Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Jaimo-so/xiaohongshu-knowledge-carousel-skill --skill create-xiaohongshu-knowledge-carouselgit clone --depth 1 https://github.com/Jaimo-so/xiaohongshu-knowledge-carousel-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jaimo-so/xiaohongshu-knowledge-carousel-skill/create-xiaohongshu-knowledge-carousel)<a href="https://agentmods.dev/skills/jaimo-so/xiaohongshu-knowledge-carousel-skill/create-xiaohongshu-knowledge-carousel"><img src="https://agentmods.dev/badge/skills/jaimo-so/xiaohongshu-knowledge-carousel-skill/create-xiaohongshu-knowledge-carousel/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jaimo-so/xiaohongshu-knowledge-carousel-skill/create-xiaohongshu-knowledge-carousel"><img src="https://agentmods.dev/badge/skills/jaimo-so/xiaohongshu-knowledge-carousel-skill/create-xiaohongshu-knowledge-carousel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.01498 |
| Opus 5 | $0.00044 | $0.00749 |
| Sonnet 5 | $0.00018 | $0.00300 |
| Haiku 4.5 | $0.00009 | $0.00150 |
Grade A, and why
create-xiaohongshu-knowledge-carousel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Xiaohongshu Knowledge Carousel
Create a coherent educational carousel whose knowledge is complete, illustrations are consistent, Chinese text is reliable, and deliverables contain only final effect images.
Non-negotiable rules
- Preserve every source definition, meaning, cause, mechanism, step, condition, limitation, warning, exception, and verification requirement. Never fold several distinct knowledge points into a vague summary. Add pages when the copy would otherwise be compressed.
- Complete visual generation and exact Chinese typesetting as one final-render operation. Do not create, review, display, or deliver a standalone wordless illustration-base stage.
- Keep one approved character identity, outfit, prop set, palette, print texture, safe margin, and corner-label system throughout the series.
- Use exactly two full-page background roles in the bundled house style: vintage blue
#287F98for the cover and old-paper yellow#EFE4CCfor every interior page. Never rotate orange-red, mustard, blue, or other full-page interior backgrounds. - Make the fully typeset final page the first reviewable and user-visible image. Call
generatedImageonly for finished pages, never for a raw visual layer. - If an image tool technically returns a temporary visual layer, consume it immediately inside the same final-render operation and delete it after composition. It must not become a named workflow step, review checkpoint, saved project asset, or deliverable.
- Never delete user source files unless the user explicitly asks. “Final-only delivery” means a clean deliverable directory; it does not authorize cleaning unrelated project files.
Required references
- Before planning pages or writing copy, read references/content-integrity.md.
- Before generating or editing images, read references/visual-system.md, then use the available image-generation skill/tool.
- When the topic is RAG or the user requests this exact series, read references/rag-eight-page-example.md. Do not shorten its definitions or boundaries.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 333 B
- assets/manifest.example.json 2.5 KB
- assets/style-anchor-cover.png 2475 KB
- assets/style-anchor-interior.png 1920 KB
- references/content-integrity.md 2.6 KB
- references/rag-eight-page-example.md 4.1 KB
- references/visual-system.md 5.2 KB
- scripts/typeset_carousel.py 7.6 KB runs code
- scripts/verify_deliverables.py 1.9 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 128 lines · 89 tokens per session scan A c279047964a6
create-xiaohongshu-knowledge-carousel is a skill published in the GitHub repository Jaimo-so/xiaohongshu-knowledge-carousel-skill (15 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,498 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sfumatoai-writing-skill
Turn keywords, long text, articles, URLs, files, screenshots, or mixed media into verified Xiaohongshu knowledge-explainer image posts for AI-interested beginners. Use when Codex must analyze the input instead of blindly summarizing it, choose the strongest topic, research ambiguous or technical claims with…
ian-xiaohei-illustrations
A method for creating hand-drawn Chinese illustrations that explain the main idea, structure, process, or metaphor in an article or document. It uses a recurring black character called Xiaohei as the central figure.
xiaohongshu-title
A Chinese-language title-writing and editing assistant for Xiaohongshu, a Chinese social-media platform for image and video posts. It creates titles for posts, covers, tutorials, reviews, recommendations, and services.
xiaohongshu-magazine
A Chinese-language planning guide for treating a Xiaohongshu account as a magazine. Xiaohongshu is a Chinese social platform where people publish and follow posts, and the guide helps define recurring content themes and columns.
xiaohongshu-suite
A Chinese-language workflow guide for improving a Xiaohongshu account, its content, and its path from posts to private messages or sales. It routes a request to a more specific skill, such as titles, profile text, topic planning, comments, or conversion paths.
xiaohongshu-conversion-path
A Xiaohongshu conversion-path guide maps how people move from seeing content on Xiaohongshu, a Chinese social-content platform, to taking a next step such as messaging, booking, trying a tool, or buying.