The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the openspec command-line utility to query project status and retrieve instruction templates for artifacts such as proposals, specs, designs, and tasks.- [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by reading external content into the model context. * Ingestion points: The workflow involves reading data from local files including proposal.md, specs/**/*.md, design.md, and tasks.md. * Boundary markers: There are no explicit delimiters or delimiters specified to isolate the content of these files from the agent's core operating instructions. * Capability inventory: The skill possesses the ability to execute CLI commands via the openspec tool based on the processed context. * Sanitization: The instructions do not include steps to sanitize or validate the content of the read artifacts before they are used to generate instructions for subsequent steps.

openspec-continue