Cold Email
v1.0.0Write B2B cold emails and follow-up sequences that get replies. Use when the user wants to write cold outreach emails, prospecting emails, cold email campaig...
⭐ 0· 100·0 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 and description match the included guidance, benchmarks, frameworks, and follow-up templates. The skill is instruction-only and does not ask for unrelated credentials, binaries, or system-level access that would be out of scope for a cold-email writer.
Instruction Scope
SKILL.md directs the agent to check for and read .agents/product-marketing-context.md (or .claude/product-marketing-context.md) and to perform prospect research using a local CLI (node tools/clis/exa.js). Reading a product-marketing-context file and using a research tool is coherent with personalization needs, but it does mean the agent will be instructed to access files in the agent workspace and to run a local Node CLI if available — verify those files and the CLI don't contain sensitive secrets or unexpected behavior.
Install Mechanism
No install spec or code files that would be downloaded and executed are present; the skill is instruction-only, so nothing is written to disk by the skill itself during install.
Credentials
The skill declares no environment variables, credentials, or config paths. The only data access it requests is to optional local context files and optional local tooling for prospect research, which are proportionate to personalization objectives but should be reviewed for sensitive content.
Persistence & Privilege
always is false and the skill does not request elevated or permanent platform privileges. It does not modify other skills or system settings. Autonomous invocation is allowed by default (platform normal) but is not combined with other concerning privileges.
Assessment
This skill appears to be what it says: a cold-email writing guide with examples and templates. Before installing or enabling it for autonomous use, check the following: (1) Inspect any .agents/product-marketing-context.md or .claude/product-marketing-context.md files the agent may read — they can contain internal/product or sensitive data you may not want automatically consumed. (2) Confirm whether your agent environment has the referenced local CLI (tools/clis/exa.js); if present, review that CLI's behavior and what network access it has. (3) If you are concerned about automatic file reads, restrict the agent's filesystem access or remove/rename the context files. (4) Remember this skill does not request external credentials, but the agent could still be instructed to query external sources according to the guidance — ensure that any research activity complies with your privacy and compliance rules.Like a lobster shell, security has layers — review code before you run it.
latestvk97eyt2vsneb55050xq73vcf91834enz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.