The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from local project files to ground its reasoning in the project's specific context. * Ingestion points: Reads project configuration from openspec/config.yaml and accesses existing artifacts through the openspec CLI. * Boundary markers: The skill contains explicit instructions to treat the ingested configuration as constraints and not to reproduce the content in responses or new artifacts. * Capability inventory: Uses the openspec CLI tool via shell to perform metadata management and artifact generation. * Sanitization: The skill processes these project files as standard text-based artifacts without specialized sanitization logic.

openspec-explore