Ross ROSS = Recommend OSS · open-source software intelligence for agents

ziguishian/xhs-visual-director-skill

这是一个用于规划小红书图文的 Agent Skill。它不是普通文案助手,而是一个“视觉导演”:先判断内容任务,再选择适合的视觉风格,最后输出完整图文结构、逐页视觉方案、图像生成提示词、发布文案和自检清单。 observed · 2026-08-28

github.com/ziguishian/xhs-visual-director-skill · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

54/100

  • Activity 90
  • Release rhythm 35
  • Longevity 6

Flags: no_releases young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 97
  • days_rel: n/a
  • days_push: 61
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1272 stars · 125 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

An Agent Skill (Codex Skill) that acts as a 'visual director' for planning Xiaohongshu (Little Red Book) image-and-text posts. It interviews the user Socratically, selects from 24 built-in visual styles, and outputs a full multi-page post plan with per-page visual specs, image-generation prompts, captions, and a self-check checklist.

Use cases

  • plan xiaohongshu carousel posts
  • generate image prompts for social media covers
  • choose a visual style for a content topic
  • turn drafts or screenshots into polished image posts
  • write xiaohongshu titles, body text and hashtags
  • avoid cheap-looking AI-generated social media graphics

When to choose

  • you create Xiaohongshu image-text content and want structured, style-consistent multi-page posts
  • you use an agent platform (Codex Skills) and want a reusable visual workflow
  • you need image-generation prompts plus publishing copy in one package

When to avoid

  • you need a standalone app or GUI rather than an agent skill
  • your target platform is not Xiaohongshu or you need English-first output
  • you want fully automated generation without the interactive Q&A flow

Facets

plugin · maturity active

prompt-engineering agent-framework image-processing social-media artificial-intelligence media cross-platform agent-skill xiaohongshu content-creation visual-design image-generation-prompts social-media-marketing chinese-content

1 source

Member repositories

RepositoryRoleHealth v2
ziguishian/xhs-visual-director-skillmain54

For agents

markdown · JSON · MCP: product_card(name="ziguishian/xhs-visual-director-skill")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem