Dry-run a hypothetical user message against a public registry skill (no auth, no LLM call)
registry
Dry-run a hypothetical user message against a public registry skill (no auth, no LLM call)
Public dry-run for a registry skill. Mirrors the auth'd
/api/v1/skills/{name}/playground-run but takes a public registry
skill ID and skips the org-ownership check, so a visitor can
sanity-check the trigger match + rendered body BEFORE installing.
Body: { user_input: str, variables?: dict, version_number?: int }
Response shape matches the auth'd endpoint exactly so the UI can
share the result component.
POST
Dry-run a hypothetical user message against a public registry skill (no auth, no LLM call)