← Plugin catalog
Sales

Common Room

Common Room v4.2.1

Act on contacts & accounts

Create a free account to save this plugin.

From the developer

Not specified in the available declarations: capabilities, limitations, pricing & account requirements.

Onboarding example

Help me choose a priority account from my target accounts and build an approach plan
Sources & dates

Developer declarations; not independently tested. Listing last checked Nov 22, 2026. Package observed Nov 21, 2026.

View package source →

Description

From the marketplace listing

Embed complete buyer intelligence directly within ChatGPT, and act on it. Research accounts and contacts, surface buying signals, and browse activity history - all through natural language. Build prospect lists of net-new companies by industry, size, tech stack, or location. Filter and sort contacts by segment, role, lead score, or website visits. Enroll contacts in sequences or campaigns, add them to call lists, or export them to your CRM, then check the result for every contact. Report on your team's activity and tie it to pipeline. Every result is grounded in real context, real prioritization, and real revenue opportunity directly from your CRM fields, scores, enrichment, and signals - so you always know what's actually happening in your accounts. You can use Common Room to: - Account Research: "Tell me about Datadog and create a plan on how to approach the account." - Contact Lookup: "Research jane.doe@company.com using Common Room." - Prospecting: "Find SaaS companies in the US using Snowflake with 200-1000 employees." - Segment and Role Filtering: "Show me all Economic Buyers in my 'Champions changing jobs' segment." - High-Intent Contacts: "Find contacts at ICP companies who have visited our pricing page this week." - Website Visitor Tracking: "Who visited our pricing page in the last 7 days?" - Segment Building: "Create a segment of ICP accounts that visited the pricing page in the last 30 days." - List Qualification: "Here are 20 webinar attendees and their companies. Which fit our ICP?" - Sequence Enrollment: "Enroll the Acme champions in our Q4 expansion sequence — show me the messages first." - Call Lists: "Load this week's high-intent contacts with phone numbers into the SDR call list." - CRM Export: "Export the new champions we found today to Salesforce." - Action Results: "Did all of yesterday's enrollments go through? Which failed and why?" - Call Follow-up: "Log a demo activity for everyone on today's Figma call." - Team Activity: "How many contacts did each team send to sequences this month?" Outreach, call list and CRM actions are off until a workspace admin turns them on, and ChatGPT asks before each one.

Language: English · Automatically detected from descriptions.

What changed

· 4 observations

Capabilities & instructions

Skill instructions changed from “Smartlead, Zoom Engage) | enroll_in_sequence | Yes, now and on the sequence's schedule | | Salesforce campaign | enroll_in_sequence | Can start the...” to “Nooks, Smartlead, Zoom Engage) | enroll_in_sequence | Yes, now and on the sequence's schedule | | Salesforce campaign |...

View comparison →
Positioning & listing

Full description changed from “Find people and companies that aren't in your workspace yet in Prospector, build prospect lists by industry, size, tech stack, or location, and keep them in...” to “Build prospect lists of net-new companies by industry, size, tech stack, or location. Filter and sort contacts by...

View comparison →

Technical updates · 1

Package or technical metadata updated

View technical comparison →

· 9 observations

Capabilities & instructions

Supporting files updated; open the comparison for details. Skill instructions changed from “Generate a single comprehensive weekly briefing that covers every external customer or prospect call in the next 7 days, with per-meeting account and contact...” to “## Data Sources Use the Common Room MCP server as the...

View comparison →
Capabilities & instructions

Full description changed from “Prospector. Triggers on 'find companies that match [criteria]', 'build a prospect list', 'find contacts at [type of company]', 'show me companies hiring...” to “Prospector, and save the ones that fit to Common Room and a segment. Triggers on 'find companies that match [criteria]',...

View comparison →
Capabilities & instructions

Full description changed from “data. Triggers on 'who is [name]', 'look up [email]', 'research [contact]', 'is [name] a warm lead',” to “data, including people not yet in your workspace. Triggers on 'who is [name]', 'look up [email]', 'research [contact]', 'is [name] a warm lead', 'what does...”. Supporting files...

View comparison →
Capabilities & instructions

Full description changed from “signals. Triggers on 'draft outreach to [person]', 'write an email to [name]', 'compose a message for [contact]',” to “signals, and enroll the contact in a sequence when the seller wants to send. Triggers on 'draft outreach to [person]', 'write an email to [name]', 'compose a...”....

View comparison →
Pricing references

Full description changed from “signals. Triggers on 'prep me for my call with [company]', 'prepare for a meeting with [company]', 'what should I know before talking to [company]', or any...” to “signals, and log what came out of it afterwards. Triggers on 'prep me for my call with [company]', 'prepare for a meeting...

View comparison →
Capabilities & instructions

Full description changed from “data. Triggers on 'research [company]', 'tell me about [domain]', 'pull up signals for [account]', 'what's going on with” to “data, including companies not yet in your workspace. Triggers on 'research [company]', 'tell me about [domain]', 'pull up signals for [account]', 'what's...”....

