Update to Common Room
Snapshot Nov 11, 2026 · 00:08 UTC · version 4.2.0
Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.
Payment or plan references changed
Full description — Now says: 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...
Observed in published text. Live prices and checkout terms have not been verified by this change.
Up to 3 plugins free · no card required.
All fields and original values.
Full description
Sep 30, 2026 · 22:52 UTC
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 call preparation
Nov 11, 2026 · 00:08 UTC
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 ...
Skill instructions
Sep 30, 2026 · 22:52 UTC
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 call preparation request." Produce a complete, scannable call prep brief by combi...
Nov 11, 2026 · 00:08 UTC
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 ...
Supporting files
Sep 30, 2026 · 22:52 UTC
[{"relative_path":"LICENSE","size_in_bytes":11358},{"relative_path":"NOTICE","size_in_bytes":173},{"relative_path":"agents/openai.yaml","size_in_bytes":429},{"relative_path":"references/call-types-guide.md","size_in_bytes":2224},{"relati...
Nov 11, 2026 · 00:08 UTC
[{"relative_path":"LICENSE","size_in_bytes":11358},{"relative_path":"NOTICE","size_in_bytes":173},{"relative_path":"agents/openai.yaml","size_in_bytes":437},{"relative_path":"references/call-types-guide.md","size_in_bytes":2224}]
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -1,23 +1,21 @@ --- name: call-prep -description: "Prepare for a customer or prospect call using Common Room 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 call preparation request." +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 -Produce a complete, scannable call prep brief by combining account research, contact research, and signal synthesis from Common Room. +**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. +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 -Parse what the user has provided: -- **Company name** — required; look up the account in Common Room -- **Attendee names** — optional; if provided, research each one +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. @@ -25,47 +23,46 @@ ### Step 2: Run Account Research -Use the account-research skill process to build a full account snapshot. For call prep, prioritize: -- Recent product signals (what are they doing in the product right now?) -- Open opportunities or renewal timeline -- Any risk signals (declining usage, support tickets, churned seats) -- Key recent events (funding, executive change, new hire) +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). -When reviewing activity history, prioritize Gong and call recording activities — these provide direct context about previous conversations. Do not filter out call recordings by activity origin. +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 -For each external attendee, use the contact-research skill process. For call prep, focus on: -- Role and influence in the buying process -- Their personal activity and engagement history -- Any recent signals that suggest their current mood/priorities -- Spark persona classification if available +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 -Based on the combined account and contact research: -- Identify the **call objective** (e.g., discovery, demo, expansion conversation, renewal, QBR) -- Generate **3–5 tailored talking points** grounded in specific signal data -- Anticipate **2–3 likely objections or topics** the customer may raise -- Suggest a **recommended outcome** for the call - -When the user's company context is available (see `references/my-company-context.md`), tailor talking points to the user's product and value proposition. +- 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 gathering all Common Room data, run a quick recency check to catch anything that happened since the last CR data sync. This is supplementary — CR data drives the prep; web search only adds recency. +After the Common Room research, check for anything newer than its data. Common Room drives the prep; web search only adds recency. -**Company news:** Search `"[company name]" news` filtered to the last 14 days. Look for funding announcements, product launches, leadership changes, layoffs, partnerships, or press coverage. +- **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. -**Attendee presence:** For each external attendee, search `"[full name]" "[company name]"` — look for recent articles, LinkedIn posts, conference talks, podcasts, or published opinions. +Put a significant item (a new round, a major hire) in Signal Highlights; mention the rest briefly. -If a company news item is significant (e.g., just raised a round, announced a major hire), flag it in Signal Highlights. Otherwise, include findings briefly — don't let web search results overshadow CR signals. +### Step 6: After the Call -## Output Format +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 a quote or timestamp for each: meeting type, each attendee's role (only when the source shows it), product feedback and feature requests, objections, commitments with owners and dates, and the next meeting if one was booked. +4. **Propose updates, grouped by record:** + - An activity per attendee with commonroom_create_object: demo → UserInputAttendedDemoAdded; other meeting → UserInputAttendedMeetingAdded; next meeting booked → UserInputBookedMeetingAdded; product feedback → UserInputProvidedProductFeedbackAdded; feature request → UserInputSubmittedFeatureRequestAdded. Body: one or two sentences from the source; occurredAt: the meeting time. + - One note on the organization: summary, objections, next steps with owners and dates. + - Role tags such as "Champion": look up existing tags with commonroom_list_objects (objectType Tag) and reuse them; create a missing one with commonroom_create_object (objectType Tag, entityType