luma SKILL.md skillA

luma from sutchan/agent-skills-hub is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add sutchan/agent-skills-hub/luma@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
sutchan/agent-skills-hub
Path
skills/luma/SKILL.md
Versions recorded
5
Latest version
v1.0.0, committed Oct 17, 2026
First version recorded
Aug 22, 2026
Size
8,923 bytes
Repository stars
2
License
MIT

Luma AI 工艺技能——用 Luma 的 AI 模型(Dream Machine / Ray / 图生视频)生成与编辑视频。当用户想要 AI 生成视频、图生视频、镜头运动控制,或了解 Luma 的生成档位与权利时使用。智能体撰写简报并在已连接时驱动 API;人工评判输出。须披露 AI 生成画面。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# luma

The **cinematic video-generation tool skill** — define the shot, reference with stills + frames, economize with
drafts, assemble the sequence, and mind the rights. The agent briefs (and can drive the API where connected);
the **human judges every clip**; **WoopSocial publishes**. (Ships with `tools/integrations/luma.md`.)

## The POV: shots, not films — and drafts, not gambles
Dream Machine's 2026 edge is per-shot cinematic quality: Ray3 was the first "reasoning" video model (it
interprets, generates, self-evaluates, retries), with 16-bit HDR, keyframes, character reference, and Modify
(restyle real footage, keep the performance). The top-1% operator holds four truths the marketing softens.
**(1) Generations are shots, not films:** 5–10 seconds each, Extend degrades past the initial clip — a brand
film is a shot list, generated shot-by-shot and **assembled in an editor** with **sound added in post** (no
native audio; that's Veo/Kling territory). **(2) Draft first, always:** iterate cheap in Draft Mode, Hi-Fi
master only the winner — because HDR at 1080p runs ~16× standard credits and monthly credits expire at reset.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add sutchan/agent-skills-hub/luma@sha256:dc5aa3ba8a8f8f79

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_4cw3o3ythfnqst7f.svg)](https://markdownregistry.com/a/art_4cw3o3ythfnqst7f)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Aug 22, 2026 and Oct 17, 2026, about one every 14 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-10-17 b913806 8,923 BA view · diff
v1.0.02026-10-07 ab00264 8,308 BA view · diff
v1.0.02026-08-22 725c5cd 8,314 BA view · diff
v1.0.02026-08-22 13607aa 8,340 BA view · diff
v1.0.02026-08-22 a6a02f8 8,492 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8923 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

sutchan/agent-skills-hub · 2 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4cw3o3ythfnqst7f
GET https://markdownregistry.com/api/v1/resolve?ref=sutchan/agent-skills-hub/luma
GET https://markdownregistry.com/api/v1/blob/dc5aa3ba8a8f8f790fc20ec252dd127e8eda4b1c1786d30fceedc71d0c0fbdf6

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from sutchan/agent-skills-hub

AGENTS.md@docs AGENTS.md file
sutchan/agent-skills-hub · docs/AGENTS.md
git:20261103.bc94795 · audit A · 2 stars
DESIGN.md@prototype DESIGN.md file
sutchan/agent-skills-hub · prototype/DESIGN.md
git:20261105.5aba97e · audit A · 2 stars
ad-creative SKILL.md skill
sutchan/agent-skills-hub · skills/ad-creative/SKILL.md · 规模化生成与迭代广告创意文案、标题与变体
v2.12.2 · audit A · 2 stars
ads-creative SKILL.md skill
sutchan/agent-skills-hub · skills/ads-creative/SKILL.md · 审计付费广告的文案、图片、视频、钩子、概念、格式覆盖、平台原生契合度、信息匹配、创意疲劳、可访问性与政策合规。适用于创意审计、广告文案评审、视频评审、图片评审或生产优先级排定。
git:20261017.b913806 · audit A · 2 stars
agent-browser SKILL.md skill
sutchan/agent-skills-hub · skills/agent-browser/SKILL.md · 为 AI 智能体提供浏览器自动化操作能力
git:20261103.e8273b5 · audit A · 2 stars
agent-development SKILL.md skill
sutchan/agent-skills-hub · skills/agent-development/SKILL.md · 构建与开发 AI 智能体的方法与最佳实践
v0.1.0 · audit A · 2 stars
ai-avatar-video SKILL.md skill
sutchan/agent-skills-hub · skills/ai-avatar-video/SKILL.md · 通过 inference.sh CLI 创建 AI 数字人与口播视频。推荐 P-Video-Avatar(最快最便宜、内置 TTS),另支持 OmniHuman、Fabric、PixVerse;音频可用 Inworld…
git:20261007.ab00264 · audit A · 2 stars
ai-image-generation SKILL.md skill
sutchan/agent-skills-hub · skills/ai-image-generation/SKILL.md · 通过 RunComfy CLI 使用 FLUX 2、GPT Image 2、Seedream、Nano Banana 等 11+ 模型生成和编辑 AI 图像。支持文生图、图生图、局部重绘、LoRA、文字渲染。
git:20261007.ab00264 · audit A · 2 stars
ai-music SKILL.md skill
sutchan/agent-skills-hub · skills/ai-music/SKILL.md · 通过 runcomfy CLI 在 RunComfy 上生成 AI 音乐——智能路由到合适的音乐模型目录。覆盖 ElevenLabs AI 音乐生成( premium 人声轨)与 ACE Step…
git:20261007.ab00264 · audit A · 2 stars
ai-research-reproduction SKILL.md skill
sutchan/agent-skills-hub · skills/ai-research-reproduction/SKILL.md · Rigor Reproduce 兼容技能,面向 README 优先的深度学习仓库复现。当用户想按 README 复现实验结果、核对环境/依赖/随机种子、定位复现差异时使用。
git:20261007.ab00264 · audit A · 2 stars
ai-video-generation-runcomfy SKILL.md skill
sutchan/agent-skills-hub · skills/ai-video-generation-runcomfy/SKILL.md · 通过本地 RunComfy CLI 在 RunComfy 目录中智能路由生成 AI 视频,覆盖文生视频、图生视频、参考视频转视频以及 Veo 视频扩展。作为智能路由器,根据用户真实意图匹配最合适的视频生成模型,并附上对应模型的提示词写法。
git:20261007.ab00264 · audit A · 2 stars
ai-video-generation SKILL.md skill
sutchan/agent-skills-hub · skills/ai-video-generation/SKILL.md · 通过 inference.sh CLI 使用 Google Veo、Seedance、Wan、Grok 等 40+ 模型生成 AI 视频。支持文生视频、图生视频、参考生视频、视频编辑、唇形同步、数字人动画、视频放大、拟音。适用于社媒视频、营…
git:20261007.ab00264 · audit A · 2 stars

Every file in sutchan/agent-skills-hub

Other files named luma

luma SKILL.md skill
social-media-skills/skills · skills/luma/SKILL.md · The Luma Dream Machine craft skill — generate cinematic AI video shots (Ray3: text-to-video, image-to-video, keyframes…
v1.0.0 · audit A · 251 stars

Browse by kind, by grade A, or by owner.