View comparison →
Pricing references

Full description changed from “ChatGPT. Research accounts and contacts, surface buying signals, and browse activity history - all through natural language. Build prospect lists of net-new...” to “ChatGPT, and act on it. Research accounts and contacts, surface buying signals, and browse activity history - all through...

View comparison →

Technical updates · 1

Package or technical metadata updated

View technical comparison →

· 3 observations

Pricing references

Is template instance added: “false”. Full description: added “- Segment Building: "Create a segment called 'Q4 Expansion Targets' and add Datadog, Snowflake, and Stripe to it."”. Logo url dark changed from “https://files.openai.com/content?id=file_00000000bb0c71fd91d63c48910b9603” to...

View comparison →
Pricing references

Is template instance added: “false”. Full description: added “- Segment Building: "Create a segment called 'Q4 Expansion Targets' and add Datadog, Snowflake, and Stripe to it."”. Logo url dark changed from “https://files.openai.com/content?id=file_00000000bb0c71fd91d63c48910b9603” to...

View comparison →

Technical updates · 1

Package or technical metadata updated

View technical comparison →

Similar plugins

Finding similar plugins… Results will appear here automatically.

Browse plugins →

Files & skills

File archives

Plugin package51 files · 43.1 KBBrowse files →
Skill instructions
account-research8.95 KB

View saved version →

---
name: account-research
description: "Research a company using Common Room data, including companies not yet in your workspace. Triggers on 'research [company]', 'tell me about [domain]', 'pull up signals for [account]', 'what's going on with [company]', 'what's the tech stack at [domain]', 'who's on the buying committee at [company]', 'who are we missing at [company]', or any account-level question."
---

# Account Research

When a company isn't in Common Room, look it up in Prospector instead of stopping.

**Company context** means what the user's company sells and who it sells to (its ICP). Load it only when a step uses it (fit, ICP or positioning), not for plain lookups. `Me.company` gives the company's name, domains and a summary; if that's empty, look the company up as an Organization, then search the web; if neither helps, ask the user once per session.

## Data Source

Use the Common Room MCP server as the primary source. If its tools are unavailable or unauthenticated, tell the user that the Common Room connection is required and stop before producing account conclusions. Ground every account fact in tool output.

## Step 0: Load User Context (Me)

Fetch the `Me` object for the user's title, role, personas and segments. Default all queries to the user's own segments ("My Segments") unless they ask for a broader view.

## Step 1: Identify the Interaction Pattern

- **Pattern 1 — Full overview** ("Tell me about Datadog"): fetch the full property set and produce the briefing in Step 6.
- **Pattern 2 — Targeted question** ("Who owns the Snowflake account?"): fetch only the relevant properties and answer in 1–3 sentences, not a brief.
- **Pattern 3 — Sparse or missing data:** say what Common Room has. No record → Prospector (Step 3.5); limited data → web search (Step 4).
- **Pattern 4 — Combined reasoning** ("Is Stripe a good fit?"): fetch the data, then reason over it (Step 5).
- **Pattern 5 — Buying committee** ("Who are we missing at acme.io?"): Step 5.5.

## Step 2: Look Up the Account

Find the Organization by domain (`companyWebsite`) or name (`companyName`) across the whole workspace, not just My Segments; if it isn't in My Segments, say so. Exact match first; if nothing, try a partial match and confirm with the user before proceeding.

If there's still no match, the company isn't in the workspace. Go to Step 3.5 with its domain; if the user gave only a name, ask for the domain.

## Step 3: Fetch the Right Properties

Call commonroom_get_catalog for the Organization properties this workspace has, then commonroom_list_objects with only the `properties` the question needs:

- `leadScores` — `{scoreId, score, percentile}` per configured score. Report the raw score or percentile, never a label.
- `researchResults` — RoomieAI research answers, each with its `promptName`; `isPrimaryPrompt` marks the primary account summary.
- `topContacts` — up to 5 names and titles, with no scores, and it can still list people who have left. Use it for a quick "who's there" and as the departure check below, not as the ranked contact list.

**Contacts at the account:** a second commonroom_list_objects call on Contact with `companyWebsite` `eq` the domain, sorted by a contact lead score (`ls_*`; check the LeadScore list, since organization scores also appear) descending where the workspace has one (otherwise `latest_activity`), limit 5–10, requesting `title`, `leadScores`, `jobChangeDate`, `previousCompany` and `recentActivities`. Flag anyone whose `jobChangeDate` is recent (a new arrival). This query only returns current employees, so for departures fetch `currentCompany` for any `topContacts` entry it didn't return; anyone now at another company has left — flag them, especially a former champion.

