The Agent Skills Directory

[COMMAND_EXECUTION]: Executes subcommands of the claude-coach CLI tool for authentication, data synchronization, and querying training history from a local database.
[EXTERNAL_DOWNLOADS]: Utilizes npx to fetch and run the claude-coach utility directly from the npm registry, which is the primary driver of the skill's functionality.
[INDIRECT_PROMPT_INJECTION]: Identifies an attack surface where untrusted data could influence agent behavior.
Ingestion points: Reads historical training activities from a local SQLite database and collects fitness benchmarks from user input via conversation.
Boundary markers: The instructions do not specify the use of delimiters or specific instructions to ignore embedded commands when processing data from the database.
Capability inventory: The skill can execute shell commands via npx, read local reference files, and generate local JSON and HTML files for training plans.
Sanitization: No explicit sanitization or validation logic is defined for the external data being processed and interpolated into the generated training plans.

coach