Plan Editorial Illustrations
Translate ideas into visual actions. Do not decorate every paragraph.
Workflow
- Read the complete source and identify the audience, publication surface, aspect ratio, illustration count, brand constraints, and required recurring character or style.
- Extract the article's central thesis, key turns, abstract mechanisms, and moments that benefit from visual explanation.
- Select only illustration-worthy moments. Prefer scenes that clarify tension, sequence, comparison, system, or consequence.
- Create a shot list before generation: purpose, scene, subject action, composition, labels, color accents, and placement.
- Assign one dominant visual structure per image: single action, before/after, path, balance, funnel, loop, ladder, or contrast.
- Keep a consistent visual grammar across the set while varying composition and action.
- Write generation prompts that specify canvas, hierarchy, character action, environment, text limits, palette, line quality, whitespace, and exclusions.
- Generate immediately when the user explicitly requests images and an image tool is available; otherwise return prompts and a shot list.
- Inspect every result for text errors, hierarchy, cropping, duplicated limbs, inconsistent character identity, crowded labels, and accidental commercial-slide styling.
- Revise failed images individually rather than regenerating the whole set without diagnosis.
Default visual direction
When the user requests a restrained hand-drawn editorial style but gives no brand guide, use a clean light background, black imperfect linework, large whitespace, one clear action, and sparse accent colors. Do not copy a living artist's or third party's signature style or protected character.
Route by need
- Read references/shot-list.md to select scenes and structure a set.
- Read references/prompt-and-qa.md to write prompts and review outputs.
Output standard
Return the relevant subset of: visual concept, illustration count, placement map, shot list, production prompts, negative constraints, alt text, and QA findings. Keep in-image text short and reproduce names, numbers, and quotations exactly from verified source material.
1---2name: plan-editorial-illustrations3description: 将中文或英文文章转化为连贯的编辑插画体系，包括配图规划、镜头清单、生成提示词和视觉质检方案。适用于文章配图、小红书配图、公众号插画、视觉叙事、固定角色体系，以及检查构图、文字准确性、信息层级和风格一致性。4---56# Plan Editorial Illustrations78Translate ideas into visual actions. Do not decorate every paragraph.910## Workflow11121. Read the complete source and identify the audience, publication surface, aspect ratio, illustration count, brand constraints, and required recurring character or style.132. Extract the article's central thesis, key turns, abstract mechanisms, and moments that benefit from visual explanation.143. Select only illustration-worthy moments. Prefer scenes that clarify tension, sequence, comparison, system, or consequence.154. Create a shot list before generation: purpose, scene, subject action, composition, labels, color accents, and placement.165. Assign one dominant visual structure per image: single action, before/after, path, balance, funnel, loop, ladder, or contrast.176. Keep a consistent visual grammar across the set while varying composition and action.187. Write generation prompts that specify canvas, hierarchy, character action, environment, text limits, palette, line quality, whitespace, and exclusions.198. Generate immediately when the user explicitly requests images and an image tool is available; otherwise return prompts and a shot list.209. Inspect every result for text errors, hierarchy, cropping, duplicated limbs, inconsistent character identity, crowded labels, and accidental commercial-slide styling.2110. Revise failed images individually rather than regenerating the whole set without diagnosis.2223## Default visual direction2425When the user requests a restrained hand-drawn editorial style but gives no brand guide, use a clean light background, black imperfect linework, large whitespace, one clear action, and sparse accent colors. Do not copy a living artist's or third party's signature style or protected character.2627## Route by need2829- Read [references/shot-list.md](references/shot-list.md) to select scenes and structure a set.30- Read [references/prompt-and-qa.md](references/prompt-and-qa.md) to write prompts and review outputs.3132## Output standard3334Return the relevant subset of: visual concept, illustration count, placement map, shot list, production prompts, negative constraints, alt text, and QA findings. Keep in-image text short and reproduce names, numbers, and quotations exactly from verified source material.
ShenyuanNext