minimax-h3
Skill3 starsChanged 3 months agoMITView on GitHub
Write MiniMax H3 video generation prompts from a VideoProjectSpec. Use when a video project targets MiniMax H3 (Hailuo) and needs a mode-selected, grammar-compliant prompt for text-to-video, first-frame, last-frame, first-last-frame, or Ref2VA generation, including reference asset roles, 4-15 second duration handling, and 32 kHz stereo audio direction. Works in Claude Code, Codex, Cursor, and any agent that can read local files.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- ryannel/skillstheir own version, first seen Nov 15, 2026
- calesthio/OpenMontagetheir own version, first seen Nov 9, 2026
- OpenMontageInc/OpenMontagetheir own version, first seen Nov 8, 2026
- Gopyr/gopyr-skills-hubtheir own version, first seen Oct 11, 2026
- teskor-hub/minimax-h3-skilltheir own version, first seen Sep 19, 2026
- mini-yifan/open-source-video-gen-skilltheir own version, first seen Sep 8, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- calesthio/OpenMontage★ 81ksame name
- OpenMontageInc/OpenMontage★ 81ksame name
- mini-yifan/open-source-video-gen-skill★ 21same name
- teskor-hub/minimax-h3-skill★ 9same name
- badgids/Story-Film-Skills★ 4same name
- aleiby/claude-skills★ 1same name
- ryannel/skills★ 1same name
- Gopyr/gopyr-skills-hub★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- llms.txtllms.txt
- seedance-minimax-promptsSkill
- seedance-2.5Skill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 10 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
10
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
All facts below are from the official MiniMax H3 repository (source_url: https://github.com/MiniMax-AI/MiniMax-H3, checked_at: 2026-08-19).
- Distinctive: line 45
H3-Context-IR and H3-Regenerate-2K are not open-sourced: Never claim the complete 2K pipeline is locally open-sourced.
- Very specific: line 55
Every dynamic capability claim carries a source: Use source_url: https://github.com/MiniMax-AI/MiniMax-H3 and checked_at: 2026-08-19 for …
- Very specific: line 122
Write camera motion as natural English: motion type + optional amplitude + optional speed (e.g.
- Distinctive: line 127
Put on-screen text in English double quotation marks, verbatim.
- Distinctive: line 143
Keep the duration inside 4–15 s and state it explicitly.
- Distinctive: line 152
Don't write a prompt for a duration outside 4–15 s.
- Distinctive: line 153
Don't claim the full 2K pipeline is locally open-sourced, or that H3-Context-IR / H3-Regenerate-2K are open-sourced.
- Distinctive: line 155
Don't exceed Ref2VA limits (9 images / 3 videos / 3 audio / 12 files).
- Distinctive: line 156
Don't use video or audio references in FL2VA modes.
- Distinctive: line 157
Don't invent API endpoints, pricing, or third-party capabilities.
- Distinctive: line 158
Don't copy MiniMax's prompt-skill files verbatim.
- Very specific: line 160
Don't use movie/TV/brand IP, celebrities, or unlicensed assets in examples.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
MiniMax H3 Prompt Writing
Turn a VideoProjectSpec (see schemas/video-project.schema.json) into a
MiniMax H3 generation prompt. The full grammar lives in
models/minimax-h3/prompt-grammar.md; read it before writing a prompt. This
skill is written in this repository's own words and does not copy MiniMax's
prompt-skill files.
When to use
- The project targets MiniMax H3 (
spec.model == "minimax-h3"). - You need one of the five official H3 modes:
text-to-video,first-frame,last-frame,first-last-frame, orref2va. - You have reference assets (keyframe images, style images, reference videos, audio) that must be wired into the prompt with correct roles.
Official capability facts
All facts below are from the official MiniMax H3 repository (source_url: https://github.com/MiniMax-AI/MiniMax-H3, checked_at: 2026-08-19).
| Capability | Official value |
| Output duration | 4–15 seconds (hard limit) |
| Output audio | Native 32 kHz stereo, generated together with video |
| Output resolution | 768p shorter side by default (H3-Base); 2K via H3-Regenerate-2K |
| Output frame rate | 24 FPS |
| Aspect ratios | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 (and others) |
| Multimodal context | Text, images, video, and audio understood together |
| FL2VA modes | 0 images = text-to-video; 1 image = first-frame or last-frame; 2 images = first-and-last-frame |
| Ref2VA limits | ≤ 9 images, ≤ 3 videos, ≤ 3 audio, total ≤ 12 files; each video/audio clip 2–15 s, total ≤ 15 s |
| H3-Context-IR | Hosted only, NOT open-sourced; API reproduces the official workflow |
| H3-Regenerate-2K | NOT open-sourced; API available |
| Full 2K pipeline | Requires the official API combined with a locally deployed H3-Base |
Hard rules
- Duration MUST be within 4–15 seconds. A 3-second or 16-second request is invalid. Never clamp, round, or silently adjust a duration.
