ClawHub

Stickiness Audit

v1.0.0

Run the full SUCCESs stickiness audit on a draft message, pitch, announcement, slide, speech, landing page, or internal memo — the book's capstone diagnostic...

⭐ 0· 32·0 current·0 all-time
byHung Quoc To@quochungto
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
CryptoCan make purchases
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name, description, declared inputs, and the listed dependent 'specialist' skills all align with performing a stickiness audit. No unrelated binaries, credentials, or config paths are requested.
ℹ
Instruction Scope
SKILL.md confines the agent to reading a user-supplied draft, scoring it against the provided rubric, and producing a templated scorecard. It does declare tools-required: Read and Write (file access); this is appropriate for reading pasted or file-backed drafts, but operators should ensure the agent’s Read capability is constrained to the user-supplied document set so it does not read unrelated system files.
✓
Install Mechanism
Instruction-only skill with no install spec and no code files—no downloads or executable installs. Low install risk.
✓
Credentials
No environment variables, credentials, or config paths are required. The requested capabilities (document inputs, Read/Write tools) are proportionate to an audit workflow.
✓
Persistence & Privilege
always:false and default invocation settings; the skill does not request persistent system presence or elevated privileges. It recommends invoking other specialist skills, which is expected behavior for a handoff-oriented audit.
Assessment
This skill appears coherent and appropriate for reviewing drafts: it only needs the text you provide and produces a structured SUCCESs scorecard. Before installing or running it, be mindful of privacy: do not paste sensitive personal or secret data into drafts you don’t want processed. Also check the specialist skills it recommends (the handoff list) before allowing any automated chaining — those dependent skills may have different permissions or behaviors. Finally, ensure the agent environment enforces that the Read tool only accesses user-supplied documents (not arbitrary system files). If you want extra assurance, inspect the dependent skills' SKILL.md files before invoking handoffs.

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

auditvk973tz8234xbw1d9pxw202epzh84waxjbookforgevk973tz8234xbw1d9pxw202epzh84waxjcommunicationvk973tz8234xbw1d9pxw202epzh84waxjcommunications-reviewvk973tz8234xbw1d9pxw202epzh84waxjcopywritingvk973tz8234xbw1d9pxw202epzh84waxjdiagnosticvk973tz8234xbw1d9pxw202epzh84waxjlatestvk973tz8234xbw1d9pxw202epzh84waxjmessagingvk973tz8234xbw1d9pxw202epzh84waxjrubricvk973tz8234xbw1d9pxw202epzh84waxjscorecardvk973tz8234xbw1d9pxw202epzh84waxjstickinessvk973tz8234xbw1d9pxw202epzh84waxjsuccess-frameworkvk973tz8234xbw1d9pxw202epzh84waxj

License

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

Runtime requirements

📚 Clawdis

Comments