prompt-to-asset: Skill for Claude Code

.claude/skills/t2i-prompt-dialect/SKILL.md

t2i-prompt-dialect is a skill for Claude Code from MohamedAbdallah-14/prompt-to-asset. It costs 95 tokens per session (3,010 once invoked), scanned A, original, MIT.

A tool that rewrites image descriptions into the prompt format expected by a chosen image-generation model.

In plain words
What is it for?
Use it to adapt an asset brief for models such as OpenAI image models, Imagen, Gemini, SDXL, Flux, Midjourney, Ideogram, or Recraft.
Why use it?
Different image models handle negative prompts, transparency, brand colors, and text limits differently, so one prompt may not work well everywhere.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is MohamedAbdallah-14/prompt-to-asset's own configuration. It tells Claude Code how to work on prompt-to-asset itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything prompt-to-asset configures →

Part of the prompt-to-asset plugin — 13 skills, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to MohamedAbdallah-14/prompt-to-asset. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MohamedAbdallah-14/prompt-to-asset/main/.claude/skills/t2i-prompt-dialect/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MohamedAbdallah-14/prompt-to-asset

Made for: Claude Code.

Or install prompt-to-asset, the plugin that ships this one along with the rest of its 13 skills, 1 MCP server.

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 t2i-prompt-dialect

README.md
[![agentmods](https://agentmods.dev/badge/skills/mohamedabdallah-14/prompt-to-asset/t2i-prompt-dialect/github.svg)](https://agentmods.dev/skills/mohamedabdallah-14/prompt-to-asset/t2i-prompt-dialect)
Your own site
<a href="https://agentmods.dev/skills/mohamedabdallah-14/prompt-to-asset/t2i-prompt-dialect"><img src="https://agentmods.dev/badge/skills/mohamedabdallah-14/prompt-to-asset/t2i-prompt-dialect/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 t2i-prompt-dialect

Your own site · 80×15
<a href="https://agentmods.dev/skills/mohamedabdallah-14/prompt-to-asset/t2i-prompt-dialect"><img src="https://agentmods.dev/badge/skills/mohamedabdallah-14/prompt-to-asset/t2i-prompt-dialect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,010 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00095 $0.03010
Opus 5 $0.00048 $0.01505
Sonnet 5 $0.00019 $0.00602
Haiku 4.5 $0.00010 $0.00301

Measured 12d ago against content hash cdbb38e91a0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

t2i-prompt-dialect 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 12d 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.

.claude/skills/t2i-prompt-dialect/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

T2I prompt dialect

Runs between asset_enhance_prompt() and asset_generate_*(). Takes a normalized brief plus a target model and emits a prompt that honors that model's syntax, token budget, and quirks.

Per-model rules (quick card, verified Apr 2026)

Model Grammar Token / char ceiling Negative prompt Transparency Text ceiling
gpt-image-2 Prose ~100 words silently ignored NOT supported — background:"transparent" 400s (regression vs 1.5) — route transparent jobs to gpt-image-1.5 instead ~80 chars / paragraph (~99% accuracy per third-party tests)
gpt-image-1.5 Prose ~100 words silently ignored API param background: "transparent" dense text ~60 chars (LM Arena #1)
gpt-image-1 Prose ~100 words silently ignored API param background: "transparent" ~50 chars / ≤5 words
Imagen 4 (Fast/Standard/Ultra) Narrative prose, ≥30 words suppresses auto-rewriter unbounded negativePrompt accepted on Vertex AI; ignored on Gemini API never request in prompt (renders checkerboard as RGB) ≤25 chars per Google's own guidance
Gemini 3.1 Flash Image (Nano Banana 2) Prose unbounded ignored renders checkerboard ~50 chars / ~90% accuracy (#1 Image Arena at launch — strong-text, not weak)
Gemini 3 Pro Image (Nano Banana Pro) Prose unbounded ignored renders checkerboard paragraph-length reliable (~94-96% accuracy)
SD 1.5 / SDXL Tag-soup, comma-separated, no articles 77 CLIP tokens, chunk via BREAK native LayerDiffuse adapter or matte post "cannot render legible text" per HF card — ≤1 glyph
SD 3 / SD 3.5 Large Prose + tags hybrid 256 (T5) native matte post ~30 chars (mid-tier; not strong-text)
Flux 1.1 Pro / Flux Pro Prose narrative 512 rejected at fal schema; no-op on BFL native matte post 1–3 words / ~25 chars
Flux 2 (pro/flex/dev/klein) Prose, JSON-structured prompts allowed T5 + Mistral-3 24B VLM officially unsupported per BFL guide ("FLUX.2 does not support negative prompts") matte post 5–10 words / one tagline (~92% layout accuracy)
Flux Schnell Prose 256 unsupported matte post 1–2 words max
Midjourney v7/v8 Prose + --flags unbounded --no X flag none; matte post ≤15 chars with --text
Ideogram 3 / 3 Turbo Prose + text in "double quotes" unbounded native dedicated POST /v1/ideogram-v3/generate-transparent endpoint; rendering_speed: "TURBO" for Turbo tier (no style:"transparent" param exists) ~3–6 words reliable, ~10 with seed retries
Recraft V3 / V4 Prose + controls.colors + style_id (V3 only — V4 dropped it) unbounded native native SVG handles alpha trivially ~3–5 words

Read the full file on GitHub · 179 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. 12d ago First seen · 179 lines · 95 tokens per session scan A cdbb38e91a0f

Subscribe to this mod's changes

t2i-prompt-dialect is a skill published in the GitHub repository MohamedAbdallah-14/prompt-to-asset (19 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 3,010 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.