{"id":11166,"plugin_id":"plugin_asdk_app_6a7b22a8eaa881918ffc0a2f427d2bbf","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T22:58:55.189Z","digest":"8628c82792d93598a40012901f7e9731cf2ff57c44334835eb596ca70b5b8a4a","against":null,"payload":{"name":"connecting-apis-to-mcp","description":"Use when all four API-evidence inputs exist—and only then: API base URL, authentication scheme, representative safe read, and observed response.","included_files":[],"skill_md_contents":"---\nname: connecting-apis-to-mcp\ndescription: \"Use when all four API-evidence inputs exist—and only then: API base URL, authentication scheme, representative safe read, and observed response.\"\n---\n\n<!-- noodle-skill version:0.62.1 hash:21bbd3ec441ffd30 -->\n\n# connecting-apis-to-mcp\n\nConnect a real API using managed credentials and mappings proven against observed output.\n\n## Use when\n\n- Connect this API after confirming its base URL, authentication scheme, safe read, and observed response.\n\n## Do not use when\n\n- Do not use for static local behavior.\n- Do not use when all available API evidence is stale, inaccessible, undocumented-only, or otherwise unusable.\n\n## Required inputs\n\n- API base URL and authentication scheme.\n- Representative safe read.\n- User intent and observed response shape.\n\n## Workflow\n\nRead and follow the canonical playbook `references/connect-an-api.md` at `../noodle-seed/references/connect-an-api.md`. It owns the workflow; do not recreate it here or load the command catalog speculatively.\nLoad `references/authoring-workflow.md` at `../noodle-seed/references/authoring-workflow.md` only when the playbook or observed evidence names that concern.\n\n## Verification evidence\n\nA safe live read returns populated intentionally mapped fields through the effective local target.\n\n## Recovery paths\n\nSeparate authentication, transport, response-shape, mapping, and empty-result failures before editing.\n\n## Stop conditions\n\nStop before live writes without explicit approval, known effect, and a safe target.\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":{}}