The Agent Skills Directory

[SAFE]: The skill contains educational content and workflow instructions related to software engineering best practices such as type-driven design and the 'parse, don't validate' pattern.
[PROMPT_INJECTION]: No attempts to bypass agent safety guidelines, override system instructions, or extract system prompts were found. The 'Constitutional Rules' defined are within the scope of defining the agent's task-specific behavior.
[DATA_EXFILTRATION]: There are no network operations, file access to sensitive paths, or credential harvesting patterns identified.
[REMOTE_CODE_EXECUTION]: No remote script downloads or execution patterns (e.g., curl | bash) were detected. The skill references standard local build tools (cargo, tsc, pyright) relevant to its purpose.
[COMMAND_EXECUTION]: The execution of build and check commands is documented as a verification step for the user's project and does not involve unauthorized or hidden command execution.
[EXTERNAL_DOWNLOADS]: No external URLs or remote dependencies are referenced for download or installation.

type-driven