**Recent activity at the account** (full overview): commonroom_list_objects on Activity with `organizationId`, sort `activityTime` descending, limit 15. `EmploymentStarted` entries show contacts taking new roles; when the previous role at th

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 4 — file references are metadata, not package contents.

call-prep6.75 KB

View saved version →

---
name: call-prep
description: "Prepare for a customer or prospect call using Common Room signals, and log what came out of it afterwards. Triggers on 'prep me for my call with [company]', 'prepare for a meeting with [company]', 'what should I know before talking to [company]', 'log my call with [company]', 'what came out of my call with [company]', 'update Common Room after my meeting', or any call preparation or follow-up request."
---

# Call Prep

**Company context** means what the user's company sells and who it sells to (its ICP). Load it only when a step uses it (fit, ICP or positioning), not for plain lookups. `Me.company` gives the company's name, domains and a summary; if that's empty, look the company up as an Organization, then search the web; if neither helps, ask the user once per session.

## Data Sources

Use the Common Room MCP server as the primary source. If its tools are unavailable or unauthenticated, tell the user that the Common Room connection is required and stop before producing signal-backed prep. Use an available calendar connector only to identify meeting context and attendees, and an available conversation intelligence connector only for call transcripts and analysis.

## Prep Process

### Step 1: Identify the Account and Attendees

The company name is required; attendee names are optional.

**Calendar lookup:** If a calendar connector is available, search for upcoming meetings with the named company to automatically surface attendee names, meeting time, and any meeting notes or agenda. Use this to fill gaps the user didn't provide.

If neither attendees nor a calendar match can be found, ask: "Who will be on the call from [Company]? I can research each attendee to make your prep more useful."

### Step 2: Run Account Research

Follow the account-research skill. For call prep, prioritize recent product signals, open opportunities or the renewal timeline, risk signals (declining usage, support tickets, churned seats) and key recent events (funding, executive change, new hire).

In the activity history, prioritize Gong and call recording activities; they show what was said in earlier conversations. Do not filter out call recordings by activity origin.

### Step 3: Run Contact Research for Each Attendee

Follow the contact-research skill for each external attendee. Focus on their role and influence in the buying process, their own activity, recent signals of their current priorities, and their Spark persona if available.

### Step 4: Synthesize Talking Points and Objectives

- The **call objective** (discovery, demo, expansion, renewal, QBR)
- **3–5 talking points**, each grounded in a specific signal and, with company context, tied to the user's product
- **2–3 likely objections or topics** the customer may raise
- A **recommended outcome** for the call

### Step 5: Recency Check (Web Search)

After the Common Room research, check for anything newer than its data. Common Room drives the prep; web search only adds recency.

- **Company news:** `"[company name]" news`, last 14 days: funding, launches, leadership changes, layoffs, partnerships.
- **Attendees:** `"[full name]" "[company name]"`: recent articles, posts, talks or podcasts.

Put a significant item (a new round, a major hire) in Signal Highlights; mention the rest briefly.

### Step 6: After the Call

When the seller asks to log the call or what came out of it. Nothing is written without the seller's approval.

1. **Get the source.** In order: the transcript or call analysis from a conversation intelligence connector (Zoom, Gong) if connected; call recording activity in Common Room; the seller's notes. If there is none, ask for notes. Never infer what happened from the calendar entry alone.
2. **Match attendees.** Look up each external attendee by email with commonroom_list_objects. Offer to save anyone not found with commonroom_create_object. External attendees only; never log activities on teammates.
3. **Pull out what happened,** with 

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 4 — file references are metadata, not package contents.

compose-outreach6.28 KB

View saved version →

---
name: compose-outreach
description: "Generate personalized outreach messages using Common Room signals, and enroll the contact in a sequence when the seller wants to send. Triggers on 'draft outreach to [person]', 'write an email to [name]', 'compose a message for [contact]', 'enroll [person] in [sequence]', 'send this', 'add them to a sequence', or any outreach drafting request."
---

# Compose Outreach

**Company context** means what the user's company sells and who it sells to (its ICP). Load it only when a step uses it (fit, ICP or positioning), not for plain lookups. `Me.company` gives the company's name, domains and a summary; if that's empty, look the company up as an Organization, then search the web; if neither helps, ask the user once per session.

## Data Source

Use the Common Room MCP server as the primary source. If its tools are unavailable or unauthenticated, tell the user that the Common Room connection is required and stop before claiming signal-based personalization. Ground every referenced signal in Common Room output or a cited web result.

## Outreach Process

### Step 1: Look Up the Target

Retrieve the target company and/or contact from Common Room: recent product activity and engagement, community activity, third-party intent signals (job postings, news, funding) and relationship history (prior contact, meetings, email opens).

If the user named a person, research that contact. If only a company was given, pick the best contact by title, engagement and role.

### Step 2: Web Search for External Hooks (If CR Signals Are Thin)

When Common Room returned strong signals, use them and skip web search. When they're thin, or the user asks for external hooks, search:
- `"[company name]" funding OR acquisition OR launch OR announcement` — last 30 days
- `"[contact full name]" "[company name]"` — recent articles, interviews, posts or talks

Prefer hooks under two weeks old that are public and signal change (growth, new role, new product, new market).

