The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the openspec CLI tool to perform its operations, including listing stores, creating changes, and checking status. The execution environment is restricted to the openspec tool as specified in the allowed-tools frontmatter.
[DYNAMIC_EXECUTION]: The skill includes logic to delegate artifact creation to other commands or skills if specified in the instruction field returned by the openspec CLI.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external CLI outputs that could contain instructions.
Ingestion points: The instruction, context, and rules fields provided by the openspec instructions command output in SKILL.md.
Boundary markers: The skill instructs the agent to treat context and rules as constraints and specifically not to copy them into the final output files.
Capability inventory: The skill has the capability to execute openspec commands and write files to the local filesystem at paths determined by the tool.
Sanitization: No explicit sanitization of the instruction content is performed before the agent processes it.

openspec-propose