The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documentation instructs the user to execute npx @yasuakiomokawa/oura-mcp configure, which downloads and runs the vendor-owned MCP server package from the NPM registry.
[COMMAND_EXECUTION]: The setup instructions reference shell command execution (npx) for configuring the underlying tool environment.
[DATA_EXFILTRATION]: The skill is designed to access sensitive personal health data via the Oura API, including sleep cycles, heart rate, and activity levels. This data is retrieved through tools like oura_api_get as part of the intended functionality.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing potentially untrusted strings (e.g., tags and workout descriptions) fetched from the external Oura API.
Ingestion points: The recipes/event-prep.md and recipes/personal-best-discovery.md files specify fetching data from /v2/usercollection/enhanced_tag and /v2/usercollection/workout using the oura_api_get tool.
Boundary markers: The recipes do not specify the use of delimiters or 'ignore' instructions when processing the retrieved text content.
Capability inventory: The skill provides tools for authentication (oura_authenticate) and data retrieval; the agent typically retains standard capabilities such as shell and file system access.
Sanitization: No explicit sanitization or filtering logic is documented for the text retrieved from the API endpoints.
[NO_CODE]: The skill consists entirely of Markdown documentation and instructions, containing no executable scripts or binary files within its own structure.

oura-api-skill