### Step 3: Spark (If Available)

Read the contact's Spark summary (`sparkSummary`) for persona, background and influence signals, and use it to set tone and angle.

### Step 4: Identify the Best Hooks

Pick the 1–3 strongest hooks, ranked by recency (last 7–14 days), specificity (a concrete action they took, such as a community question or a new hire wave, not "I noticed you're a customer" or an industry trend) and relevance to what the user's product delivers.

### Step 5: Generate All Three Formats

Write an email, a call script and a LinkedIn message from the strongest hooks, clearly labeled, following `references/outreach-formats-guide.md`. Warm and conversational for inbound or community signals; more formal for cold or executive outreach. With company context, ground the value bridge in the user's product and positioning.

### Step 6: Annotate Your Choices

After the drafts, add 2–4 sentences: which signals were used and why, any assumptions, and alternative angles.

Then offer: "Want me to enroll [Name] in a sequence with this angle?"

### Step 7: Enroll (When the Seller Wants to Send)

Only when the seller asks to send or enroll. Never enroll unasked.

1. **Check the contact is saved.** Enrollment needs a Common Room contact ID. If the target came from web search or Prospector, offer to save them with commonroom_create_object first.
2. **Pick the sequence.** List enrollment destinations with commonroom_list_action_destinations (action enroll_in_sequence). Recommend the one whose name or steps fit the hook from Step 4, and say why. Ask for the sending mailbox when the provider needs one; Zoom Engage sends as the seller by default. If the Sequences category is disabled, stop and say a workspace admin can allow it.
3. **Reconcile the messages.** If the destination uses RoomieAI prompts, get each contact's draft with commonroom_get_message_drafts (up to 10 contacts per call). Compare each draft with the hook. Propose edits that work the hook in while keepi

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 4 — file references are metadata, not package contents.

contact-actions8.06 KB

View saved version →

---
name: contact-actions
description: "Act on contacts: enroll up to 10 named contacts in a sequence or Salesforce campaign after reviewing each contact's message, add a segment or filtered audience to a call list, or export contacts to the CRM, and report results for every contact. Also checks how earlier runs went. Triggers on 'enroll [contacts] in [sequence]', 'push [segment] to the call list', 'run a call blitz on [signal]', 'export [contacts] to Salesforce', 'did that go through', 'why did [contact] fail'."
---

# Contact Actions

Turn an audience into an action. The value is the audience — who qualifies, who must be left out — and matching the action to the signal. The action itself is one step, and every run ends with results per contact.

Enrollment sends real outreach, so it is one-to-one: at most 10 named contacts per run, each with a message the seller has reviewed. Never enroll a segment, filter or signal audience. Call lists and CRM exports send nothing and can take a filtered audience. To draft a fresh message for a contact before enrolling, use compose-outreach.

**Company context** means what the user's company sells and who it sells to (its ICP). Load it only when a step uses it (fit, ICP or positioning), not for plain lookups. `Me.company` gives the company's name, domains and a summary; if that's empty, look the company up as an Organization, then search the web; if neither helps, ask the user once per session.

## Data Source

Use the Common Room MCP server for audiences, destinations, runs and results. If its tools are unavailable or unauthenticated, tell the user that the Common Room connection is required and stop before building an audience or starting a run. Report only outcomes the action logs show.

## Step 0: Load Context

Fetch the `Me` object for the user's segments. Default the audience to "My Segments" unless the seller asks for a wider one.

## Step 1: Define the Audience

The run takes exactly one of:
- **Named contacts:** up to 10 for enrollment, up to 50 for a call list or CRM export. Find their contact IDs with commonroom_list_objects. Anyone not in Common Room must be saved first with commonroom_create_object. Champions who changed jobs come from the moves the seller approved in watchlist; pass them as named contacts.
- **A segment, filter or signal (up to 1,000), for call lists and CRM exports only:** build a contact filter. Check field names and values with commonroom_get_catalog; never guess them.

If the seller asks to enroll a segment or signal audience, preview it (Steps 2–3), then offer to pick up to 10 of the strongest contacts by name and review a message for each. Larger enrollments belong in Common Room or the sequencing tool, not here.

| Seller says | Filter on |
|-------------|-----------|
| "visited the pricing page this week" | contact web visits to /pricing in the last 7 days |
| "high intent" | lead score percentile, intent topics, or the workspace's intent score |
| "in the Enterprise segment" | segment membership |
| "attended the webinar" | activity type and date, or the segment the list was saved to |
| "at ICP accounts" | organization filters for the ICP from the company context |

If the signal is ambiguous ("engaged contacts"), propose a concrete filter and confirm it.

## Step 2: Clean the Audience (Filter Runs)

Add these exclusions unless the seller says otherwise, and list the ones you added:
- **Customers** — for net-new outreach
- **Teammates**
- **Unreachable** — contacts without the phone number a call list needs
- **Recently sequenced** — contacts sent to a sequence in the last 30 days, where the workspace exposes that as a filter

If an exclusion can't be expressed as a filter in this workspace, say so instead of skipping it silently.

