The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local prerequisite check script located at .specify/scripts/bash/check-prerequisites.sh and various shell commands for project environment verification (e.g., git rev-parse).- [COMMAND_EXECUTION]: The skill implements an extension hook system that automatically triggers the execution of commands defined in the project's .specify/extensions.yml file using the EXECUTE_COMMAND directive.- [DATA_EXPOSURE]: The skill reads several project-specific files to build context, including tasks.md, plan.md, data-model.md, and security-sensitive configuration like .specify/extensions.yml and .specify/memory/constitution.md.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository to drive its logic. * Ingestion points: tasks.md, plan.md, .specify/extensions.yml, and the contracts/ directory (SKILL.md). * Boundary markers: None. The skill does not use delimiters or warnings when processing instructions from these files. * Capability inventory: Shell script execution, file system modifications (creating ignore files), and command execution via extension hooks (SKILL.md). * Sanitization: None. The skill interprets content from the repository as direct instructions for the agent to follow during implementation.

speckit-implement