The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run node website/scripts/sync-docs.mjs to validate documentation changes during the consolidation step. This command execution targets a local script within the project's repository structure.
[INDIRECT_PROMPT_INJECTION]: The skill's iterative drafting process involves reading from and writing to multiple files, which creates a surface for indirect prompt injection.
Ingestion points: The agent reads project metadata and context from docs-lab/README.md, docs-lab/message-map.md, and existing content or user edits within the target documentation page (SKILL.md).
Boundary markers: The instructions lack specific delimiters or negative constraints to prevent the agent from following instructions potentially embedded within the documentation it is tasked to process.
Capability inventory: The skill possesses the ability to modify documentation files, search the project directory using grep, and execute a local Node.js script.
Sanitization: The skill does not define any sanitization or validation procedures for the content read from files before it is processed or incorporated into new drafts.

draft-openspec-docs