## Step 3: Preview (Filter Runs)

Run commonroom_list_objects with the final filter and `"recordCount"` in properties for the total. Show the count, a plain-language filter summary, the exclusions, and 5–10 sample rows wit

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 3 — file references are metadata, not package contents.

contact-research7.06 KB

View saved version →

---
name: contact-research
description: "Research a specific person using Common Room data, including people not yet in your workspace. Triggers on 'who is [name]', 'look up [email]', 'research [contact]', 'is [name] a warm lead', 'what does [email] do', or any contact-level question."
---

# Contact Research

When the person isn't in Common Room, look them up in Prospector by name and company instead of stopping.

**Company context** means what the user's company sells and who it sells to (its ICP). Load it only when a step uses it (fit, ICP or positioning), not for plain lookups. `Me.company` gives the company's name, domains and a summary; if that's empty, look the company up as an Organization, then search the web; if neither helps, ask the user once per session.

## Data Source

Use the Common Room MCP server as the primary source. If its tools are unavailable or unauthenticated, tell the user that the Common Room connection is required and stop before producing a contact profile. Ground every contact fact in tool output.

## Step 1: Locate the Contact

Query Contact with commonroom_list_objects:

| What the user gives | Filter |
|---------------------|--------|
| Email address | `memberEmail` `eq` the full address (most reliable) |
| Name + company | `fullName` `like` the name and `companyWebsite` `eq` the company's domain; show the matches if several |
| Name only | `fullName` `like` the name; if several match, show a brief list and ask which |
| LinkedIn, Twitter/X or GitHub handle | No Contact filter takes a handle. Ask for an email, or a name and company |

If no match is found, say: "Common Room doesn't have a record for this person." Then:
- **Name and company given:** go to Step 1.5.
- **Email only:** use its domain as the company and ask for the name, then go to Step 1.5.
- **LinkedIn URL, Twitter/X or GitHub handle, or name only:** ask for the name and company. Prospector can't be searched by email or profile URL.

## Step 1.5: Look Up People Not in Common Room

Search `ProspectorContact` with `fullName` `like` the name and `companyDomain` `eq` the company's domain, requesting `title`, `companyName`, `seniority` and `linkedInHandle`. If several match, show them and ask which. Reading Prospector adds nothing to the workspace.

If found and their company isn't in Common Room, also find it: `ProspectorCompany` with `groupWebsite` `eq` the domain (exact match; `like` returns unrelated companies), requesting `description`, `employees`, `revenueRange`, `subIndustry`, `technologies` and `location`. Then produce the "Not in Common Room" output below. Prospector has no activity, scores or Spark — skip Steps 2–5.

If not found, say so and offer a web search on their name and company.

For a contact already in Common Room, `jobChangeDate` and `previousCompany` show a job change; `currentCompany` carries the new company's `domain`. If they were a champion, check the new company: in Common Room with commonroom_list_objects (owner, customer status, open opportunity), otherwise in Prospector (`ProspectorCompany`, `groupWebsite` `eq` its domain, requesting `description`, `employees`, `revenueRange`, `subIndustry`, `technologies` and `location`). Rate its fit against the company context. If the new company is a customer or has an open opportunity, tell its owner instead of offering outreach. Otherwise, if it's worth acting on, offer outreach (compose-outreach) or enrollment (contact-actions).

## Step 2: Fetch Contact Properties

Call commonroom_get_catalog for the Contact properties this workspace has, then commonroom_list_objects with only the `properties` the question needs:

- `leadScores` — report the raw score or percentile, never a label.
- `recentActivities` — the contact's own activities, newest first, not your team's. For a set window (default: last 60 days), query Activity with `contactId`, `activityTime` and `activityIsUserInitiated` true.
- `recentWebVisitsNumber` and `recentWebPages` — visit total and top 5 pages f

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 4 — file references are metadata, not package contents.

manager-report9.91 KB

View saved version →

---
name: manager-report
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."
---

# Manager Report

Answers 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.

## Data Source

Use 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.

## 1. Find "my team" (once per conversation)

1. `commonroom_list_objects` objectType `Me` → the caller's `id` and `personas`.
2. 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.
3. 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.
4. 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`.

Other 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.

## 2. Time

Pass `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.

## 3. Manager questions

**Team snapshot** — "how's my team doing?"
1. 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.
2. 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.
3. 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.
4. Open tasks: `tasksOpen` by `["rep"]`, `time.asOf` today and again a week ago, for the change.
5. Calls 2–3 for the previous period, for the change column.
Show 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.

