The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a prerequisite bash script located at .specify/scripts/bash/check-prerequisites.sh and runs shell commands like git rev-parse. It also triggers commands defined within the .specify/extensions.yml project configuration.
[INDIRECT_PROMPT_INJECTION]: The skill ingests instructions from multiple project-level documentation files to guide its execution and task management. 1. Ingestion points: .specify/extensions.yml, tasks.md, plan.md, data-model.md, contracts/, research.md, .specify/memory/constitution.md, and quickstart.md. 2. Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent to ignore instructions embedded within these files. 3. Capability inventory: The skill can execute local bash scripts and invoke other skills via EXECUTE_COMMAND. 4. Sanitization: No sanitization or schema validation is defined for the content of the ingested files.
[DYNAMIC_EXECUTION]: The skill dynamically generates and executes command identifiers at runtime by mapping strings found in the .specify/extensions.yml file to command names (e.g., mapping speckit.git.commit to /speckit-git-commit).

speckit-implement