← Common RoomCONTENT HISTORY

Update to Common Room

Snapshot Nov 11, 2026 · 00:08 UTC · version 4.2.0

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save Common Room and check future changes in Following.

Up to 3 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Help a sales manager see how their team uses Common Room — a weekly or monthly team snapshot, 1:1 prep for one rep, coaching flags (inactive, researching but not sending, task backlog), which plays the team worked, and trends — and turn any list in the report into a segment. Also serves admins reporting across teams. Use for 'how's my team doing', rep activity, adoption, leaderboards and play activity. For pipeline, meetings or revenue tied to that activity, use roi-attribution.",
  "included_files": [
    {
      "relative_path": "LICENSE",
      "size_in_bytes": 11358
    },
    {
      "relative_path": "NOTICE",
      "size_in_bytes": 173
    },
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 436
    }
  ],
  "name": "manager-report",
  "skill_md_contents": "---\nname: manager-report\ndescription: \"Help a sales manager see how their team uses Common Room — a weekly or monthly team snapshot, 1:1 prep for one rep, coaching flags (inactive, researching but not sending, task backlog), which plays the team worked, and trends — and turn any list in the report into a segment. Also serves admins reporting across teams. Use for 'how's my team doing', rep activity, adoption, leaderboards and play activity. For pipeline, meetings or revenue tied to that activity, use roi-attribution.\"\n---\n\n# Manager Report\n\nAnswers come from `commonroom_query_analytics`, which totals on the server: one call returns a small table. Never page through action rows to count things yourself.\n\n## Data Source\n\nUse the Common Room MCP server as the only source for team activity. If its tools are unavailable or unauthenticated, tell the user that the Common Room connection is required and stop before reporting numbers. Report only what commonroom_query_analytics returns.\n\n## 1. Find \"my team\" (once per conversation)\n\n1. `commonroom_list_objects` objectType `Me` → the caller's `id` and `personas`.\n2. Teams they manage: objectType `Persona`, filter `{\"type\":\"and\",\"clauses\":[{\"type\":\"stringFilter\",\"field\":\"managedBy\",\"params\":{\"op\":\"eq\",\"value\":\"<Me.id>\"}}]}`. Pass those ids as `filters.personaIds`; sub-teams are included.\n3. None returned → they manage no team in Common Room. Fall back to the team in `Me.personas` only if they say it's theirs, or ask which team.\n4. Managers can query only the teams they manage and their sub-teams; anything else is denied. Say so plainly if a request fails that way. Admins and owners can query any team; for the whole workspace, list Personas (no filter, limit 1000) and pass every id with null `parentId`.\n\nOther names: a team by name → list Personas and match, allowing abbreviations (\"BDR\" → \"Business Development Representative\"). A rep by name → `groupBy: [\"rep\"]` on the team and read `repId`. A play by name → objectType `Segment`, `stringFilter` on `segmentName` `like`; near-duplicates are common, so ask or say which you used.\n\n## 2. Time\n\nPass `time.timeZone` (the user's zone). \"This week\" / \"last month\" → `start`/`end` with the zone's offset at each edge, end exclusive. The offset can differ between the two edges across a daylight-saving change. Rolling → `range` (`P7D`, `P30D`). Max one year. Managers think in weeks: default to the last full week, Monday to Monday, unless asked.\n\n## 3. Manager questions\n\n**Team snapshot** — \"how's my team doing?\"\n1. Context: `actions` by `[\"rep\",\"week\"]` over the last 8 weeks including the current partial week. This shows who is new, dormant, bursty or collapsing. Read it before flagging anyone.\n2. Per rep: `contactsResearched`, `recordsActioned`, `tasksMarkedDone`, `tasksDisqualified` by `[\"rep\"]`. Lists every rep with `lastActiveAt` (latest page view) and `lastActionedAt` (latest action), both not limited to the window.\n3. Sequence sends per rep: `records` by `[\"rep\"]`, `filters.repMetrics: [\"recordsAddedToSep\"]`, `sepDestinations` = the sequence destinations (see **Sends**). These are distinct contacts, so they're lower than an `actions` count.\n4. Open tasks: `tasksOpen` by `[\"rep\"]`, `time.asOf` today and again a week ago, for the change.\n5. Calls 2–3 for the previous period, for the change column.\nShow one table: rep · researched · actioned · sent to sequence · tasks done · disqualified · open tasks (change) · change vs last period · last action. List reps with no activity for 90+ days below the table instead of in it, and leave them out of medians. Then the flags, then two or three sentences.\n\n**Coaching flags** (name the rep and the number; compare to the team median, not the top rep):\n- New or returning: no actions in the 8-week context before the last two weeks. The context can't tell a new rep from one back after a long gap, so say \"new or returning\"; don't flag them for low numbers.\n- Dormant: no action for 90+ days (`lastActionedAt`). May have left the team; suggest checking.\n- Active but not acting: page views in the window, 0 on every metric.\n- Big drop: under half their own average of the previous 4 weeks, not just under last week.\n- Researching but not sending: `contactsResearched` at or above the median and sequence sends under a quarter of the median.\n- Disqualifying a lot: `tasksDisqualified` more than half of `tasksMarkedDone`.\n- Backlog growing: `tasksOpen` up week over week while tasks done are below the median. Open-task totals are often whole segments assigned automatically, so the change matters, not the size.