The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes existing MoonBit implementation files which constitute an untrusted data ingestion surface. Maliciously crafted comments or code could theoretically attempt to influence the agent's behavior during analysis.\n
Ingestion points: Existing MoonBit source code files referenced in the analysis phase (Step 1).\n
Boundary markers: Absent; no specific instructions are provided to the agent to treat input code as untrusted data or to ignore embedded instructions.\n
Capability inventory: The skill directs the agent to execute shell commands (moon check, moon test) which interact with the local environment.\n
Sanitization: Absent; the skill does not suggest any validation or sanitization of the input code prior to processing.\n- [COMMAND_EXECUTION]: The workflow involves executing standard language toolchain commands to verify the extracted specifications and generated tests.\n
The agent is instructed to run moon check and moon test to perform type-checking and execute test suites, which is necessary for the skill's primary function of test generation.\n- [DYNAMIC_EXECUTION]: The skill generates new MoonBit source files and executes them as part of the verification process.\n
The workflow involves creating spec and test files (Steps 2-4) which are then compiled and run by the moon CLI (Step 5).

moonbit-extract-spec-test