The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the openspec CLI tool with the list --json argument to retrieve and display available change sets for user selection.
[PROMPT_INJECTION]: This skill presents an indirect prompt injection surface as it reads and interprets requirements from markdown files to modify other files. * Ingestion points: Reads delta specification files from openspec/changes/<name>/specs/*/spec.md and main specifications from openspec/specs/<capability>/spec.md. * Boundary markers: Absent; the agent is instructed to read the raw markdown content to understand and apply 'intelligent merging' based on headers and list structures. * Capability inventory: The agent has the capability to read and write files within the project directory and execute the local openspec CLI. * Sanitization: No explicit sanitization or filtering is performed on the content of the specification files before the agent processes and interprets the instructions contained within.

openspec-sync-specs