The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute several commands via the effect-solutions CLI tool, such as effect-solutions list and various show subcommands (e.g., effect-solutions show basics, effect-solutions show testing), to fetch documentation and recommended configurations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to review and debug external Effect TypeScript code, which represents an ingestion surface for potentially untrusted instructions. 1. Ingestion points: Source code files containing Effect services and runtime boundaries. 2. Boundary markers: No specific delimiters or safety instructions are defined to separate ingested code from the agent's logic. 3. Capability inventory: The skill can execute CLI commands and propose code modifications. 4. Sanitization: There are no explicit sanitization procedures for the code being reviewed.

effect-ts