ClawHub

小红书标题策略

v0.1.0

Xiaohongshu title strategy skill for Chinese creators. Use when Codex needs to pick the right title formula for a topic, draft, or existing Xiaohongshu title...

⭐ 0· 71·0 current·0 all-time
by@cellinlab
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, and all included files (SKILL.md, formula catalog, workflow, quality rules, template) are coherent: the skill exists to match topics to title formulas and does only that.
✓
Instruction Scope
Instructions tell the agent to read bundled reference files, match trigger families, select formulas, and produce labeled outputs. They do not instruct reading system files, environment variables, network endpoints, or exfiltrating data outside the expected output.
✓
Install Mechanism
No install spec and no code files — instruction-only. Nothing is downloaded or written to disk by the skill itself.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. All required inputs are user-provided content (topic, draft, audience).
✓
Persistence & Privilege
always:false and no special privileges requested. The skill does not modify other skills or system-wide settings; autonomous invocation is allowed by default (platform behavior) but not elevated here.
Assessment
This skill is instruction-only and appears internally consistent: it uses only the bundled reference docs and templates to produce Xiaohongshu title suggestions and asks for no secrets. Before installing, consider: (1) do you trust the skill source (GitHub repo link provided)? If provenance matters, verify the repo/author. (2) Don’t paste sensitive secrets or personal data into prompts — the skill expects content drafts/topics, not credentials. (3) The skill references other skill names (e.g., $content-strategy-diagnosis); those are placeholders and may require other installed skills to work as intended. (4) If you prefer the agent not to call skills autonomously, adjust agent settings (this skill itself does not force autonomy).

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

latestvk971xxwy258s4xvyas608s8khx84kjns

License

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

Comments