The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from the local codebase and OpenSpec configuration files to ground its suggestions and capture decisions.
Ingestion points: The skill reads local files, codebase search results, and configuration files such as config.yaml to establish context.
Boundary markers: There are no instructions to use delimiters or ignore instructions that may be present within the codebase files.
Capability inventory: The skill can execute various openspec CLI commands and write data to the filesystem.
Sanitization: No sanitization of the content retrieved from the files is mentioned before the agent uses it for reasoning.
[COMMAND_EXECUTION]: The skill relies on executing the openspec CLI to manage project state, changes, and artifacts.
Evidence: Several commands are invoked, including openspec store list, openspec list, openspec new change, openspec status, and openspec instructions.
[DYNAMIC_EXECUTION]: The skill follows instructions from the openspec tool that may delegate tasks to other commands or skills.
Evidence: The instructions specify that if the openspec instructions command output delegates creation to a specific skill or command, the agent should proceed with that invocation.

openspec-explore