H3lite

STRONG · 86
Community indexed

A hardware-aware Codex skill for local MiniMax H3 video generation through ComfyUI

Verified installs0
Stars126
Version1.0.0
Quality93/100 · Excellent
Trust86/100 · Review then install
Audit92/100 · Safe to try

Supply asset profile

Design and creative production

Design assets, images, video, audio, multimodal media, presentation, and creative production skills.

Browse track

Scenario

Design and creative

I need my agent to produce design assets, UI directions, presentations, or creative media workflows.

Agent fit

Claude Code + OpenAI Agents + CLI

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add Rimagination/h3lite

Maintenance

fresh

7d since push

Risk

Safe to try

Stars/forks activity: 126 stars, 21 forks; issue activity unavailable in current metadata

GitHub quality

126

93/100 Quality · 89/100 Trust

Coverage tags

DesignDesign and creativedesign-creativecodexvideo-generation

Review notes

Stars/forks activity: 126 stars, 21 forks; issue activity unavailable in current metadata

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Excellent
93

High-confidence pick with strong adoption and healthy maintenance signals.

Trust

Review then install
86

Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.

Audit

Safe to try
92

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

OpenAgentSkill Trust Score v5

Agent install candidate

Use as the primary candidate after human or sandbox review.

PythonCodexClaude CodeCursorOpenAgentSkill CLI

Stars

126 GitHub stars

Repo activity

126 stars, 21 forks

Maintenance

7d since push

License

MIT

Install

npx skills add Rimagination/h3lite

Install safety

standard package or runtime install path

Permission surface

no high-risk permission surface in public metadata

Agent outcomes

No agent outcome data yet

Docs

Strong README/SKILL.md context

Risk summary

Low metadata risk

  • Stars/forks activity: 126 stars, 21 forks; issue activity unavailable in current metadata

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is declared
  • No Agent Proven outcome evidence yet

Agent-readable metadata

Machine-readable decision data for this skill.

Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.

Open JSON

Suited tasks

  • Design and creative workflows
  • Claude Code teams
  • builders willing to evaluate younger projects
  • Inspect visual requirements

Suited agents

PythonCodexClaude CodeCursorOpenAgentSkill CLIOpenAI AgentsCLI

Install decision

Command
npx skills add Rimagination/h3lite
Policy
review
Human review
yes

Trust and risk

Trust
86/100
Audit
92/100
Risk level
Safe to try

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add Rimagination/h3lite

Do not use when

  • teams that need a vendor-supported SLA
  • high-compliance environments without internal security review
  • No major risk signals from current metadata
  • Stars/forks activity: 126 stars, 21 forks; issue activity unavailable in current metadata
  • Production credentials, payments, or irreversible account changes without explicit human review

Agent safety v2

76/100 · Review before install

Reviewedreview

Good audit and safety signals with no high-risk permission hints in public metadata.

Review the audit page, then allow agent install in a sandboxed workflow.

Resolve via API

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

medium

Filesystem access

Skill may read or write project files, documents, generated artifacts, or local workspace state.

  • Stars/forks activity: 126 stars, 21 forks; issue activity unavailable in current metadata

Install targets

Install this skill in your agent workflow

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install rimagination-h3lite

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use H3lite in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20H3lite%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/rimagination-h3lite/install
Install command: npx skills add Rimagination/h3lite
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Agent prompt

Use H3lite for this task. Review https://www.openagentskill.com/api/skills/rimagination-h3lite/install, then install with: npx skills add Rimagination/h3lite

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Agent fit

96/100

Design and creative

Platforms

Python, Claude Code, OpenAI Agents

Audit report

Safe to try · 92/100

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

View audit reportView eval report

Agent decision cockpit

Primary pick for Design and creative

Use this as a leading candidate, then validate the README and install path in your own agent stack.

96
Readiness
Adopt
Stage

Role in stack

Primary pick

Primary fit

Design and creative

Trust label

Production-ready

Install path

Command ready

Use when

  • Design and creative workflows
  • Claude Code teams
  • builders willing to evaluate younger projects

Evidence

  • recent repository activity
  • install command or GitHub repo available
  • 93/100 quality profile
  • 27 OpenAgentSkill engagement events

review first

  • No major risk signals from current metadata

Implementation path

  1. 1Install it in a sandbox agent and run one Design and creative task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Review then install

Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.

86
OpenAgentSkill Trust Score

GitHub adoption

INFO

126 GitHub stars

Stars/forks activity

CHECK

126 stars, 21 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

7d since push

License clarity

PASS

MIT

Good signals

  • Manually verified listing
  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Install command has no obvious high-risk pattern
  • Outcome loop is ready but needs first real agent run

Review before install

  • Stars/forks activity: 126 stars, 21 forks; issue activity unavailable in current metadata
  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Use as the primary candidate after human or sandbox review.

Quality profile

Excellent candidate for agent workflows

High-confidence pick with strong adoption and healthy maintenance signals.

93
GitHub stars
126
Freshness
7d ago
Install ready
Yes
License
MIT

Workflow fit

Use this skill in these scenarios

Workflow fit

Add it to a complete workflow

Alternative shortlist

Compare before you install

Similar skills that may fit this task.

