The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides a local Python validation script, scripts/check-output.py. This script is designed to verify that the generated strategy documents include all required sections and tables. It operates by reading a local file path provided as an argument and performs string-based matching for headers and placeholders. It does not perform network operations, download external code, or execute untrusted shell commands.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided context regarding Ideal Customer Profiles (ICP), personas, and business problems. While the instructions do not implement strict delimiters or sanitization for this input, the attack surface is limited. The primary output is a structured documentation document, and the skill does not grant the agent capabilities for network exfiltration or persistent file system modifications that could be abused via injected data.
[EXTERNAL_DOWNLOADS]: The skill contains numerous references to official websites, LinkedIn profiles, and GitHub repositories belonging to recognized sales and Go-To-Market (GTM) practitioners and organizations (e.g., Keith Rosen, Becc Holland, LeadMagic, Vercel Labs). These links are used strictly for documentation, expert attribution, and pedagogical purposes. They do not involve the automated retrieval or execution of remote payloads.

cold-email-strategy