ClawHub

Popup Cro

v1.0.0

When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit inte...

⭐ 0· 86·0 current·0 all-time
byMario Karras@mariokarras
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 instructions: the SKILL.md contains extensive, relevant guidance for designing and optimizing popups, triggers, copy, and UX. It references related skills (form-cro, page-cro) appropriately. There are no extra binaries, env vars, or config paths required that would be unrelated to popup/CRO work.
✓
Instruction Scope
Runtime instructions are limited to CRO guidance and behavior recommendations. The only file access the skill explicitly asks for is to read an optional product-marketing-context.md file (in .agents/ or .claude/) before asking questions, which is reasonable for tailoring marketing copy. There are no instructions that direct the agent to collect system secrets, post to unknown endpoints, or read arbitrary unrelated files.
✓
Install Mechanism
No install spec or code files are present (instruction-only), so nothing is downloaded or written to disk. This minimizes execution and persistence risk.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. That is proportionate for a content/advice skill and matches the declared requirements.
✓
Persistence & Privilege
always:false and model invocation is allowed (the platform default). The skill does not request permanent presence or special privileges, and it does not instruct modifying other skills or system-wide settings.
Assessment
This skill is instruction-only and appears coherent for popup/modal CRO work. Before enabling: (1) Confirm you’re comfortable with the agent reading a product-marketing-context.md file if present — review that file for any sensitive content first. (2) Because it can be invoked by the agent (default behavior), ensure you only enable skills for agents you trust; if you want to limit autonomous calls, consider changing the agent policy or disabling model invocation for this skill. (3) No credentials or installs are required, so there is low technical risk from this skill itself, but always monitor agent outputs for accidental disclosure of sensitive information coming from any workspace files the agent can read.

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

latestvk97fp2e0dbjy509k90m2wr471d8399dz

License

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

Comments