Cold Outreach

v2.0.0

Create targeted, personalized multi-touch cold outreach messages using proven frameworks to engage prospects and boost response rates for B2B and local servi...

1· 2.8k·8 current·8 all-time
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
The SKILL.md is a focused cold-outreach framework with templates, sequence advice, and use cases that match the skill name. There are no unrelated requirements (no env vars, binaries, or installs) that would contradict the stated purpose.
Instruction Scope
Runtime instructions are limited to generating outreach copy and saving outputs to workspace/artifacts/. The doc does not instruct the agent to read unrelated system files, access credentials, or transmit data to external endpoints.
Install Mechanism
No install spec and no code files — this is instruction-only, so nothing will be downloaded or written to disk aside from generated artifacts.
Credentials
No environment variables, credentials, or config paths are requested. The permissions requested are minimal and proportional to a content-generation skill.
Persistence & Privilege
Does not request always:true or other elevated persistence. The skill can be invoked normally; it only writes its outputs to workspace/artifacts/, which is expected for generated content.
Assessment
This skill appears coherent and low-risk, but consider these practical points before use: (1) Review generated messages for accuracy and compliance with spam laws (CAN-SPAM, GDPR, etc.) and platform policies before sending. (2) Avoid including or asking for sensitive personal data or credentials in outreach content. (3) Be cautious about scale — do not use this to run mass blasts without consent or unsubscribe mechanisms. (4) Generated outputs are stored in workspace/artifacts/ — if you paste private data into prompts, it may be persisted there. (5) Always test templates and sequences on a small, controlled sample and vet personalization tokens to avoid embarrassing or harmful errors.

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

latestvk97d1rtnxq1xz59qeksj6pp25h810zcd

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments