ClawHub

screenshot-ux-auditor

v1.0.0

Turn app screenshots into structured UX, copywriting, and conversion audits with issue severity and recommended fixes.

⭐ 0· 164·0 current·0 all-time
byvx：17605205782@52yuanchangxing
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 files and behavior. Declared runtime need (python3) is justified by the included script and there are no unexpected binaries, services, or credentials requested.
✓
Instruction Scope
SKILL.md limits actions to analyzing user-provided screenshots, applying a local heuristics checklist, and optionally running a local script to produce CSV/Markdown. It does not instruct reading unrelated system files, fetching remote payloads, or exfiltrating data.
✓
Install Mechanism
No install spec; skill is instruction-only with a small auditable helper script bundled. No downloads, remote installers, or obscure package pulls are present.
✓
Credentials
No environment variables, credentials, or configuration paths are required. The bundled script operates on explicit user-supplied JSON and writes a CSV to the local working directory.
✓
Persistence & Privilege
Skill is not always-enabled and does not request elevated or persistent privileges or modify other skills. Autonomous invocation is allowed by platform default but the skill itself is not privileged.
Assessment
This skill appears internally consistent and low-risk: it only uses a small local Python script and a local heuristics file. Before running, confirm that the screenshots you provide don't contain sensitive personal data or credentials (the skill will process what you give it). If you want extra assurance, inspect scripts/generate_issue_log.py yourself — it only reads a JSON file and writes a CSV. Ensure python3 is available and review any generated CSV/Markdown before sharing externally. Note: like all skills, it can be invoked by an agent — if you restrict autonomous runs, keep the skill user-invocable only.

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

latestvk971shxae99h3nne3wgn7y5n6x82vgw9

License

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

Runtime requirements

🧰 Clawdis
Binspython3

Comments