The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local PowerShell script (.specify/scripts/powershell/check-prerequisites.ps1) to gather environment data and check project state.
[DYNAMIC_EXECUTION]: The skill implements a plugin-like system that reads command strings from a local configuration file (.specify/extensions.yml) and instructs the agent to execute them (e.g., EXECUTE_COMMAND: {command}). This allows local project configuration to drive agent actions.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from spec.md, plan.md, and tasks.md to generate checklists. These files are potentially untrusted and could contain instructions designed to influence the agent's behavior.
Ingestion points: Files located at FEATURE_DIR/spec.md, FEATURE_DIR/plan.md, and FEATURE_DIR/tasks.md.
Boundary markers: None identified for the requirement data ingested into the prompt.
Capability inventory: The skill can execute local shell scripts, trigger slash commands via hooks, and write/append files to the FEATURE_DIR/checklists/ directory.
Sanitization: The instructions include logic to escape single quotes when passing arguments to the prerequisite script, demonstrating an attempt to prevent command injection.

speckit-checklist