ClawHub

Tina Creator - 小红书笔记创作

v1.0.0

生成小红书爆款笔记（标题、正文、标签、AI封面图），采用 Research-Create-Grow 三阶段工作流。Use when the user wants to create Xiaohongshu/小红书 posts, RED notes, social media content for 小红书, or...

⭐ 0· 49·0 current·0 all-time
by@tina-zhang-coder
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the behavior: the skill provides a Research→Create→Grow workflow for Xiaohongshu notes. It requests no credentials, no unrelated binaries, and only uses internal templates and examples—all proportional to the stated purpose.
✓
Instruction Scope
Runtime instructions operate on skill-local files (templates.md, examples.md, strategies/_index.md), interact with the user via AskQuestion, and call GenerateImage for cover art. There are no instructions to read system files, environment variables, or send data to arbitrary external endpoints.
✓
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes surface area (nothing is downloaded or written to arbitrary disk locations by an installer).
✓
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. That matches the simple content-creation purpose.
ℹ
Persistence & Privilege
The skill instructs appending new strategies to strategies/_index.md (i.e., writing to its own strategy file), which is a reasonable, scoped persistence behavior. It is not set to always:true. Be aware the skill can be invoked autonomously by the agent (platform default), but that is not unique or excessive here.
Assessment
This skill appears coherent and low-risk: it uses only packaged templates and examples and asks no credentials. Before installing, consider: (1) the skill will write new strategies to strategies/_index.md inside its bundle—ensure you are okay with persistent notes being stored there; (2) generated cover images use the agent's GenerateImage capability — if your execution environment proxies image generation through an external provider, avoid including private data in prompts; (3) review generated content before publishing (copyright/accuracy). If you want stricter control, disable autonomous invocation for the agent or inspect outputs manually before any external posting.

Like a lobster shell, security has layers — review code before you run it.

latestvk97205cfkn9a2j6v4xxptxnpch83x351

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments