The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to interact with the local openspec CLI tool. It executes openspec list --json to retrieve the current state of project changes and openspec status --change "<name>" --json to obtain details about specific artifacts.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is instructed to read and process the contents of codebase files and OpenSpec artifacts provided by the CLI tool's output.
Ingestion points: Local files identified by the artifactPaths in the status JSON and general codebase content.
Boundary markers: None specified; the skill lacks explicit instructions to treat file content as untrusted or to use delimiters.
Capability inventory: The skill can execute local openspec commands and read files. It is explicitly restricted from performing write operations or code implementation.
Sanitization: No validation or sanitization of the ingested file content is mentioned.

openspec-explore