**Coaching flags** (name the rep and the number; compare to the team median, not the top rep):
- 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.
- Dormant: no action for 90+ days (`lastActionedAt`). May h

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 3 — file references are metadata, not package contents.

prospect7.91 KB

View saved version →

---
name: prospect
description: "Build targeted account or contact lists using Common Room's Prospector, and save the ones that fit to Common Room and a segment. Triggers on 'find companies that match [criteria]', 'build a prospect list', 'find contacts at [type of company]', 'show me companies hiring [role]', 'save these to Common Room', 'put these in a segment', 'qualify this attendee list', 'score these domains', 'which of these leads fit our ICP', or any list-building request."
---

# Prospecting

**Company context** means what the user's company sells and who it sells to (its ICP). Load it only when a step uses it (fit, ICP or positioning), not for plain lookups. `Me.company` gives the company's name, domains and a summary; if that's empty, look the company up as an Organization, then search the web; if neither helps, ask the user once per session.

## Data Source

Use the Common Room MCP server and its object catalog. If its tools are unavailable or unauthenticated, tell the user that the Common Room connection is required and stop before producing a prospect list. Show only fields returned by the selected object type.

## Critical Distinction: Two Object Types

Settle which one is in play before running a query:

- **`ProspectorCompany`** — companies **not yet in Common Room**. Firmographic and technographic filters and fields only (industry, size, geography, funding, revenue, tech stack); no signals, scores or activity. Use for net-new lists, territory planning and top-of-funnel expansion.
- **`Organization`** — companies **already in the workspace**. Adds signal, score, segment, CRM and custom-field filters. Use for prioritizing warm accounts, expansion candidates and intent within existing pipeline.

When a request could mean either ("Show companies hiring AI engineers this month"), ask:
> "Are you looking for net-new companies not yet in Common Room, or filtering accounts already in your workspace?"

## Step 0: Load User Context (Me)

Fetch the `Me` object to get the user's segments. When prospecting against `Organization` records (accounts already in CR), default to filtering within "My Segments" unless the user asks for a broader search.

## Step 1: Gather Targeting Criteria

If criteria are already provided, proceed. Otherwise ask what they're looking for: company size, industry, job titles, region, signals such as product activity, or intent such as recent funding or job postings.

Check commonroom_get_catalog for the filters each object type has.

**Lookalike search:** If the user asks to "find companies like [X]", first look up the reference company in Common Room. If it isn't there, find it in Prospector (`ProspectorCompany` with `groupWebsite` `eq` the domain (exact match; `like` returns unrelated companies), requesting `description`, `employees`, `revenueRange`, `subIndustry`, `technologies` and `location`), and use web search only if that returns nothing. Extract its industry, employee range, tech stack, funding stage and geography, propose those as filter criteria, and have the user confirm which matter before running the search.

## Step 2: Refine

With 50 or more results, summarize and suggest a filter to narrow by; with fewer than 5, name the criterion to relax. Apply each follow-up as a change to the current filter, not a new search.

## Step 3: Run the Query and Present Results

Sort by signal strength or fit score where available, not alphabetically. Show only what the query returned ("—" for missing fields), and never mix `ProspectorCompany` and `Organization` fields in one list.

**For `ProspectorCompany` (net-new) results:**

| Company | Domain | Industry | Size | Capital Raised | Revenue | Location |
|---------|--------|----------|------|---------------|---------|----------|

**For `Organization` (in CR) results:**

| Company | Industry | Size | Top Signal | Signal Date | Score | CRM Stage |
|---------|----------|------|-----------|-------------|-------|-----------|

Flag any results where data 

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 4 — file references are metadata, not package contents.

roi-attribution11.3 KB

View saved version →

---
name: roi-attribution
description: "Tie Common Room rep activity to Salesforce outcomes (opportunities, pipeline, closed won). Agrees the customer's definitions first (stages, opp types, amount, match rule, timing), then counts outcomes and attributes them to rep actions where the data allows, and can save the attributed accounts as a segment. Use for ROI, attribution, 'did Common Room source or influence this pipeline', play or rep impact on deals, and QBR/EBR value reports. For activity-only questions use manager-report."
---

# ROI and Attribution

Every customer defines "pipeline", "won" and "touched by Common Room" differently. The definitions are the deliverable: agree them before computing, and repeat them with every number.

Tools: `commonroom_get_catalog`, `commonroom_list_objects` (CRM records), `commonroom_query_analytics` (rep actions), `commonroom_list_action_logs` (per-contact workflow history; only where contact actions are enabled).

## Data Source

Use the Common Room MCP server for CRM records and rep activity. If its tools are unavailable or unauthenticated, tell the user that the Common Room connection is required and stop before producing attribution. Ground every outcome and match in tool output.

## What can be answered

| Question shape | Path | Result |
| --- | --- | --- |
| Outcome counts and amounts (won, created, by month/type/stage) | Step 3 | Exact |
| One rep / one segment / one month of actions → which accounts opened opps | A | Account-level attribution |
| ≤ 10 named opps → was Common Room on them first | B | Contact-level, workflow actions only, needs action logs enabled |
| "How much of all our pipeline/won did Common Room source" | C | Outcomes + activity trend, labelled correlation |

Rep action rows can't be filtered by account, contact or domain, so whole-funnel attribution isn't possible yet. Say so up front when the question needs it, and offer the closest path above. Never estimate attribution from a sample and present it as a total.

