Update to Resolve AI

{
  "name": "investigations",
  "description": "List recent Resolve investigations. Use when the user asks \"show me investigations\", \"list my team's investigations\", \"investigations from last week\", \"what auto-investigations ran today\", \"any manual investigations this month\", or wants a focused investigations view (separate from a full overview snapshot).",
  "included_files": [],
  "skill_md_contents": "---\n# Copyright 2026 Resolve AI, Inc.\n# SPDX-License-Identifier: Apache-2.0\nname: investigations\ndescription: List recent Resolve investigations. Use when the user asks \"show me investigations\", \"list my team's investigations\", \"investigations from last week\", \"what auto-investigations ran today\", \"any manual investigations this month\", or wants a focused investigations view (separate from a full overview snapshot).\nversion: 0.1.0\nargument-hint: <optional filter description>\nlicense: Apache-2.0\n---\n\n# List Resolve Investigations\n\nWraps `list_investigations`.\n\n## Arguments\n\nIf `$ARGUMENTS` is non-empty, translate it into `list_investigations` filters.\n\nIf `$ARGUMENTS` is empty, call `list_investigations` with the tool defaults. Only ask the user to narrow if the result set is overwhelming.\n\n## Filter Intent\n\nMap common phrasings to the right filter family:\n\n- **Time** — \"today\", \"last week\", explicit date ranges, or \"since deploy\".\n- **Ownership** — team, service, or alert context.\n- **Run origin** — auto-investigations vs human-started investigations.\n- **Source** — alert-driven, chat-started, incident, or triage-only.\n- **Volume** — use a limit when the user asks for \"top\", \"latest N\", or a short list.\n\n## Output\n\nSummarize compactly:\n\n- Count + the time range covered.\n- Per-investigation one-liner: `title`, `phase`, `stop_reason` (if terminal), `run_type`, `use_case`, `team`, primary alert summary if present, `created_at`, and the canvas URL (`<your-resolve-host>/chat/<investigation_id>`).\n- When the list is long, group by `phase`, `team`, or `run_type` and offer to narrow.\n- Always surface canvas URLs — they're the user's drill-in path.\n- Preserve any `[label](path)` citations verbatim.\n\nAfter listing, offer the next step: `resolve-ai:investigate <id>` to load one, or `resolve-ai:ask` if the user wants to follow up on a specific investigation.\n\n## Handoffs\n\n- \"Show me everything happening in Resolve\" — broader snapshot → `resolve-ai:overview`.\n- \"Open this one\" — drill in → `resolve-ai:investigate <id>`.\n- \"Show me firing alerts\" — alerts-focused view → `resolve-ai:alerts`.\n- \"What chats are in flight?\" — `resolve-ai:chats`, or `resolve-ai:overview` for the unified view.\n"
}