The Agent Skills Directory

[PROMPT_INJECTION]: The skill establishes a workflow that processes external requirements to generate implementation plans, creating a surface for indirect prompt injection. Ingestion points: Requirements are processed and saved to markdown files in the docs/plans/ directory. Boundary markers: The generated output utilizes markdown headers and bold step indicators to separate instructions. Capability inventory: The generated plans include instructions for file system modifications and the execution of git and pytest commands. Sanitization: No explicit sanitization or escaping mechanisms for the input specifications are defined in the template.
[COMMAND_EXECUTION]: The skill provides templates for executing standard development commands, such as git add, git commit, and pytest. These commands are restricted to common development tools and are consistent with the skill's primary purpose of implementation planning.

writing-plans