ClawHub

Ecommerce Copy Humanizer TH

v1.0.0

Humanize Thai ecommerce copy to make it sound more natural, local, and less machine-written while preserving selling intent. Best for product pages, social c...

⭐ 0· 114·0 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
The name, description, and SKILL.md all focus on humanizing Thai ecommerce copy; there are no unrelated requirements (no env vars, binaries, or config paths) that would be inconsistent with that purpose.
✓
Instruction Scope
The SKILL.md gives a focused workflow (detect AI tone, rewrite, preserve intent, flag risky phrases). It does not instruct the agent to read system files, access external endpoints, or collect unrelated data. It does ask for contextual inputs (platform, audience, compliance boundaries) which are reasonable for the task.
✓
Install Mechanism
There is no install spec and no code files; this is instruction-only so nothing is written to disk or downloaded during install.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. The inputs it asks the user to provide (copy, platform, tone, banned wording) are proportional and relevant.
✓
Persistence & Privilege
always is false and there is no indication the skill modifies other skills or system settings. disable-model-invocation is false (normal default) meaning the agent could call it autonomously — expected for skills and not by itself a risk.
Assessment
This skill appears coherent and low-risk: it only contains instructions for rewriting Thai ecommerce text and requests no credentials or installs. Before using, avoid pasting any private customer data or secrets into inputs; review rewritten copy for legal or regulated-claims (the skill explicitly excludes legal/medical review), and test outputs on a small set of real examples to confirm tone and compliance. If you want to prevent autonomous invocation, consider setting disable-model-invocation or invoking the skill manually when needed.

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

latestvk979hr0fk72ss67e6s5zgyg1758337f6

License

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

Comments