h3-prompt-writing SKILL.md skillA
h3-prompt-writing from mini-yifan/open-source-video-gen-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mini-yifan/open-source-video-gen-skill/h3-prompt-writing@git:20260906.fe772b9Pins git:20260906.fe772b9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mini-yifan/open-source-video-gen-skill
- Path
skills/h3-prompt-writing/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260906.fe772b9, committed Sep 6, 2026
- First version recorded
- Aug 30, 2026
- Size
- 6,213 bytes
- Repository stars
- 40
- License
- a license file GitHub does not identify
Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, defining reference labels, or when the caller hands off a structured handoff (the production's own shot/segment notes, or a minimax-h3 brief) after choosing a workflow. Do not SSH, pick ComfyUI workflows, or submit GPU jobs.
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
# H3 Prompt Writing This skill writes the prompt body only. Connecting to SeetaCloud, choosing U03/U06/U02, acceleration, upload, and download belong to [`minimax-h3`](../minimax-h3/SKILL.md). It is portable to any agent that can read local files and requires no external API calls, MiniMax Hub tools, or proprietary runtime. The `agents/openai.yaml` file only adds optional ChatGPT/Codex UI metadata and does not restrict the skill to OpenAI agents. ## Workflow 1. If the caller passed a **structured handoff** — the production's own shot/segment notes, or a `minimax-h3` brief — read `references/comfy-handoff.md`, lock `prompt_mode` from it, and apply its override table. Do not re-guess the mode from the images alone. 2. Otherwise identify the input mode: T2VA, I2VA, FL2VA, L2VA, or full-reference Ref2VA. Use only `references/base-en.txt` or `references/ref-en.txt` — do not apply Comfy patches. 3. For base text/keyframe modes, follow `references/base-en.txt`. 4. For full-reference mode, follow `references/ref-en.txt`. 5. Preserve the exact field names, section order, labels, and timing notation from the selected guide. ## Base Modes …
Read the whole file at its exact version.
How to install
mdr add mini-yifan/open-source-video-gen-skill/h3-prompt-writing@sha256:687a373bdbfc9023The line at the top of this page pins the label git:20260906.fe772b9, 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.
[](https://markdownregistry.com/a/art_dza6nxrqd2wb3bfk)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 30, 2026 and Sep 6, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260906.fe772b9 latest | 2026-09-06 | fe772b9 | 6,213 B | A | view · diff |
| git:20260904.ec83cad | 2026-09-04 | ec83cad | 6,122 B | A | view · diff |
| git:20260901.d472b7a | 2026-09-01 | d472b7a | 4,980 B | A | view · diff |
| git:20260830.8cf2ae7 | 2026-08-30 | 8cf2ae7 | 4,801 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6213 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
mini-yifan/open-source-video-gen-skill · 40 stars · license a license file GitHub does not identify · pushed 2026-09-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_dza6nxrqd2wb3bfk GET https://markdownregistry.com/api/v1/resolve?ref=mini-yifan/open-source-video-gen-skill/h3-prompt-writing GET https://markdownregistry.com/api/v1/blob/687a373bdbfc902300ac45deca0d26cf83b89e046f73c0de53dabc14a858b32f
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 mini-yifan/open-source-video-gen-skill
Every file in mini-yifan/open-source-video-gen-skill