Compare all

Overview

# H3 Lite

<p align="center"> <img src="assets/h3-lite-hero.gif" alt="H3 Lite — MiniMax H3 本地部署与视频生成 Skill" width="100%"> </p>

<p align="center"> <img alt="License MIT" src="https://img.shields.io/badge/License-MIT-1F5E4A?style=for-the-badge"> <img alt="Hosts Codex" src="https://img.shields.io/badge/Hosts-Codex-4B6B8A?style=for-the-badge"> <img alt="Route Low VRAM Fast" src="https://img.shields.io/badge/Route-Low--VRAM%20Fast-D9A441?style=for-the-badge"> </p>

<p align="center"> 中文 | <a href="README.en.md">English</a> | <a href="#参考资料">参考资料</a> </p>

`H3 Lite` 是一个给 Codex、WorkBuddy 等 AI Agent 使用的 MiniMax H3 本地视频生成 Skill。你只需要用自然语言描述想看的画面,Agent 就会根据电脑配置选择 ComfyUI 路线、准备必要组件、生成带原生声音的视频并检查结果。

它面向第一次接触本地视频生成的用户:你不必先学习 ComfyUI 节点,也不必自己判断模型、文本编码器、LoRA、双 VAE 和低显存参数怎样组合。

## 一分钟交给 Agent

把下面这句话发给 Codex 或 WorkBuddy:

```text 请帮我安装 H3 Lite,并根据我的电脑配置准备本地 MiniMax H3 视频生成环境: https://github.com/Rimagination/h3lite ```

这“一分钟”指把任务和安装位置交给 Agent。模型文件较大,首次下载和部署时间取决于网络、硬盘与电脑配置。

如果不想占用系统盘,把目标位置写进同一条消息:

```text 请把 MiniMax H3 和 ComfyUI 安装到 F:\MiniMax-H3;如果那里已经有健康环境就直接复用。 ```

## 基本配置

当前默认支持 **Windows + NVIDIA CUDA** 的本地低显存路线。已实测验证的下限是 **RTX 3060 Ti 8 GB 显存 + 16 GB 系统内存**;这只代表当前 W4A8 快速路线可以运行,不代表所有 8 GB 显卡都能得到相同结果。仍建议配 32 GB 系统内存和 SSD;12–16 GB 显存会更宽裕。

6 GB 显存属于社区实验路线,建议配 32 GB 系统内存;低于 6 GB 显存或低于 16 GB 系统内存时,不建议下载和部署这套工作流。

AMD/ROCm、RTX 50 系列新架构和原生 BF16 H3 不在当前默认验证范围内,Agent 会先做兼容性判断,不会仅凭显存容量承诺“能跑”。详细硬件、组件和分辨率说明见 [`references/deployment-matrix.md`](references/deployment-matrix.md)。 默认从 `fast` 路线开始。质量档位、I2V/Ref2VA、人脸质量和时间预估由 Agent 根据实际环境自动选择;这些判断不会给视频推理图增加额外采样或模型。

## 常见视频分辨率推荐

社区通常推荐视频模型使用 32 的倍数作为宽高。未指定分辨率时,本 skill 默认使用 `640×352`;指定分辨率时按用户设置执行。

| 用途/比例 | 尺寸 | MP | H3 使用建议 | |---|---:|---:|---| | 横屏 16:9(低显存快速档) | `640×352` | 0.23 | 8 GB 显存首选 | | 横屏 16:9(实验档) | `736×416` | 0.31 | 提升细节和动作遵循度 | | 横屏 16:9(约 0.4MP) | `864×480` | 0.42 | 质量更好但更慢 | | 横屏 16:9(高分辨率) | `1280×704` | 0.90 | 接近 720P,8 GB 显存不建议直接生成 | | 竖屏 9:16(低显存) | `352×640` | 0.23 | 适合短视频竖屏草稿 | | 竖屏 9:16(中等质量) | `416×73

Platform compatibility

pythonFULL

Technical details

Version
1.0.0
License
MIT
Last updated
Aug 18, 2026
Published
Aug 15, 2026

Frameworks & tools

Python

Decision snapshot

Primary pick

96
Ready
Adopt
Stage

recent repository activity

Audit

Install review

Install and adoption review

92
Safe to try
Security
90/100
Maintenance
100/100
Install
92/100
Open full auditView eval report

Agent-proven evidence

Agent-proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
Success rate
Recent failure
Outcomes
0
Output quality
Failed
0
Not relevant
0
Installs
0
Risk blocked
0
Setup needed
0
Production
0

No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.

Install

Add to agent workflow

Free and open source. Review the report before installing into production agents.

Growth loop

Share kit

X

Scenario-led draft for H3lite, ready for a manual X post.

Curator note
H3lite: A hardware-aware Codex/WorkBuddy skill that automates local MiniMax H3 video generation throu...

126 stars

https://www.openagentskill.com/skills/rimagination-h3lite?ref=x
Open X draft
Optional reply with install command
Listing + install path for H3lite:
https://www.openagentskill.com/skills/rimagination-h3lite?ref=x

Install: npx skills add Rimagination/h3lite

Listing source

Community indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This Community indexed listing is attributed to Rimagination but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/rimagination-h3lite?metric=listed&label=Listed)](https://www.openagentskill.com/skills/rimagination-h3lite)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/rimagination-h3lite?metric=trust&label=Trust)](https://www.openagentskill.com/skills/rimagination-h3lite)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/rimagination-h3lite?metric=audit&label=Audit)](https://www.openagentskill.com/skills/rimagination-h3lite/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/rimagination-h3lite?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/rimagination-h3lite)

Author

R

Rimagination

@rimagination

Health signals

GitHub stars
126
Quality score
57/100
Last GitHub push
Aug 15, 2026
Framework hints
1
OpenAgentSkill views
27
Install copies
0
Outbound clicks
0

Community signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & safety

Review then install

86
  • GitHub adoption126 GitHub starsINFO
  • Stars/forks activity126 stars, 21 forks; issue activity unavailable in current metadataCHECK
  • Recent maintenance7d since pushPASS
  • License clarityMITPASS
  • README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
  • Dependency/runtime riskno major dependency risk hints in public metadataPASS