\n- Outlier: a value over 10× the median usually means bulk or automated activity. Say \"verify before reading as performance\".\nThese are prompts for a conversation, not verdicts; say so once.\n\n**1:1 prep** — one rep (if asked for \"whoever is most behind\", exclude new or returning and dormant reps and say who you picked and why):\n1. Reuse their rows from the team snapshot if you have it; otherwise run snapshot steps 2–5 with `memberIds: [rep]`.\n2. Trend: `records` by `[\"week\",\"repMetric\"]` with `repMetrics: [\"contactsResearched\",\"tasksMarkedDone\"]` over the last 8 weeks, and sequence sends separately: `records` by `[\"week\"]` with `repMetrics: [\"recordsAddedToSep\"]` and `sepDestinations` = the sequence destinations (see **Sends**). Fill missing weeks with 0 and list them oldest first.\n3. What they worked: `records` by `[\"segment\"]` with `repMetrics: [\"recordsActioned\"]` over the last 4 weeks.\n4. Five recent actions (see **Drill-down**), with names and titles.\nOutput: their numbers beside the team median, the trend in one line, top plays, the recent actions, and 2–3 talking points drawn from the numbers.\n\n**Which plays my team worked**: `records` by `[\"segment\"]` with `repMetrics: [\"recordsActioned\"]` (or sequence sends per **Sends**), sort desc, limit 10; then `records` by `[\"segment\",\"rep\"]` with `segmentIds` for the top 3. Null segment = work outside any play.\n\n**Trend**: `records` by `[\"week\"]` or `[\"month\"]`, plus `[\"rep\"]` or `[\"repMetric\"]`, with `filters.repMetrics`. One call, not one per period.\n\n**Adoption** (\"how many of my reps use it\"): `repsActive`, `repCount`, `groupBy: []`, per team. There is no per-rep grouping; for one rep use `memberIds`.\n\n## 4. Metric reference\n\n| Metric | Counts | Groupings |\n| --- | --- | --- |\n| `contactsResearched` | Contacts the rep viewed, opened profiles of, copied email/phone of, emailed | `rep`, `team`, `segment`, pairs |\n| `recordsActioned` | Records the rep messaged, sent somewhere, changed segment status on, completed a task for | same |\n| `tasksMarkedDone` / `tasksDisqualified` | Segment tasks the rep completed / disqualified | same |\n| `tasksOpen` / `tasksAssigned` | Tasks assigned now (latest daily snapshot) | `rep`, `team`; `time.asOf` |\n| `recordsAddedToSep` | Contacts sent to each destination, success or not | must include `sepDestination` |\n| `repsActive`, `repCount` | Reps with any action or page view / reps covered | `[]` (`repCount` also `team`) |\n| `actions`, `records` | Action count / distinct records, filtered by `repMetrics` | any of rep, team, segment, sepDestination, repMetric, actionType, recordType, month, week |\n\n`filters.repMetrics` and `sepDestinations` work only with `actions`/`records`; passing them with another metric errors with \"applies only to repAction metrics\".\n\n**Sends.** A workflow often sends one contact to several destinations (an Outreach sequence plus a Salesforce export). Get the destination names in use once: `actions` by `[\"sepDestination\"]` with `repMetrics: [\"recordsAddedToSep\"]`. Sequences are `addTo…Sequence`; `exportTo…` and `create…Prospect` create CRM records. Report sequence sends unless asked otherwise, and never add sequence and CRM numbers together.\n\n**Reading results.** A missing rep/week/segment row means 0. `team` rows are each rep's own team, so sub-teams appear separately — roll them up if the manager thinks of one team. Team totals add per-rep values (a contact two reps worked counts twice). `records` counts a record once per rep per period, so weekly rows can sum to more than the whole window. On a 400, the message names the allowed combination; fix and retry once.\n\n## 5. Drill-down\n\nOnly when asked, or five rows for 1:1 prep: `metrics: [\"actions\"]`, `groupBy: [\"action\"]`, same filters, `limit` 25 at most (larger pages exceed the response size). Rows: date, rep, action type, play, destination, `status` (failed sends included — show it), contact email, domain, `recordId`. For names and titles, `list_objects` with `id` and `properties: [\"fullName\",\"title\"]`, one call per contact, so only for the rows shown.\n\n## 6. Present\n\n- Lead with one sentence a manager can act on (\"Two of your eight reps sent nothing to sequences last week.\"), then the table, then flags.\n- State the window, time zone and which teams are covered.\n- Say what a metric counts when it matters (\"sends count attempts, successful or not\").\n- Offer a chart for trends, as a chart or doc artifact if the client supports one.\n- Activity isn't an outcome. For pipeline or meetings, hand off to roi-attribution.\n\n## 7. Turn a list into a segment\n\nWhen a drill-down gives the manager a list worth acting on — \"contacts Sam researched but never sent\", \"records the team actioned in the Job Change play\" — offer to save it as a segment.\n\n1. Collect the `recordId`s from the drill-down rows (page with the cursor until the list is complete). Keep contacts and organizations separate; one segment holds one record type.\n2. Create the segment with commonroom_create_segment (no filter, `entityType` `contact` or `organization` to match the records, named after the report and window), then add the records with commonroom_update_object, up to 100 per call.\n3. Ask before creating: show the name, record type and count, and check for an existing segment of that name with commonroom_list_objects. Then report what was added and anything rejected, with the reason.\n4. Offer the next step: enrolling the segment's contacts or adding them to a call list (contact-actions).\n"
}

SHA-256 of public snapshot: c5d695cb40db39ea1113b63d9b8835288490da381be3a8fcd5243bb8b15eb1a7