model-adapters
Skill8 starsChanged 28 days agoMITView on GitHub
Translate a finished shot-brief into per-model instructions for Muse, Gemini/Veo, Sora, Kling, Runway, Pika, Luma, and Hailuo. Constraint sheets, prompt quirks, and what to verify. Use after the prompt is written, before generating.
In this repository8 other files it gives its agents.
- assembly-and-deliverySkill
- character-consistencySkill
- cinematic-directionSkill
- dialogue-and-audioSkill
- muse-google-veo-webSkill
- story-and-shotsSkill
- video-prompt-craftSkill
- video-qaSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Every sheet is dated; if the date is old, check the provider before planning around a number.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Model Adapters
The shot-brief grammar is universal. Models are not. Each one has its own duration caps, aspect ratios, prompt quirks, and failure patterns, and they change every few months. This skill is the translation layer: finished brief in, model-ready instructions out.
The workflow
- Write the prompt model-agnostic first. Finish the shot-brief
(
../video-prompt-craft/) completely before opening an adapter. Adapters translate; they don't write. - Read the adapter for your target. Each sheet covers: what the model is good at, prompt quirks that matter, hard limits, and how negatives and reference images work there.
- Apply the quirks, keep the story. The beats, the camera, the Preserve slot. Those don't change. What changes is formatting and emphasis.
- Verify volatile specs. Durations, resolutions, and prices move fast. Every sheet is dated; if the date is old, check the provider before planning around a number.
The adapter list
| Adapter | File | Best for |
| Muse (Meta) | references/muse.md | Agent-driven generation inside Muse |
| Gemini / Veo (Google) | references/gemini-veo.md | Dialogue-heavy, JSON-structured prompts |
| Sora (OpenAI) | references/sora.md | Long coherent takes, storyboards |
| Kling | references/kling.md | Realistic motion, camera controls |
| Runway | references/runway.md | Stylized looks, creative tools |
| Pika | references/pika.md | Quick social clips, effects |
| Luma (Dream Machine) | references/luma.md | Natural camera motion |
| Hailuo / MiniMax | references/hailuo.md | Character acting, Chinese-language content |
Adding an adapter
Copy references/adapter-template.md. One page max. Facts over adjectives,
dates on every number, and a clear line between "prompting advice" (durable)
and "current specs" (perishable). If you can't verify a spec, write "verify"
instead of guessing.
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.