The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill describes processes for ingesting data from external web sources such as company homepages, job listings, and customer reviews.
Ingestion points: Data extracted from homepages, job posts, help docs, blogs, and reviews as described in SKILL.md.
Boundary markers: The skill does not define specific delimiters for separating untrusted web content from agent instructions during the ingestion process.
Capability inventory: The skill suggests adding a ManyPI MCP server which performs lead searches and data writes.
Sanitization: The skill advocates for a fact-based extraction method to mitigate fabrication risks.
[EXTERNAL_DOWNLOADS]: The skill provides instructions to configure an external MCP server from the author's infrastructure.
Evidence: claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user in SKILL.md.

lead-enrichment