- H3-Context-IR and H3-Regenerate-2K are not open-sourced. Never claim the complete 2K pipeline is locally open-sourced. Local H3-Base output is 768p; 2K requires the official API.
- Ref2VA file limits are hard: ≤ 9 images, ≤ 3 videos, ≤ 3 audio, total ≤ 12 files. Each reference video/audio clip must be 2–15 seconds long with total reference duration ≤ 15 seconds.
- FL2VA modes accept only keyframe images:
first-frame= exactly one first-frame image,last-frame= exactly one last-frame image,first-last-frame= exactly two images (one first, one last). No video or audio references in FL2VA modes. - Every dynamic capability claim carries a source. Use
source_url: https://github.com/MiniMax-AI/MiniMax-H3andchecked_at: 2026-08-19for facts from the official repo. - No fabricated endpoints or pricing. API endpoints and pricing come only from official MiniMax platform docs; do not invent them.
How to build a VideoProjectSpec
A valid spec needs at least: spec_version, project_goal, model
("minimax-h3"), duration_seconds (4–15), aspect_ratio, creative
(subject, scene, action required), and evidence. Add:
references[]— each entry{id, type, role, uri}. Roles:first-frame,last-frame,style,subject,motion-reference,soundtrack,reference.frames—first_frame_asset_id/last_frame_asset_idpin keyframes;continuity_requirements[]lists what must survive cuts.audio—dialogue(with speaker and language),ambient,music.constraints—preserve[],modify[],forbidden[].shots[]— optional inline timeline; each shot hasdescription,camera,duration_seconds,order.
Mode selection
Pick the mode from the intent and the reference set:
| Intent | Mode |
| New scene from text only, no reference media | text-to-video |
| Start from a specific first frame and develop forward | first-frame |
| Land on a specific final frame at the end | last-frame |
| Interpolate a continuous path between a first and a last frame | first-last-frame |
| Combine images + videos + audio (style, subject, motion, soundtrack) | ref2va |
Mode is inferred from references: no references → text-to-video; one
first-frame image → first-frame; one last-frame image → last-frame; two
keyframe images → first-last-frame; any video/audio reference, more than two
images, or non-keyframe image roles → ref2va.
How to compile the final prompt
- Validate duration — reject anything outside 4–15 s.
- Collect references — merge the manifest and
spec.references; applyframesrole overrides. - Resolve the mode and validate its reference rules.
Build the prompt in English (dialogue stays in its original language inside
<d>):- Base modes (
text-to-video,first-frame,last-frame,first-last-frame): optional alignment instruction line, then exactly three fields in order:integrated_multimodal_description,overall_soundscape,non_diegetic_music. ref2va: exactly six sections in order:subject_definitions,summary,retention_analysis,detailed_description,overall_soundscape,non_diegetic_music.
- Base modes (
- Emit the generation request with
model: "minimax-h3",mode,prompt,reference_manifest,duration_seconds,resolution_hints,provider, andevidence.
Prompt writing rules
[Shot 1]has no timestamp; later shots use[Shot N] At MM:SS.mmm, ...with strictly increasing cut times inside the duration.- State style and initial composition at the start of
[Shot 1](e.g.Live-action, cinematic, a medium-wide shot frames ...). - Write camera motion as natural English: motion type + optional amplitude +
optional speed (e.g.
The camera pushes in with small amplitude at slow speed). - Give speakers stable IDs
(S1),(S2), ...; write dialogue as<d>[Language] exact words</d>and never translate it. - Put on-screen text in English double quotation marks, verbatim.
overall_soundscape: 1–4 sentences of ambience and physical sounds; useN/Aonly for complete silence.non_diegetic_music: 1–3 sentences of instrumentation, tempo, dynamics; useN/Awhen there is no audience-only score.- Ref2VA: define
<Subject N>/<Picture N>/<Video N>/<Audio N>labels once insubject_definitions, keep them consistent across all six sections, and useretention_analysismarkers (fully_preserved,partially_preserved,attribute_transfer,weak_referencefor visible content;fully_copy,partially_copy,reference,weak_referencefor audio). - Match the description's timeline to the requested duration; the final shot must land exactly at the end.
Do
- Keep the duration inside 4–15 s and state it explicitly.
- Describe sound in every prompt — H3 generates native 32 kHz stereo audio.
- Preserve dialogue and visible text verbatim in their original language.
- Fold continuity requirements and constraints into the description text.
- Mark anything not in the official repo as "community practice, not official".
Don't
- Don't write a prompt for a duration outside 4–15 s.
- Don't claim the full 2K pipeline is locally open-sourced, or that H3-Context-IR / H3-Regenerate-2K are open-sourced.
- Don't exceed Ref2VA limits (9 images / 3 videos / 3 audio / 12 files).
- Don't use video or audio references in FL2VA modes.
- Don't invent API endpoints, pricing, or third-party capabilities.
- Don't copy MiniMax's prompt-skill files verbatim; write original prompts following this grammar.
- Don't use movie/TV/brand IP, celebrities, or unlicensed assets in examples.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

