The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script (scripts/build.py) to perform lead classification and data coverage analysis. This is the primary function of the skill and is used to provide an auditable first pass before AI review.
[EXTERNAL_DOWNLOADS]: The skill's documentation provides installation instructions that involve cloning a repository from the official La Growth Machine GitHub organization and using a utility from Vercel Labs. These references are to well-known and relevant services.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted lead data (job titles, company names, and biographies) that could be manipulated to influence the AI's classification decisions during the semantic review pass.
Ingestion points: Data enters the context via the get_audience_leads tool or through CSV file contents provided by the user.
Boundary markers: The skill instructs the agent to use a script-based first pass to categorize leads, but the AI is then tasked with adjudicating a 'review queue' of specific leads.
Capability inventory: The skill has the capability to write data back to the La Growth Machine platform using the create_lead tool.
Sanitization: The skill uses an esc() function within its results widget to escape HTML entities in lead data before rendering them in the UI.

audience-icp-filter