#321321st of 455 in Skills, plugins and promptsFor image, video and design, image and design

ian-xiaohei-illustrations

Codex skill that generates hand-drawn 16:9 illustrations for Chinese articles

Stars
13.2k
License
MIT
Last commit
Oct 2026
Last release
May 2026
Stars, last 24 weeks+13,164
26 May 2026: 18 stars2 Jun 2026: 1,741 stars9 Jun 2026: 3,647 stars16 Jun 2026: 4,835 stars23 Jun 2026: 5,829 stars30 Jun 2026: 6,514 stars7 Jul 2026: 7,163 stars14 Jul 2026: 7,830 stars21 Jul 2026: 8,238 stars28 Jul 2026: 8,620 stars4 Aug 2026: 8,941 stars11 Aug 2026: 9,275 stars18 Aug 2026: 9,513 stars25 Aug 2026: 10,114 stars1 Sept 2026: 10,797 stars8 Sept 2026: 11,212 stars15 Sept 2026: 11,647 stars22 Sept 2026: 11,936 stars29 Sept 2026: 12,184 stars6 Oct 2026: 12,353 stars13 Oct 2026: 12,533 stars20 Oct 2026: 12,694 stars27 Oct 2026: 12,914 stars3 Nov 2026: 13,075 stars10 Nov 2026: 13,182 stars

18 on 26 May 202613,182 on 10 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

A Codex Skill that reads a Chinese article, picks 4-8 key ideas, and writes a shot list. It then generates one white-background, hand-drawn 16:9 PNG per idea with an image model, using a recurring black character called Xiaohei and sparse red, orange and blue Chinese annotations. Files are saved to assets/<article-slug>-illustrations/.

Who it is for: Chinese writers using Codex who want consistent hand-drawn illustrations

Strengths

  • Fixed visual style (white background, thin black lines, limited annotation colors) keeps a series consistent
  • Outputs a shot list first, so images can be planned before generation
  • Includes QA checklist and style reference files for the agent to check results against
  • Supports editing an existing image, such as removing a stray title

Weaknesses

  • Output is raster PNG only; no SVG, HTML or editable vector source
  • Image models may produce wrong Chinese characters or extra titles, so manual review is needed
  • Built for Codex; Claude Code or other agents are not documented
  • README and prompts are in Chinese; the style targets Chinese articles

What it needs

  • Needs Codex, image generation model

What changed

From the release notes. No flag means the note does not say so, not that the upgrade is safe.

Also in Skills, plugins and prompts

See all 455
Also in Skills, plugins and prompts
RankProjectScore
1claude-memPersistent cross-session memory plugin for Claude Code and other coding agents116.4k stars+16,587 (+17%) in 30 daysApache-2.097 out of 100
2impeccableDesign skill with 24 slash commands for AI coding agents' frontend output Live demo ↗ (opens in a new tab)108.8k stars+28,464 (+35%) in 30 daysApache-2.097 out of 100
3gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles141.3k stars+5,544 (+4.1%) in 30 daysMIT96 out of 100
#4rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex Live demo ↗ (opens in a new tab)81.5k stars+7,374 (+9.9%) in 30 daysMIT96 out of 100
#5cavemanShortens coding-agent replies and compresses tool output before the model reads it Live demo ↗ (opens in a new tab)119.3k stars+8,422 (+7.6%) in 30 daysApache-2.095 out of 100