The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the openspec CLI to list active changes and retrieve status information (openspec list --json, openspec status --change "<name>" --json). These commands are scoped to project management within the OpenSpec ecosystem.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data, including codebase files and OpenSpec artifacts (proposal.md, design.md, tasks.md, spec.md), to provide context for discussions. While this introduces a potential attack surface for indirect prompt injection from codebase content, the risk is mitigated by the skill's restricted capabilities.
[SAFE]: The skill contains strong guardrails that explicitly forbid the agent from writing application code or implementing features, limiting its operations to reading files and creating or updating design-related documentation with user consent.

openspec-explore