## Step 0 — Basics for every analytics call

- `filters` needs `personaIds` or `memberIds`. Whole workspace: `list_objects` objectType `Persona`, every id with null `parentId`. Team names may be abbreviated ("BDR", "AE").
- Windows: at most one year; `start`/`end` with the user's offset (`2026-09-01T00:00:00-04:00`) and `timeZone`.
- Two call shapes. Per-rep counts: `metrics: ["recordsAddedToSep"]` (etc.), no `repMetrics`/`sepDestinations` filters. Action counts and rows: `metrics: ["actions"]` or `["records"]` with `filters.repMetrics` (values: `contactsResearched`, `recordsActioned`, `recordsAddedToSep`, `tasksMarkedDone`, `tasksDisqualified`) and optionally `sepDestinations`. Mixing them errors with "applies only to repAction metrics".
- Destination names in use: `actions` by `["sepDestination"]` with `repMetrics: ["recordsAddedToSep"]`. Sequences are `addTo…Sequence`; `exportTo…` and `create…Prospect` are CRM/record creation, often sent alongside the sequence — count sequences only unless the user says otherwise.
- A play is a segment: `list_objects` objectType `Segment`, `stringFilter` on `segmentName` `like`. Near-duplicate names are common: ask, or state which one you used.

## Step 1 — Find the outcome data

1. `commonroom_get_catalog` — the response is large; extract only the `objectTypeId` (`cot_…`) of the Opportunity object ("CRM Opportunity records"), Account ("CRM Account records") and any "Opportunity Contact Role" junction. Event/Task objects, if present, are meeting candidates. No Opportunity object → stop: Salesforce opportunities aren't mapped.
2. `list_objects` objectType `CustomField`, filter `entityType` eq `<cot_id>`, properties `["id","name"]`, for the Opportunity and then the Account. Opportunity: stage, amount, type / record type, created date, close date. Account: the domain/website field. No created-date field → "sourced" timing can't be checked; say so.

Field ids go in `properties` as `cf_…`; values come back under `custo

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 3 — file references are metadata, not package contents.

watchlist9.21 KB

View saved version →

---
name: watchlist
description: "Monitor the seller's accounts and champions for what changed since the last check — intent and web visits, score jumps, new people engaging, hiring and news, opportunity changes, buyers who left, champions who joined a new company — rank what needs action, and hand off the follow-up. Works as a scheduled run. Triggers on 'what changed on my accounts', 'anything new on my accounts this week', 'which of our champions changed jobs', 'watch these accounts', 'track my champions', 'what should I work on today'."
---

# Watchlist

It suits a scheduled run, for example every Monday morning, when the scheduled task's prompt names the window.

**Company context** means what the user's company sells and who it sells to (its ICP). Load it only when a step uses it (fit, ICP or positioning), not for plain lookups. `Me.company` gives the company's name, domains and a summary; if that's empty, look the company up as an Organization, then search the web; if neither helps, ask the user once per session.

## Data Source

Use the Common Room MCP server as the primary source. If its tools are unavailable or unauthenticated, tell the user that the Common Room connection is required and stop before reporting changes. Ground every change in tool output.

## Step 0: Define the Watchlist

Fetch the `Me` object. The watchlist is accounts, champions, or both:
- **Accounts:** default to "My Segments" or the accounts the seller owns; or a segment or list of domains they name.
- **Segments:** a segment in `Me.segments` holds contacts or organizations. Scope account queries with `groupSegmentId`. For contacts at those accounts, nest an Organization group (`target` "Organization") with `groupSegmentId` in the Contact filter; `memberSegmentId` only matches a segment that holds contacts, such as a champion list; if one comes back empty, check the segment's `entityCount` before reporting no changes.
- **Lead score:** sort by the score the seller uses for accounts. List the scores with objectType LeadScore; ask once if it isn't obvious, and reuse it.
- **Champions:** propose what the workspace has: contacts tagged "Champion" or similar (look up tags with commonroom_list_objects, objectType Tag); a Champion or Economic Buyer Spark persona; contacts on closed-won opportunities, if Salesforce opportunities are mapped; power users by product usage; or a segment the seller names.

If the list is defined by filters, offer to save it as a segment with commonroom_create_segment so it stays current and later runs start from it (with the seller's approval). Reuse a saved watchlist segment when one exists.

Window: the last 7 days, unless the seller gives a start date. Say the window in the heading. Nothing records when the last run happened. For a scheduled run, the scheduled task's prompt should name its window (for example "since last Monday" or "the last 7 days"), matching how often it runs.

