy the skill folder (the killkli/minimax-h3-colab-skill repository) into .claude/skills/minimax-h3-colab in your project. Claude Code loads it when a task matches its description.

How do I install Minimax H3 Colab in Codex?

Run `npx skills add killkli/minimax-h3-colab-skill --skill minimax-h3-colab -a codex`. Or copy the skill folder (the killkli/minimax-h3-colab-skill repository) into .agents/skills/minimax-h3-colab in your project. Codex loads it when a task matches its description.

Can I use Minimax H3 Colab 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 killkli/minimax-h3-colab-skill --skill minimax-h3-colab -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/minimax-h3-colab, .gemini/skills/minimax-h3-colab, .github/skills/minimax-h3-colab and .opencode/skills/minimax-h3-colab in your project.

What does Minimax H3 Colab need to run?

Going by SKILL.md and its folder, Minimax H3 Colab needs a shell and Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3; A Bash shell.

Does Minimax H3 Colab access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Minimax H3 Colab 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 Minimax H3 Colab use?

No licence was found for Minimax H3 Colab or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Minimax H3 Colab use?

About 743 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Minimax H3 Colab?

Skills that share tags, products or a category with Minimax H3 Colab: Minimax H3 Video Reverse (gnipbao/minimax-h3-video-reverse-skill, 230 stars), H3 Prompt Writing (vllm-project/vllm-omni, 7.1k stars), Handdrawn Live Video Generator (tl2012tl/comfyUI-llama-TE, 241 stars) and ComfyUI Local Driver (SlavaSexton/ComfyUI-Agent-Kit, 105 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Minimax H3 Colab?

killkli (a GitHub user) maintains it in killkli/minimax-h3-colab-skill, which has 110 GitHub stars. The repository was last updated on September 26, 2026.

Source: killkli/minimax-h3-colab-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.