The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and follows instructions provided by the output of the openspec CLI, which serves as a potential vector for data-driven instruction changes. Ingestion points: Data from openspec instructions (JSON) is used to guide artifact generation in SKILL.md. Boundary markers: The skill instructs the agent to treat the context and rules fields as internal constraints and explicitly forbids copying them into the output artifacts. Capability inventory: The agent has the ability to write files to disk and execute various openspec CLI subcommands. Sanitization: The skill does not describe specific sanitization of the instruction text fetched from the CLI.
[DYNAMIC_EXECUTION]: The skill includes logic to dynamically invoke other commands or skills if directed by the instruction field from the CLI tool's output.
[COMMAND_EXECUTION]: The skill relies on executing openspec CLI commands via bash to manage the change lifecycle, retrieve status, and obtain generation templates.

openspec-propose