## Step 1: Account Changes

Check commonroom_get_catalog for the fields the workspace has; never guess them. Don't look accounts up one at a time. Run one commonroom_list_objects query per kind of change, scoped to the whole watchlist (its segment with `groupSegmentId` or `memberSegmentId`, or its domains with `companyWebsite`) and to the window:

| Change | Query |
|---|---|
| Visits to high-intent pages (pricing, docs, security, integrations) | Organizations with `groupWebVisitLastSeen` in the window, filtered by `groupWebVisitPagesViewed` for those pages. The result carries no visit date, so report these as "visited [pages] in the window" rather than with a date |
| New contacts engaging, especially senior titles or a buying role the account lacked | Contacts at watchlist accounts (a nested Organization group with `groupSegmentId` or `companyWebsite`) with `memberLastActivity` or `memberWebVisitLastSeen` in the window, requesting `recentActivities` for dated activity. Contact results carry no visit date, so report a web visit as "visited in the 

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 3 — file references are metadata, not package contents.

weekly-prep-brief3.83 KB

View saved version →

---
name: weekly-prep-brief
description: "Generate a comprehensive weekly briefing for all external calls in the next 7 days. Triggers on 'weekly prep brief', 'prepare my week', 'what calls do I have this week', 'Monday prep', or any weekly planning request."
---

# Weekly Prep Brief

## Data Sources

Use the Common Room MCP server as the primary account and contact source. If its tools are unavailable or unauthenticated, tell the user that the Common Room connection is required and stop before producing signal-backed briefings. Use an available calendar connector to retrieve meetings; otherwise collect meeting details from the user.

## Briefing Process

### Step 1: Get the Week's External Meetings

**Option A — Calendar connected:**
Use an available calendar connector to fetch all meetings scheduled in the next 7 days (or a user-specified range). Filter to keep only external meetings — those with attendees from outside your organization. Discard internal-only meetings, one-on-ones with colleagues, and recurring internal syncs.

For each external meeting, note the company, the date and time, and the external attendees' names and emails.

**Option B — No calendar connected:**
Ask the user: "To build your weekly prep brief, I'll need your upcoming external calls. Please list them: company name, date/time, and attendee names."

### Step 2: Confirm the Meeting List

Before researching, show the meetings found (company, day, time, attendees) and ask whether anything is missing or should be excluded.

### Step 3: Research Each Meeting

For each confirmed meeting, in parallel where possible:
1. **Account research** — account snapshot using the account-research skill
2. **Contact research** — profile for each external attendee using the contact-research skill

Then a recency check per company, secondary to the Common Room data: search `"[company name]" news` for the last 7 days and, for executive attendees, their name for recent posts or interviews. Include only noteworthy findings (funding, leadership changes, major press).

Research high-priority accounts (large, open opportunity, renewal risk) at full depth; give lower-priority or short meetings 3–4 bullets each.

### Step 4: Synthesize the Weekly Brief

Compile one document sorted by meeting date and time. Open with a week overview that flags accounts with urgent signals (at risk, trial expiring, expansion opportunity), meetings needing special preparation or executive involvement, and the external call count with estimated time.

## Output Format

```
# Weekly Prep Brief — Week of [Date]

## Week Overview
[2–4 bullets: key themes, flagged priorities, call count]

---

## [Monday / Tuesday / etc.]

### [Company Name] — [Time]
**Attendees:** [Names and titles]
**Meeting type:** [Discovery / QBR / Renewal / Expansion / etc. — say if inferred]

**Company Snapshot**
[4–5 bullets: account status, top signals, recent activity]

**Attendee Profiles**
- **[Name]** ([Title]): [2–3 bullets on their signals, persona, conversation angle]
- [Repeat per attendee]

**Top Signals This Week**
[2–3 most relevant signals for this specific call]

**This Week's News** [If notable news found]
[Only genuinely noteworthy findings — funding, leadership changes, major press]

**Recommended Objectives**
[1–2 sentences: what to accomplish in this meeting]

---

[Repeat per meeting, sorted by date/time]
```

**Sparse data:** when Common Room returns little for a meeting's account or attendees, mark that meeting "Limited Data", show only what was returned plus any web findings, and say what's missing so the rep can check before the call. Don't fill the template; every fact must come from a tool call.

## Reference Files

- **`references/briefing-guide.md`** — guidelines for structuring briefings, prioritization logic, and how to handle edge cases (cancelled meetings, new accounts with no data, etc.)

Referenced files: 4 — file references are metadata, not package contents.

Release notes

Updates the listing description and replaces the account-specific starter prompt with one that works in any workspace.

Declared in the saved package. Remote tools may change independently.

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package author
Common Room

Package observed Nov 21, 2026.

Technical details
First seen
Sep 30, 2026 · 22:02 UTC
Last seen
Nov 22, 2026 · 06:00 UTC
Latest observed change
Nov 18, 2026 · 06:12 UTC
Collection status
Collected

plugin_asdk_app_6970230238d8819196e64c67af28ab38

Download plugin data (JSON)

Plugin details: served from cache. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.