h3-prompt-writing
Skill4 starsChanged 3 months agoApache-2.0View on GitHub
Write MiniMax H3 prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA using the required audiovisual fields, keyframe alignment, speaker IDs, dialogue tags, reference labels, and timing.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- glitterpixely/skillstheir own version, first seen Nov 1, 2026
- sethliao/one-person-studiotheir own version, first seen Oct 20, 2026
- himly0302/use-skillstheir own version, first seen Oct 13, 2026
- MiniMax-AI/MiniMax-H3their own version, first seen Oct 8, 2026
- vllm-project/vllm-omnitheir own version, first seen Oct 8, 2026
- SwotAtmk/infinite-creationtheir own version, first seen Sep 28, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- MiniMax-AI/MiniMax-H3★ 11ksame name
- vllm-project/vllm-omni★ 7.8ksame name
- SwotAtmk/infinite-creation★ 56same name
- sjh00/minimax-h3-storyboard-prompt-skills★ 35same name
- mini-yifan/open-source-video-gen-skill★ 21same name
- glitterpixely/skills★ 7same name
- full-aigc-skills/minimax-skills★ 4same name
- himly0302/use-skills★ 4same name
- daha1216/dsh-skill-h3-prompt-writing★ 1same name
- SuperMate-Ai/SuperMate-Harness-System★ 1same name
1 more not listed
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 repository139 other files it gives its agents.
- 3d-animation-short-generatorSkill
- ace-step-xlSkill
- adapt-screenplaySkill
- asset-approvalSkill
- audience-simSkill
- audio-masterSkill
- batch-recoverySkill
- beat-sheetSkill
- book-planSkill
- brand-promo-video-generatorSkill
- campaign-brandSkill
- campaign-deliverySkill
- character-bibleSkill
- character-simSkill
- comfyui-api-v2Skill
- comfyui-assetsSkill
- comfyui-binding-auditSkill
- comfyui-cliSkill
- comfyui-discoverSkill
- comfyui-handoffSkill
- comfyui-mcpSkill
- comfyui-offline-batchSkill
- comfyui-runSkill
- comfyuiSkill
- comfyui-troubleshootSkill
- comfyui-workflowSkill
- content-repurposeSkill
- context-shardsSkill
- continuity-checkSkill
- co-op-game-intro-generatorSkill
- creative-pressure-testSkill
- creative-production-specSkill
- crew-reviewSkill
- decision-tree-interviewSkill
- delivery-qcSkill
- design-systemSkill
- dialogue-audio-authoritySkill
- dialogue-timing-preflightSkill
- dialogue-voiceSkill
- director-bookSkill
- documented-creative-discoverySkill
- edit-assistSkill
- editorial-packageSkill
- editorial-reconciliationSkill
- editor-project-exportSkill
- edit-planSkill
- evidence-researchSkill
- ffmpegSkill
- film-completenessSkill
- film-masterSkill
- generation-budgetSkill
- generation-model-setupSkill
- generation-packSkill
- generation-workflow-setupSkill
- guided-production-wizardSkill
- handdrawn-live-video-generatorSkill
- imagemagickSkill
- kdenlive-exportSkill
- krea-2Skill
- llm-model-lifecycleSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 45
Use stable <Subject N>, <Picture N>, <Video N>, and <Audio N> labels.
- Very specific: line 52
Use <scenetrans> when verbal audio crosses a shot boundary and <cutoff> only when the requested clip actually truncates speech.
“Common” is measured: kept by at least 6 in 10 of the 10 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
H3 Prompt Writing
This is Story-Film's portable implementation of the current public MiniMax H3 prompt-writing guidance. It is the mandatory formatting layer for every Story-Film MiniMax H3 prompt.
It contains no MiniMax Hub tool calls. Source behavior was reviewed at MiniMax-H3 commit d21241f0a4b3acbb34c97dae47fa417b7065e438; see SOURCES.md.
Workflow
- Identify the actual H3 mode supported by the selected workflow: T2VA, I2VA, FL2VA, L2VA, or Ref2VA.
- For T2VA/I2VA/FL2VA/L2VA read
references/base-en.txt. - For Ref2VA read
references/ref-en.txt, and use the base guide for shared shot, camera, speaker, dialogue, and sound conventions. - Preserve the required field names, section order, reference labels, shot numbering, and timing notation.
- Preserve user dialogue, lyrics, and visible scene text exactly in their original language.
- Hand the structured result back to
minimax-h3so Story-Film continuity, reference authority, exact-audio, and capture constraints are also enforced.
Base modes
Final core field order:
integrated_multimodal_descriptionoverall_soundscapenon_diegetic_music
I2VA, FL2VA, and L2VA also require the correct keyframe alignment instruction before the three fields. T2VA does not.
Ref2VA
Final section order:
subject_definitionssummaryretention_analysisdetailed_descriptionoverall_soundscapenon_diegetic_music
Use stable <Subject N>, <Picture N>, <Video N>, and <Audio N> labels. Do not assign a reference a broader authority than the Story-Film source manifest allows.
Shared output rules
[Shot 1]has no cut timestamp. Later shots use strictly increasingAt MM:SS.mmmcut times inside the requested duration.- Vocal sources use stable
(S1),(S2), and later IDs. - Spoken or sung content uses
<d>[Language] exact content</d>. - Use
<scenetrans>when verbal audio crosses a shot boundary and<cutoff>only when the requested clip actually truncates speech. - Describe camera motion as natural shot action. Use motion type, amplitude, and speed only when they matter.
overall_soundscapecontains ambience, physical action sounds, and non-verbal human sounds, not repeated dialogue.non_diegetic_musicdescribes audience-only score. Diegetic music belongs in the shot description.- Match the written audiovisual timeline to the requested H3 duration, normally 4 to 15 seconds per generated clip.
Done
The H3 format is exact, every reference label resolves, dialogue and visible text are preserved, and the final timeline matches the requested duration.
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.

