The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the openspec list --json command to retrieve the current state of project changes. This is a local, read-only operation necessary for the skill's core functionality.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and analyze local project artifacts, which introduces a surface for indirect prompt injection.
Ingestion points: Reads markdown files from openspec/changes/ and specs/ directories.
Boundary markers: The instructions do not define specific delimiters for parsed file content.
Capability inventory: The agent is permitted to read codebase files, list changes via CLI, and write documentation artifacts (proposals, designs, specs).
Sanitization: There is no explicit requirement to sanitize or validate the content of the documentation files before processing.

openspec-explore