Copywriting
v1.0.0When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages,...
⭐ 0· 135·0 current·0 all-time
byMario Karras@mariokarras
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (marketing copy for web pages) align with the skill's content and required artifacts. The SKILL.md provides copy frameworks, templates, and prompts consistent with a copywriting helper; it does not request unrelated system access or credentials.
Instruction Scope
The instructions tell the agent to read local context files if present (.agents/product-marketing-context.md or .claude/product-marketing-context.md and .agents/brand-voice-guide.md). That is coherent with producing brand-aligned copy, but it means the skill will access workspace files if they exist — users should ensure those files do not contain secrets or unrelated sensitive data.
Install Mechanism
No install spec or code files that execute; this is an instruction-only skill so nothing is downloaded or written to disk at install time.
Credentials
Skill declares no required environment variables, credentials, or config paths. The only file access is to workspace documents relevant to copywriting; no disproportionate credential/requested secrets are present.
Persistence & Privilege
always is false and disable-model-invocation is default (agent may call it autonomously, which is normal). The skill does not request elevated or permanent presence, nor does it modify other skills or system-wide settings.
Assessment
This skill appears coherent and safe for its stated use: it provides copy templates and instructs the agent to consult local marketing/brand files if available. Before installing, check any .agents/ or .claude/ context files in your workspace to ensure they don't contain secrets or unrelated sensitive information (the skill may read them to inform copy). Because it's instruction-only and asks for no credentials or installs, the main risk is inadvertent exposure of sensitive data in those local context files — if you want to be cautious, remove or redact secrets from those files or avoid placing them in the agent workspace. If you prefer to limit autonomous runs, you can disable autonomous invocation in your agent settings.Like a lobster shell, security has layers — review code before you run it.
latestvk979ecrfeb0e96qjy0hvbp6b3n834vcx
License
MIT-0
Free to use, modify, and redistribute. No attribution required.