The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes openspec list --json to retrieve project context, including active changes and their statuses. This is a local command intrinsic to the skill's purpose as an OpenSpec thinking partner.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection as it ingests and processes content from local project artifacts.
Ingestion points: Reads files from the openspec/changes/ directory, including proposal.md, design.md, and tasks.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its primary goals and the potentially untrusted content of the artifacts.
Capability inventory: The skill can execute CLI queries and read the filesystem, but it is explicitly forbidden from implementing code or writing application features.
Sanitization: No sanitization or verification of the artifact content is performed before processing.

openspec-explore