The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands in its lifecycle hooks to automate the development workflow.
The pre hook executes directory checks to identify existing test suites.
The post hook automatically runs npm test or python -m pytest to verify the generated implementation.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core function of processing external data into executable actions.
Ingestion points: The agent receives external specifications and design documents during the implementation phase.
Boundary markers: There are no explicit delimiters or instructions provided in the skill to ignore embedded commands within the ingested specifications.
Capability inventory: The skill has the ability to write files (Write, MultiEdit) and execute shell commands (Bash).
Sanitization: The skill documentation does not define specific sanitization or validation steps for the input specifications before they are processed.

agent-implementer-sparc-coder