Claude Skills by ory

Add a new benchmark task to the bench-swe pipeline from a real GitHub bug-fix. The human provides the GitHub issue or PR URL; the agent handles extraction, validation, and file creation.

Run a health check on the bundled Lumen semantic search setup for the current project, verify backend reachability and index freshness, and summarize remediation steps.

Refresh or rebuild the bundled Lumen index for the current project, preferring MCP-driven refreshes and using the CLI only for an explicit clean rebuild.