Prompt Adapt
- 6 installs
- 100 repo stars
- Updated April 10, 2026
- agricidaniel/claude-prompts
prompt-adapt is a Claude Code skill that converts AI image and video prompts between generation models (Midjourney, Flux, DALL-E, Sora, Leonardo, and others) while preserving intent.
About
prompt-adapt is a Claude Code skill that converts an AI generation prompt from one model to another, such as Midjourney to Flux or DALL-E. It strips or maps model-specific parameters, rewrites shorthand into the target model's preferred style, and reports what changed. A developer uses it when a prompt written for one image or video model needs to run well on a different one.
- Converts AI image/video prompts between models (Midjourney, Flux, DALL-E, Sora, Leonardo, and more)
- Handles parameter mapping, syntax differences, and model-specific optimizations
- Outputs original, adapted prompt, translation notes, parameter mapping, and a confidence level
Prompt Adapt by the numbers
- 6 all-time installs (skills.sh)
- Ranked #1,096 of 1,335 Generative Media skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
prompt-adapt capabilities & compatibility
- Capabilities
- prompt conversion · image generation · video generation
- Use cases
- image generation · video generation
- Pricing
- Free
What prompt-adapt says it does
Adapt and convert AI prompts between different models and platforms.
Convert prompts between AI models while preserving intent and maximizing output quality.
npx skills add https://github.com/agricidaniel/claude-prompts --skill prompt-adaptAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 6 |
|---|---|
| repo stars | ★ 100 |
| Last updated | April 10, 2026 |
| Repository | agricidaniel/claude-prompts ↗ |
What it does
Convert an AI image or video prompt from one generation model to another while preserving intent.
Who is it for?
Reusing an existing generation prompt across a different image or video model
Skip if: Terminal or CLI prompts, code prompts, or general LLM chat prompts
When should I use this skill?
you say adapt prompt, convert prompt, translate prompt, port to flux, or midjourney to dall-e
What you get
An adapted prompt for the target model with parameter mapping and translation notes.
- An adapted prompt
- A source-to-target parameter mapping
- Translation notes with a confidence rating
By the numbers
- 5-step adaptation workflow (identify, analyze, translate, search examples, present)
Files
Prompt Adapter
Convert prompts between AI models while preserving intent and maximizing output quality.
Adaptation Workflow
Step 1: Identify Source and Target
Determine: 1. Source model: What model was this prompt written for? 2. Target model: What model should it run on? 3. Priority: Preserve style fidelity or optimize for target strengths?
Step 2: Analyze Source Prompt
Break down the prompt into components:
- Core subject/action
- Style modifiers
- Technical parameters (model-specific)
- Negative prompts (if any)
- Aspect ratio / dimensions
Step 3: Apply Model Translation Rules
Load {PROMPT_ENGINE_DIR}/references/model-guide.md for detailed rules. Key translations:
Midjourney -> Flux:
- Remove
--ar,--v,--style,--s,--chaosparameters - Expand shorthand into natural language descriptions
- Flux prefers longer, more descriptive prompts
- Remove
::weight syntax, integrate naturally
Midjourney -> DALL-E:
- Remove all
--parameters - Rewrite as clear, direct descriptions
- DALL-E prefers straightforward language over artistic jargon
- Remove negative prompts (DALL-E doesn't support them well)
Flux -> Midjourney:
- Add
--arfor aspect ratio - Add
--v 6.1or appropriate version - Condense long descriptions into key phrases
- Add style parameters (
--style rawfor photorealistic)
Any -> Sora (Video):
- Add camera movement descriptions (pan, zoom, tracking, etc.)
- Add temporal flow ("the scene transitions from... to...")
- Specify duration if possible
- Focus on motion and action over static details
Any -> Leonardo AI:
- Reference specific Leonardo models (Phoenix, Alchemy, etc.)
- Use Leonardo-specific quality tokens
- Adapt negative prompts to Leonardo format
Step 4: Search for Target Model Examples
Find reference prompts in the target model:
python3 {PROMPT_ENGINE_DIR}/scripts/search_prompts.py "SUBJECT" --model TARGET_MODEL --limit 3Use these as style references for the adaptation.
Step 5: Present Adaptation
Output format: 1. Original prompt (source model labeled) 2. Adapted prompt (target model labeled) 3. Translation notes (what changed and why) 4. Parameter mapping (source params -> target params) 5. Confidence level (High/Medium/Low -- based on model compatibility)
Common Pitfalls
- Midjourney weight syntax (
::2) has no direct equivalent in most models - DALL-E ignores most style parameters -- weave them into descriptions
- Sora needs temporal language that image models don't use
- Aspect ratios must be specified differently per platform
- Some styles only work well on specific models (e.g.,
--nijiis Midjourney-only)
Related skills
Remotion Best PracticesGet Remotion-specific coding guidance that prevents common video rendering mistakes when creating animated React videos.451k4.2k
Ai Video GenerationGenerate videos using 40+ AI models including Veo, Seedance, and others via inference.sh442k665Ai Image GenerationGenerate images using 50+ AI models including FLUX, Gemini, and Replicate via inference.sh441k665Ai Avatar VideoGenerate videos featuring AI avatars for product demos, tutorials, marketing, or explainers441k665Remotion RenderRender videos programmatically using React components and Remotion framework441k665
Remotion RenderGenerate high-quality MP4 videos from React code using Remotion inside an AI coding agent.363k665FAQ
Which models can prompt-adapt convert between?
It translates among Midjourney, Flux, Leonardo AI, DALL-E, Sora, Imagen, Stable Diffusion, Adobe Firefly, Ideogram, and more.
What does it output?
The original prompt, the adapted prompt, translation notes, a parameter mapping, and a confidence level.