cta-generator
v1.1.1When the user wants to design, optimize, or audit call-to-action (CTA) buttons. Also use when the user mentions "CTA," "call to action," "button design," "co...
⭐ 0· 127·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description align with the instructions: the SKILL.md contains guidelines, copy suggestions, placement, accessibility checks and testing advice which are exactly what a CTA generator should provide. No unrelated binaries, env vars, or installs are requested.
Instruction Scope
Instructions ask the agent to read optional project context files (.claude/project-context.md or .cursor/project-context.md) to tailor recommendations — this is reasonable for contextualizing CTAs but means the skill will access workspace files if present. Also there are a few content inaccuracies/typos (e.g., 'Accessibility: →.5:1 contrast' looks incorrect) that users should verify against accessibility standards.
Install Mechanism
No install spec and no code files — instruction-only skills pose minimal install risk because nothing is downloaded or written to disk by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The skill does not ask for unrelated secrets or external service tokens.
Persistence & Privilege
always:false and default invocation settings are used. The skill does not request permanent/always-on presence or to modify other skills or system-wide settings.
Assessment
This skill appears coherent and low-risk: it is instruction-only, asks no credentials, and will only read optional project-context files to better tailor CTAs. Before installing or running it, review any .claude/project-context.md or .cursor/project-context.md files in your workspace to ensure they don't contain secrets you wouldn't want to be read. Also verify the accessibility recommendations (there is a likely typo in the contrast guidance) and test any scarcity/urgency copy for ethical and legal appropriateness. Finally, remember the agent may invoke skills autonomously by default — although this skill's lack of credentials limits potential harm.Like a lobster shell, security has layers — review code before you run it.
latestvk97edw3y9r71b25vfmkyxhd36583va10
License
MIT-0
Free to use, modify, and redistribute. No attribution required.