About this skill
A visual-prompt skill for turning an idea into detailed prompts for Midjourney and similar image models, including subject, composition, style, lighting and scene details.
Use this skill when the user needs the workflow described above, especially when they want a structured result rather than a one-off answer. A visual-prompt skill for turning an idea into detailed prompts for Midjourney and similar image models, including subject, composition, style, lighting and scene details.
Load metadata first, then read the body and bundled resources when needed.
Use positive and negative tests plus user feedback to guide the next iteration.
Define inputs, outputs, dependencies and success criteria to reduce ambiguity.
Skill files
Ultra-realistic amateur street photo of the same 27-year-old Turkish-looking curvy woman in Ankara, soft slightly chubby figure, blonde hair loose, tight white tank top, patterned high-waisted pants, small crossbody bag. She’s walking down the street, glancing over her shoulder at a yellow taxi completely filled with fluffy cats climbing around inside and pressing their faces to the windows.
Behind her, large road signs point to Eskişehir and Kızılay. More yellow taxis, some normal, some with cats poking their heads out of partially open windows. Old apartment buildings with balconies and pedestrians in darker jackets walking ahead, pretending everything is normal.
Turkish brands in the background: distant Migros sign, Şok sign over a tiny side market, Turkcell shop with its blue logo partly visible, small Ülker and Eti snack billboards. All slightly out of focus but readable.
Shot on a regular iPhone by someone walking a few steps behind her, handheld, slightly shaky, vertical framingnameUltra-Realistic Amateur Street Photo of Ankara ScenedescriptionUse this skill when the user needs the workflow described above, especially when they want a structured result rather than a one-off answer. A visual-prompt skill for turning an idea into detailed prompts for Midjourney and similar image models, including subject, composition, style, lighting and scene details.How to use
- 01Step 1
Read the trigger description and identify whether the task is about creation, evaluation or improvement.
- 02Step 2
Open SKILL.md and confirm the input, output and bundled resource requirements.
- 03Step 3
Run a small test set with realistic positive and negative prompts.
- 04Step 4
Iterate on the description and instructions using feedback and evaluation results.
Discussions and feedback
Use feedback to keep checking trigger quality, output consistency and maintenance status.