The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the openspec CLI tool to interact with project repositories and artifacts. Commands such as openspec list, openspec status, and openspec store list are used to retrieve context and manage documentation files.
[INDIRECT_PROMPT_INJECTION]: The skill performs codebase investigation by reading files and searching code, which exposes the agent to untrusted data that could contain malicious instructions.
Ingestion points: Reads files and searching code within the local codebase, as well as accessing OpenSpec artifacts like proposals and designs.
Boundary markers: No specific delimiters or safety instructions are provided to separate codebase content from the agent's internal instructions.
Capability inventory: The skill allows execution of local openspec CLI subcommands and file reads, though it includes a strict instruction against writing application code.
Sanitization: There are no documented procedures for sanitizing or validating the content retrieved from the codebase files.

openspec-explore