{"id":11175,"plugin_id":"plugin_asdk_app_6a7b22a8eaa881918ffc0a2f427d2bbf","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T22:58:55.324Z","digest":"f91e26963b82638e022443afea30b44e17b40a928bdbfdc2339b623234c29a29","against":null,"payload":{"name":"verifying-mcp-delivery","description":"Use when proving a Noodle Seed MCP project works at a named compile, local, connector, App, host, deployment, or production evidence level.","included_files":[],"skill_md_contents":"---\nname: verifying-mcp-delivery\ndescription: \"Use when proving a Noodle Seed MCP project works at a named compile, local, connector, App, host, deployment, or production evidence level.\"\n---\n\n<!-- noodle-skill version:0.62.1 hash:6ef6ef551e26b78e -->\n\n# verifying-mcp-delivery\n\nReport the highest evidence level actually rerun without upgrading weaker proof.\n\n## Use when\n\n- Verify this MCP delivery before handoff.\n- Prove which delivery layers currently pass.\n\n## Do not use when\n\n- Do not use as a substitute for fixing a known failure.\n- Do not infer hosted health from local success.\n\n## Required inputs\n\n- Requested evidence level.\n- Current target.\n- Existing evidence and its freshness.\n\n## Workflow\n\nRead and follow the canonical playbook `references/verify-and-recover.md` at `../noodle-seed/references/verify-and-recover.md`. It owns the workflow; do not recreate it here or load the command catalog speculatively.\nLoad `references/test-in-hosts.md` at `../noodle-seed/references/test-in-hosts.md` only when the playbook or observed evidence names that concern.\n\n## Verification evidence\n\nEvery dependency below the requested level passes now, or the first unproven layer is explicit.\n\n## Recovery paths\n\nHand a concrete failing layer to debugging-mcp-delivery with all passing evidence preserved.\n\n## Stop conditions\n\nStop after the requested level passes or the first bounded failure is isolated.\n\n## Handoff contract\n\nPass the selected outcome, explicit target, changed files, commands run, passing evidence, first unproven evidence layer, sanitized failure, remaining authority, and exact next action. The receiving skill continues from that layer; do not restart discovery or discard prior proof.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}