The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies extensively on make targets to manage the local service stack, environment setup, and data processing (e.g., make rc-start, make process, make env-setup). These are standard development operations for the platform.
[EXTERNAL_DOWNLOADS]: The documentation describes setup processes that fetch external dependencies, including npm install for workspace packages and cargo install for the Text Embeddings Inference (TEI) service. It also notes that starting the TEI service downloads a model on the first run.
[PROMPT_INJECTION]: The knowledge pipeline architecture creates a surface for indirect prompt injection. It processes HTML documents from data/knowledge/ into typed resources and indices used by the agent agents.
Ingestion points: HTML files located in data/knowledge/ (SKILL.md)
Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions for the ingested data.
Capability inventory: The agents can perform graph queries, vector searches, and delegate tasks to sub-agents (SKILL.md).
Sanitization: No explicit mention of content sanitization or validation during the transform or ingest stages of the data pipeline.

fit-guide