ClawHub

FAQ Generator From Reviews

v1.0.0

Turn ecommerce reviews and objections into practical FAQ drafts for product pages and support surfaces. Use when teams want clearer answers built from real c...

⭐ 0· 134·0 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 match the SKILL.md: it transforms user-supplied reviews and objections into FAQ drafts. No unrelated binaries, env vars, or config paths are requested.
✓
Instruction Scope
Runtime instructions are high-level, limited to clustering questions, separating pre/post-purchase issues, and drafting answers. The skill only references an included output template and asks for user-provided reviews and product facts; it does not instruct reading system files, environment variables, or sending data to external endpoints.
✓
Install Mechanism
No install spec or code files beyond the SKILL.md and a template. As an instruction-only skill, it does not write to disk or fetch remote installers.
✓
Credentials
No environment variables, credentials, or config paths are required. Inputs are explicitly user-provided review text and product facts, which is proportionate to the stated goal.
✓
Persistence & Privilege
always is false and the skill is user-invocable. It does not request persistent presence or system-level modification.
Assessment
This skill is instruction-only and internally consistent, but it operates on user-provided review text: do not paste customer PII, payment data, or internal credentials into the input. Sanitize or anonymize review content before use. Verify any factual claims the skill flags as "needs proof" and have a human review answers before publishing (to avoid inaccurate product claims or regulatory issues). Because there is no install or external endpoint, the primary risk is accidental disclosure via the text you supply — treat inputs as sensitive and review outputs for hallucinations or overbroad claims.

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

latestvk979z3aqwv2d5g1wf818r8x2n1833pcx

License

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

Comments