The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to manage development services.
Executes torii to start the indexer and configure GraphQL/gRPC APIs.
Utilizes slot CLI for authentication and remote deployments to the Cartridge platform.
Runs sozo and katana for local development workflow management.
[INDIRECT_PROMPT_INJECTION]: The skill configures a system that ingests external data, creating a potential surface for indirect injection.
Ingestion points: Watches blockchain events, indexes model state changes, and processes GraphQL queries.
Boundary markers: None explicitly defined in the provided instructions to separate external data from agent instructions.
Capability inventory: Includes file system writes (--db-dir), network API hosting, and execution of shell commands through the Dojo toolchain.
Sanitization: Relies on the internal validation logic of the Torii indexer and underlying database.

dojo-indexer