Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →blockrunai/image-prompting
Use when generating or editing images via `blockrun_image` — especially with GPT Image 2, Nano Banana, or Grok Imagine for posters, UI mockups, marketing assets, product shots, or anything with on-image text. Turns vague user requests ("make me a cool poster") into structured, text-accurate prompts that actually render what you asked for.
Passed 22 of 22 test cases with the skill, and 7 of 22 without it.
and 22 more in the full report
15 fixed7 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
A user wants a landscape announcement poster for X/Twitter using `openai/gpt-image-2`. The user asks for aspect ratio '16:9'. Which exact valid GPT Image 2 size string should be passed to the API call?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies 1536x1024 as the landscape size string for openai/gpt-image-2. | Missed | Passed |
The instructions your model reads when the skill loads.
Most image failures are prompt failures. This skill gives the MCP agent a repeatable structure for turning any user request into a prompt that renders clean typography, preserves layout on edits, and avoids AI slop. Defaults are tuned for GPT Image 2 (best legible text), with fallbacks for Nano Banana, Grok Imagine, and CogView.
Costs are what you are actually CHARGED, verified live. Size is the biggest
lever: any dimension above 1024 moves GPT Image 2 to the large tier and roughly
doubles the price ($0.064 → $0.127). Ask for 1536x1024 only when you need it.
| User wants... | Model | Mode | Size | Cost |
|---|---|---|---|---|
| Poster / typography-heavy asset | openai/gpt-image-2 | generate | 1536x1024 or 1024x1536 | $0.127 |
| Clean product / UI mockup | openai/gpt-image-2 | generate | 1024x1024 | $0.064 |
| Photoreal / fashion / editorial | openai/gpt-image-2 or google/nano-banana-pro | generate | 1024x1024 | $0.064–0.106 |
| Pro-level photoreal at Flash speed | google/nano-banana-2 | generate | 1024x1024 (only size) | $0.0955 |
| Artistic / stylized / fast | google/nano-banana | generate | 1024x1024 | $0.0535 |
| Cheapest usable draft | zai/cogview-4 | generate | 1024x1024 | $0.01675 |
| Widescreen / banner on a budget | bytedance/seedream-5-pro | generate | 2048x1024 or 1280x720 | $0.04825 ($0.0955 when both sides >1024) |
| Edit an existing image (localized change) | openai/gpt-image-2 | edit | match source | $0.064 at 1024x1024, $0.127 above |
| Composite from multiple refs | openai/gpt-image-2 | edit (multi-ref) | match target | $0.064 at 1024x1024, $0.127 above |
Valid GPT Image 2 sizes: 1024x1024 (square), 1536x1024 (landscape ~3:2), 1024x1536 (portrait ~2:3).
Write prompts as five short blocks separated by blank lines. This is the single biggest quality lever.
SCENE: where/when/background/environment, one or two lines.
SUBJECT: the main focus (who/what), described concretely.
DETAILS: materials, texture, lighting, camera angle, composition, mood,
lens feel, depth of field, surface condition. Stack concrete nouns.
USE CASE: editorial photo / product mockup / poster / UI screen / infographic / concept frame.
(This single line tells the model what kind of image to produce.)
CONSTRAINTS: what must not drift. "No extra text." "No duplicate elements."
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.