prompt-adapt

prompt-adapt is a skill for Claude Code from AgriciDaniel/claude-prompts. It costs 97 tokens per session (736 once invoked), scanned A, original, MIT.

A tool that rewrites an AI prompt so it fits a different AI model or platform while keeping the original intent. It handles differences in wording, settings, parameters, and negative prompts between models.

In plain words
What is it for?
Use it to convert prompts between models such as Midjourney, Flux, DALL-E, Sora, Stable Diffusion, and others.
Why use it?
Prompts written for one AI model may use controls or syntax that another model does not understand or handle well.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-prompts plugin — 5 skills shipped together

Good fit Use it to convert prompts between models such as Midjourney, Flux, DALL-E, Sora, Stable Diffusion, and others.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agricidaniel/claude-prompts/prompt-adapt
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add AgriciDaniel/claude-prompts --skill prompt-adapt
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/claude-prompts

Made for: Claude Code.

Or install claude-prompts, the plugin that ships this one along with the rest of its 5 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prompt-adapt

README.md
[![agentmods](https://agentmods.dev/badge/skills/agricidaniel/claude-prompts/prompt-adapt/github.svg)](https://agentmods.dev/skills/agricidaniel/claude-prompts/prompt-adapt)
Your own site
<a href="https://agentmods.dev/skills/agricidaniel/claude-prompts/prompt-adapt"><img src="https://agentmods.dev/badge/skills/agricidaniel/claude-prompts/prompt-adapt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prompt-adapt

Your own site · 80×15
<a href="https://agentmods.dev/skills/agricidaniel/claude-prompts/prompt-adapt"><img src="https://agentmods.dev/badge/skills/agricidaniel/claude-prompts/prompt-adapt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 736 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.00736
Opus 5 $0.00048 $0.00368
Sonnet 5 $0.00019 $0.00147
Haiku 4.5 $0.00010 $0.00074

Measured 11d ago against content hash 448a535f26f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prompt-adapt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/prompt-adapt/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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, --chaos parameters
  • 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 --ar for aspect ratio
  • Add --v 6.1 or appropriate version
  • Condense long descriptions into key phrases
  • Add style parameters (--style raw for 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 3

Use these as style references for the adaptation.

Read the full file on GitHub · 92 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 92 lines · 97 tokens per session scan A 448a535f26f9

Subscribe to this mod's changes

prompt-adapt is a skill published in the GitHub repository AgriciDaniel/claude-prompts (106 stars, last pushed 5mo ago), licensed MIT. It adds 97 tokens to every session and 736 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

forensic-prompt-compiler

Forensic image-to-prompt compiler for image generation models. Use this skill whenever the user wants to: convert/describe an existing image into a generation prompt, reconstruct a scene as a prompt, generate prompts from reference images for AI image tools (Midjourney, FLUX, Stable Diffusion, DALL-E, or any diffusion…

AnastasiyaW/codex-claude-code-config · 218 tokens

seedance-prompt

This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.

1370998960-del/https-github.com-Emily2040-seedance-2.0 · 68 tokens

minimax-h3-prompting

Guide an idea into a generation-ready MiniMax H3 / Hailuo H3 prompt or diagnose an inspected H3 output. Use for T2VA, I2VA, FL2VA, L2VA, or Ref2VA; text-only PV and kinetic type, Motion Design/MG, packaging and transitions, product/UI/game/MV/title work, localized reality-to-hand-drawn edits, audio/timbre reference…

q2522879285-source/minimax-h3-prompting-skill-public · 161 tokens

ai-video-prompt-generator

Generate AI video prompts from clean structured prompt specs, validate prompt specs, run an isolated OpenAI-based prompt generator, and lint prompt outputs for viewpoint, action, reference, dialogue, negative prompt, audio prompt, safety tags, and legacy-contamination failures. Use when producing or repairing…

Phantomlau3674/ai-film-director-workbench · 83 tokens

image-prompt

A skill that turns a vague request into a detailed prompt for generating images, including options for covers, posters, promotional materials, typography, and other visual formats. A prompt is an instruction given to an image-generation system.

treylom/prompt-engineering-skills · 231 tokens

seedance-2-5-prompt-director

A skill for writing and improving prompts for Seedance 2.5, a video-generation system. It covers text-to-video, image-to-video, editing, video extension, references, camera movement, green-screen work, sound, and lip sync.

zhouwei713/seedance-2-5-prompt-director · 159 tokens