illustration-prompt

星标0

分支0

更新时间2026年7月17日 23:11

Turn a vague image request into a generator-ready illustration prompt for Midjourney, DALL-E, Flux, Stable Diffusion, or similar tools. Use when the user needs visual direction, prompt structure, or reference-aware image prompting rather than image generation code.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

来源

kiku-jw

kiku-jw/codex-skills

打开 GitHub 仓库查看创作者相关仓库

下载

Illustration Prompt

Metadata

Trigger when: the real work is turning a visual idea plus references into a high-quality prompt.
Do not use when: the user already has a finished prompt or wants direct generation without prompt design.

Skill Purpose

Translate vague visual intent into a concrete, reference-aware prompt that a generator can follow without leaning on hand-wavy adjective soup.

Instructions

Lock the brief in this order: placement/context, style family, detail density, references, scene, palette/mood, and format. Collapse questions that the conversation already answered; do not re-interview for sport.
If references are present, summarize what should be borrowed and what should not. Read /Users/nick/.codex/skills/illustration-prompt/references/reference-analysis.md when you need the reference-reading checklist and /Users/nick/.codex/skills/illustration-prompt/references/prompt-template.md for the 8-block prompt structure.
Return one structured prompt in English plus a short filename and only the minimal model-specific tweak when it materially changes the result. If the user wants actual generation afterward, hand off to whatever image-generation tool is available in the current environment.

Non-Negotiable Acceptance Criteria

References and explicit scene constraints outrank decorative adjectives.
Conflicting references are called out instead of blended into fake coherence.
Perspective, composition, palette, material cues, and count-sensitive objects are concrete when they matter.
Default to no text in the image unless the user explicitly asks for text.

Output

A short kebab-case filename.
One structured English prompt using the 8-block format.
An optional short generator note only when a model-specific tweak genuinely matters.

同仓库更多 Skills

同仓库

github-seo

kiku-jw/codex-skills

Audit and improve a public GitHub repository's discoverability and any linked canonical site without confusing repository presentation with website SEO. Use for repository SEO, GitHub discoverability, topics/homepage/README optimization, GitHub Pages SEO, AEO, or agent-friendly public documentation.

2026-07-230

spreadsheet

kiku-jw/codex-skills

Create, edit, analyze, or format spreadsheets (`.xlsx`, `.csv`, `.tsv`) with `openpyxl` and `pandas`, especially when formulas, references, and formatting must survive the change. Use when spreadsheet integrity matters more than ad hoc CSV hacking.

2026-07-180

spreadsheet-tabular-analysis

kiku-jw/codex-skills

Analyze and reshape spreadsheet, CSV, or TSV data with `pandas` and stable output files. Use when the job is aggregation, filtering, joins, metrics, or tabular transformations rather than workbook-style editing.

2026-07-180

spreadsheet-xlsx-edit

kiku-jw/codex-skills

Create or edit `.xlsx` workbooks while preserving formulas, references, formatting, and layout. Use when workbook integrity matters more than raw data analysis.

2026-07-180

transcribe-basic

kiku-jw/codex-skills

Produce a fast plain-text transcript with the bundled CLI using the light transcription model. Use when speaker diarization is not needed.

2026-07-180

transcribe-diarize

kiku-jw/codex-skills

Produce a speaker-aware transcript with diarization and optional known-speaker hints using the bundled CLI. Use when the user explicitly needs speaker labels.

2026-07-180

name	illustration-prompt
description	Turn a vague image request into a generator-ready illustration prompt for Midjourney, DALL-E, Flux, Stable Diffusion, or similar tools. Use when the user needs visual direction, prompt structure, or reference-aware image prompting rather than image generation code.

Illustration Prompt

Metadata

Trigger when: the real work is turning a visual idea plus references into a high-quality prompt.
Do not use when: the user already has a finished prompt or wants direct generation without prompt design.

Skill Purpose

Translate vague visual intent into a concrete, reference-aware prompt that a generator can follow without leaning on hand-wavy adjective soup.

Instructions

Lock the brief in this order: placement/context, style family, detail density, references, scene, palette/mood, and format. Collapse questions that the conversation already answered; do not re-interview for sport.
If references are present, summarize what should be borrowed and what should not. Read /Users/nick/.codex/skills/illustration-prompt/references/reference-analysis.md when you need the reference-reading checklist and /Users/nick/.codex/skills/illustration-prompt/references/prompt-template.md for the 8-block prompt structure.
Return one structured prompt in English plus a short filename and only the minimal model-specific tweak when it materially changes the result. If the user wants actual generation afterward, hand off to whatever image-generation tool is available in the current environment.

Non-Negotiable Acceptance Criteria

References and explicit scene constraints outrank decorative adjectives.
Conflicting references are called out instead of blended into fake coherence.
Perspective, composition, palette, material cues, and count-sensitive objects are concrete when they matter.
Default to no text in the image unless the user explicitly asks for text.

Output

A short kebab-case filename.
One structured English prompt using the 8-block format.
An optional short generator note only when a model-specific tweak genuinely matters.