{"id":7142,"plugin_id":"plugin_asdk_app_6a4656c688748191be4c5247fb0d5dfc","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T22:49:56.922Z","digest":"fff7aaf7e17acb02f276cc720d2f95dc9c952fa3c0953f44a2e30ca331d6cfa8","against":null,"payload":{"name":"conversation-triage","description":"Find and prioritize the customer conversations a teammate should follow up on: ones that are still unresolved and ones the AI escalated for the team to review. Read a sample, summarize what happened, note any that got a negative rating, and suggest a next step for each. Use when the user asks what needs a reply, which chats to review, what to follow up on, or to sort the support inbox. Do NOT use for aggregate stats (use performance-review) or to change the Agent (use improve-agent).","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":201}],"skill_md_contents":"---\nname: conversation-triage\ndescription: >-\n  Find and prioritize the customer conversations a teammate should follow up on:\n  ones that are still unresolved and ones the AI escalated for the team to\n  review. Read a sample, summarize what happened, note any that got a negative\n  rating, and suggest a next step for each. Use when the user asks what\n  needs a reply, which chats to review, what to follow up on, or to sort the\n  support inbox. Do NOT use for aggregate stats (use performance-review) or to\n  change the Agent (use improve-agent).\nmetadata:\n  author: quickchat-ai\n  version: \"1.0\"\n---\n\n# Conversation triage\n\nSurface the customer conversations a teammate should follow up on, and make each\none actionable.\n\n## Before you start\n- Call `list_scenarios` to resolve the Agent. One Agent -> use it; else ask.\n- Default window: the last 7 days.\n\n## Steps\n1. Use `get_insights` with insight_type=\"flagged\" for the conversations the AI\n   escalated for the team to review. It defaults to the most recent matches\n   across ALL time, so pass `start_date`/`end_date` to constrain it to the\n   window rather than filtering all-time results yourself, and page with\n   `next_cursor` if needed.\n2. Use `list_conversations` with `resolution_status=\"open\"` plus\n   `start_date`/`end_date` for the window to find open conversations.\n3. Open `get_conversation_detail` on the most important few to read the\n   transcript, see what happened, and note any negative rating the customer left.\n4. Where a reply looks wrong or an action seems to have failed, call\n   `get_message_diagnostics` on that conversation: it shows the tools the AI\n   actually executed (with errors) and the Why AI Said That analysis when one\n   exists (`analysis_status=not_generated` means it has not run yet).\n5. Cross-reference: a conversation that is both escalated and unresolved is the\n   top priority.\n6. For each item the user approves, act on it with `update_conversation`:\n   `assign_to` to route it to a teammate (or to 'me'), or `status='resolved'` to\n   close it out (add `assign_to='me'` if it is not yours, `confirm=true` to resolve).\n\n## Guardrails\n- Assigning and resolving are real writes on the customer's Inbox, and resolving\n  ends the conversation and can ask the visitor for a final rating. Ask before\n  each one and never batch them without approval. Both need SUPPORT access or\n  above; if you do not have `update_conversation` on this connection, recommend\n  the next step and tell the user to take it in the Quickchat Inbox instead.\n\n## Output\nA prioritized list, most important first. For each: the customer's request in one\nline, why it is on the list (unresolved or escalated for review), any negative\nrating it received, and a suggested next step. End with the single top item to\nhandle first.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}