The Agent Skills Directory

[SAFE]: Analysis of the skill instructions and metadata reveals no malicious intent or suspicious patterns. The skill is designed to improve developer productivity through structured planning.- [PROMPT_INJECTION]: The skill transforms user requirements into implementation plans, creating a surface where malicious input could influence generated tasks.
Ingestion points: Processes external requirements and specifications provided by the user in the context of creating a plan.
Boundary markers: Absent; the skill does not explicitly instruct the agent to distinguish between its own logic and instructions embedded in the user's specification.
Capability inventory: Ability to write plan files to the project directory and suggest shell commands for execution by downstream agents.
Sanitization: Absent; the skill faithfully transcribes requirement details into the plan structure.- [COMMAND_EXECUTION]: The skill includes templates for common development commands such as pytest and git commit. These are provided as part of the generated plan documentation and are not executed by the skill itself during the planning process.

writing-plans