Cold Email Personalization
v1.0.0Complete cold email system teaching research-driven personalization, "poke the bear" openers, custom signal hunting, and strict QA.
⭐ 1· 973·4 current·4 all-time
by@xeroc
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (cold email personalization) matches contents: templates, research playbook, QA checklist, and scoring rubric. No unrelated credentials, binaries, or install steps are requested.
Instruction Scope
SKILL.md and assets explicitly instruct using web research and scraping tools (Claygent, ZenRows, Serper, SimilarWeb, LinkedIn) and collecting recent signals. That behavior is consistent with personalization, but it implies network scraping and use of third‑party APIs which are not provided by the skill itself and may require separate credentials, licensing, or legal/ToS review.
Install Mechanism
No install spec and no code files that run. Instruction-only skills have minimal on-disk footprint.
Credentials
The skill declares no env vars, no credentials, and no config paths. The only external requirements are conceptual (access to research/scraping tools), which is proportional to the stated research-driven personalization purpose.
Persistence & Privilege
always:false and no install means the skill does not request permanent presence or elevated privileges. It does not modify other skills or system configs.
Assessment
This skill is an offline playbook (templates + instructions) and appears internally consistent. Before installing/use: 1) confirm whether your agent or environment already has access to the third‑party research/scraping tools named (they typically require API keys and paid accounts); 2) review legal/ToS and privacy implications of scraping LinkedIn or other sites and ensure compliance with GDPR/CAN-SPAM and platform rules; 3) test outputs in a sandbox to ensure variables are not populated with unverified facts (the playbook warns against hallucination — follow that); 4) be cautious about automating sends — validate QA & scoring manually before mass mailing to avoid incorrect or sensitive personalization; 5) if you expect the skill to run network calls, supply credentials only to trusted tools and monitor usage. Overall the skill is coherent with its purpose but depends on external tooling and good operational/ethical controls.Like a lobster shell, security has layers — review code before you run it.
latestvk9719yxw99qgnx3xrcys18akkn818v5f
License
MIT-0
Free to use, modify, and redistribute. No attribution required.