The Agent Skills Directory

[COMMAND_EXECUTION]: Uses curl to interact with external LLM APIs and psql to manage vector database schemas and queries within SKILL.md.
[EXTERNAL_DOWNLOADS]: Communicates with well-known service providers including OpenAI (api.openai.com) for embeddings and Anthropic (api.anthropic.com) for message generation.
[PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by design, as it involves retrieving and processing external document content for use in LLM prompts.
Ingestion points: Functions chunk_text and chunk_by_paragraphs in SKILL.md ingest raw text from external sources.
Boundary markers: Code snippets do not demonstrate the use of XML tags or specific delimiters to isolate retrieved context from instructions.
Capability inventory: The skill uses curl for network requests to AI providers and psql for database operations.
Sanitization: No explicit sanitization or filtering of retrieved document content is implemented in the provided Python or Bash examples.

rag-engineer