The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to install the sherpy CLI tool from a remote source (github.com/validkeys/sherpy) using the go install command. This repository is owned by the skill author and represents the intended core functionality for project planning.
[COMMAND_EXECUTION]: The skill uses shell commands (e.g., sherpy prompt, sherpy validate) to interact with the installed CLI tool to retrieve step-specific instructions and verify the integrity of generated YAML planning artifacts.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting user-provided data and project context (such as interview responses and requirements) to generate planning documents. This ingestion point represents an attack surface for instructions embedded in data, though the risk is mitigated by the skill's structured workflow and automated validation steps.
Ingestion points: User responses provided during step-specific interviews and existing artifact files scanned in the target directory (documented in Step 2).
Boundary markers: None explicitly defined in the instruction text to isolate user input from agent logic.
Capability inventory: The agent has the ability to execute shell commands via the CLI tool and perform file system write operations within the specified project directory.
Sanitization: Output validation is performed via sherpy validate for YAML artifacts, but no explicit sanitization of user-provided prompt text is described.

sherpy-cli-planner