The Agent Skills Directory

[SAFE]: The skill defines a standard developer workflow for formal verification, emphasizing correctness and adherence to a formal specification (Quint).
[COMMAND_EXECUTION]: The skill utilizes legitimate Quint CLI tools (such as quint run, quint verify, and quint typecheck) to validate code against specifications. This command usage is strictly aligned with the skill's stated purpose and is performed within the local project context.
[PROMPT_INJECTION]: Instructions such as 'Never modify the spec to make a failing verification pass' and 'The spec is not advisory — it is the formal statement of what the system must do' are benign operational constraints aimed at ensuring technical accuracy and do not attempt to bypass agent safety filters or override core system instructions.
[DATA_EXPOSURE]: The skill processes local project files (source code and .qnt files) to perform gap analysis and verification. There is no evidence of access to sensitive system paths, credential harvesting, or unauthorized network activity.

quint-execute-spec