agentsclimarketplace
Sign in

Plan editorial illustrations

Skill ShenyuanNext/wepr-growth-skills/skills/plan-editorial-illustrations

Turn Chinese or English articles into coherent editorial illustration systems, shot lists, prompts, and visual QA plans. Use for 文章配图, 小红书配图, 公众号插画, editorial illustration, illustration prompts, visual storytelling, recurring character systems, or checking composition, text accuracy, hierarchy, and style consistency.From its SKILL.md

Install
npx -y skills add ShenyuanNext/wepr-growth-skills --skill plan-editorial-illustrations

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 28 days oldThe repository was created 28 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.6 KB, 442 tokens by cl100k_base, as published. Nobody here has run it

Plan Editorial Illustrations

Translate ideas into visual actions. Do not decorate every paragraph.

Workflow

  1. Read the complete source and identify the audience, publication surface, aspect ratio, illustration count, brand constraints, and required recurring character or style.
  2. Extract the article's central thesis, key turns, abstract mechanisms, and moments that benefit from visual explanation.
  3. Select only illustration-worthy moments. Prefer scenes that clarify tension, sequence, comparison, system, or consequence.
  4. Create a shot list before generation: purpose, scene, subject action, composition, labels, color accents, and placement.
  5. Assign one dominant visual structure per image: single action, before/after, path, balance, funnel, loop, ladder, or contrast.
  6. Keep a consistent visual grammar across the set while varying composition and action.
  7. Write generation prompts that specify canvas, hierarchy, character action, environment, text limits, palette, line quality, whitespace, and exclusions.
  8. Generate immediately when the user explicitly requests images and an image tool is available; otherwise return prompts and a shot list.
  9. Inspect every result for text errors, hierarchy, cropping, duplicated limbs, inconsistent character identity, crowded labels, and accidental commercial-slide styling.
  10. 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

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.

What ships with it: 3 files

2.3 KB alongside SKILL.md

agents/

references/

Gives 0 of the 12 instructions most plan spec skills give in 442 tokens

Counted across 1,099 of the 1,860 authors here whose files we hold, read 2026-08-07

  • Ask one question at a timein 51 of 1099
  • Break plans into vertical slicesin 29 of 1099, across 11 files
  • Publish issues in dependency orderin 27 of 1099, across 9 files
  • Iterate until user approves the breakdownin 25 of 1099, across 7 files
  • Explore the repository to understand the codebase statein 24 of 1099, across 7 files
  • Use domain glossary vocabularyin 23 of 1099, across 5 files
  • Apply correct triage labels to published issuesin 23 of 1099, across 5 files
  • Prefer AFK slices over HITLin 22 of 1099, across 7 files
  • Write a specification before writing any codein 22 of 1099, across 14 files
  • Write failing tests before implementation codein 22 of 1099, across 20 files
  • Ask clarifying questions until requirements are concretein 21 of 1099, across 13 files
  • Respect existing architecture decision recordsin 20 of 1099, across 5 files

Said here and by no other author read

  • do not decorate every paragraph
  • select only illustration-worthy moments
  • create a shot list before generation
  • assign one dominant visual structure per image
  • keep visual grammar consistent across the set
  • write generation prompts specifying canvas, hierarchy, and exclusions

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,851. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.