ClawHub

Comment Replies

v1.0.0

Draft short, high-clarity replies for comments, objections, and pre-sale questions. Use when responding to public comments on TikTok, X, Instagram, YouTube,...

⭐ 0· 170·0 current·0 all-time
byLeroyCreates@leooooooow
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 SKILL.md all describe drafting short public replies. There are no unexpected environment variables, binaries, or config paths requested that would be unrelated to this purpose.
✓
Instruction Scope
Runtime instructions are limited to identifying comment type, inferring hesitation, and producing short reply variants and optional CTAs. They do not instruct reading system files, accessing environment variables, or contacting external endpoints, and explicitly warn not to invent product details.
✓
Install Mechanism
No install spec or code; instruction-only skill writes nothing to disk and does not download or execute external code.
✓
Credentials
The skill requires no credentials, environment variables, or config paths. Requested scope is minimal and proportional to composing public replies.
✓
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modify other skills. Autonomous invocation is allowed by default (platform behavior) but is not combined with other risky permissions here.
Assessment
This skill appears coherent and low-risk: it only provides an instruction template for writing public replies and asks for nothing sensitive. Before installing, consider: (1) review generated replies before posting to ensure brand voice and legal compliance (avoid making factual or policy claims), (2) ensure the agent or other integrated skills cannot auto-publish without human review if you want manual control, and (3) avoid feeding private or proprietary product details into the prompt—the SKILL.md itself warns not to invent product details, but the model could hallucinate them if given sensitive inputs.

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

latestvk970r8zrk1g1dbs5g05wzavpwd82vk3r

License

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

Comments