Update to Quickchat AI

{
  "name": "performance-review",
  "description": "Produce a performance review of a Quickchat AI Agent: pull conversation volume, resolution rate, CSAT, handoff response time, and topic trends over a period and turn them into a prioritized set of recommendations. Use when the user asks how an Agent is doing, for a weekly or monthly review, a health check, KPIs, or to compare one period against another. Do NOT use for reading individual conversations (use conversation-triage) or changing settings (use improve-agent).",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 190
    },
    {
      "relative_path": "references/metrics-glossary.md",
      "size_in_bytes": 1568
    }
  ],
  "skill_md_contents": "---\nname: performance-review\ndescription: >-\n  Produce a performance review of a Quickchat AI Agent: pull conversation\n  volume, resolution rate, CSAT, handoff response time, and topic trends over a\n  period and turn them into a prioritized set of recommendations. Use when the\n  user asks how an Agent is doing, for a weekly or monthly review, a health\n  check, KPIs, or to compare one period against another. Do NOT use for reading\n  individual conversations (use conversation-triage) or changing settings (use\n  improve-agent).\nmetadata:\n  author: quickchat-ai\n  version: \"1.0\"\n---\n\n# Performance review\n\nTurn a Quickchat AI Agent's analytics into a short, decision-ready review.\n\n## Before you start\n- Call `list_scenarios` to resolve which Agent the user means. Exactly one Agent\n  -> use it; otherwise ask which one.\n- Confirm the period. Default: the last 7 days vs the 7 days before it.\n\n## Steps\n1. Use `compare_periods` to compare the current period with the previous one of\n   equal length. Pass the PREVIOUS (older) window as `period_a` and the CURRENT\n   window as `period_b`: deltas are computed as period_b minus period_a, so this\n   makes a positive delta mean \"up versus the previous period.\" Returns both\n   overviews plus per-metric deltas.\n2. Use `get_topics` for the customer-intent split, and read `topics_by_day` from\n   the overview for free-text themes that are rising.\n3. Use `get_csat` for satisfaction and `get_ttfr` for human handoff speed (only\n   if the Agent hands off).\n4. For any count, rate, total, or trend, ALWAYS use the analytics tools above.\n   Never page through `list_conversations` to compute an aggregate.\n\n## Read the numbers correctly\n- `resolution_rate` already combines confirmed and assumed resolutions; report it\n  as a percentage of conversations.\n- `get_csat` empty means no CSAT was received, NOT a low score — say \"no CSAT\n  data\" rather than implying dissatisfaction.\n- `get_ttfr` measures HUMAN responders after a handoff, in seconds, not\n  business-hours adjusted; prefer the median and note overnight gaps inflate the\n  average.\n- See `references/metrics-glossary.md` for the full field reference.\n\n## Output\n1. One-line headline: better or worse, and why.\n2. A compact table: this period vs last, with deltas, for volume, resolution\n   rate, CSAT, and handoffs.\n3. Rising topics worth attention.\n4. 2-3 concrete, prioritized recommendations.\nKeep it scannable; lead with the metric that moved most.\n"
}