contact); apply them with commonroom_update_object. +5. **Write what's approved,** one approval per group, and report what was written and anything rejected, with the reason. Then offer a follow-up email (compose-outreach) or adding attendees to a segment. -The output adapts to how much data Common Room returned. Only include sections where you have real data. Never fill a section with invented details. +## Output Format -### When data is rich (multiple field groups returned, activity history, scores, signals): +Include only sections you have real data for. Never invent deal context: no proposals, competitor comparisons, pricing, trial terms or objections that a tool call didn't return. ``` ## Call Prep: [Company] — [Date/Time if known] @@ -107,34 +104,24 @@ [1–2 sentences: what success looks like for this meeting] ``` -### When data is sparse (few fields returned, no activity, null sparkSummary): - -``` -## Call Prep: [Company] — [Date/Time if known] - -**Data available:** [List exactly what Common Room returned — e.g., "Name, title, email, two tags. No activity history, no scores, no Spark data."] - -### What I Found -[Only the fields actually returned, presented as-is] +**Sparse data** (few properties returned, no activity, null `sparkSummary`): show only what was returned plus any web findings, list what's missing, and say what you can look up next. Don't fill the template. -### Web Search Results -[Findings from web search on the company and attendees — or "No significant results"] +**After the call (Step 6):** -### Suggested Next Steps -- I can pull [specific field groups] from Common Room if available -- I can run deeper web searches on [specific topics] -- You may want to check Common Room directly for [what's missing] ``` +## [Company] — [Meeting type], [date] -Do not generate a full call prep brief from sparse data. A short honest output is always better than a long fabricated one. - -## Quality Standards - -- Ground every talking point in a real signal — no generic filler -- Keep the brief tight — it should be readable in 5 minutes or less -- Flag unknowns explicitly — if attendee research is thin, say so -- Time-box the research — don't over-research at the expense of speed -- **Never invent deal context** — no fabricated proposals, competitor comparisons, pricing, trial terms, or objections not returned by a tool call +**Activities** +| Attendee | Activity type | Body | Source | +|---|---|---|---| + +**Account note** +[Summary · Objections · Next steps with owners and dates] + +**Tags** +| Attendee | Tag | Evidence | +|---|---|---| +``` ## Reference Files
Full technical diff · 3 changed fields
changed /description
"Prepare for a customer or prospect call using Common Room 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 call preparation request."
"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."
changed /included_files
[
{
"relative_path": "LICENSE",
"size_in_bytes": 11358
},
{
"relative_path": "NOTICE",
"size_in_bytes": 173
},
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 429
},
{
"relative_path": "references/call-types-guide.md",
"size_in_bytes": 2224
},
{
"relative_path": "references/my-company-context.md",
"size_in_bytes": 1604
}
][
{
"relative_path": "LICENSE",
"size_in_bytes": 11358
},
{
"relative_path": "NOTICE",
"size_in_bytes": 173
},
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 437
},
{
"relative_path": "references/call-types-guide.md",
"size_in_bytes": 2224
}
]changed /skill_md_contents
"---\nname: call-prep\ndescription: \"Prepare for a customer or prospect call using Common Room 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 call preparation request.\"\n---\n\n# Call Prep\n\nProduce a complete, scannable call prep brief by combining account research, contact research, and signal synthesis from Common Room.\n\n## Data Sources\n\nUse 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.\n\n## Prep Process\n\n### Step 1: Identify the Account and Attendees\n\nParse what the user has provided:\n- **Company name** — required; look up the account in Common Room\n- **Attendee names** — optional; if provided, research each one\n\n**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.\n\nIf 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.\"\n\n### Step 2: Run Account Research\n\nUse the account-research skill process to build a full account snapshot. For call prep, prioritize:\n- Recent product signals (what are they doing in the product right now?)\n- Open opportunities or renewal timeline\n- Any risk signals (declining usage, support tickets, churned seats)\n- Key recent events (funding, executive change, new hire)\n\nWhen reviewing activity history, prioritize Gong and call recording activities — these provide direct context about previous conversations. Do not filter out call recordings by activity origin.\n\n### Step 3: Run Contact Research for Each Attendee\n\nFor each external attendee, use the contact-research skill process. For call prep, focus on:\n- Role and influence in the buying process\n- Their personal activity and engagement history\n- Any recent signals that suggest their current mood/priorities\n- Spark persona classification if available\n\n### Step 4: Synthesize Talking Points and Objectives\n\nBased on the combined account and contact research:\n- Identify the **call objective** (e.g., discovery, demo, expansion conversation, renewal, QBR)\n- Generate **3–5 tailored talking points** grounded in specific signal data\n- Anticipate **2–3 likely objections or topics** the customer may raise\n- Suggest a **recommended outcome** for the call\n\nWhen the user's company context is available (see `references/my-company-context.md`), tailor talking points to the user's product and value proposition.\n\n### Step 5: Recency Check (Web Search)\n\nAfter gathering all Common Room data, run a quick recency check to catch anything that happened since the last CR data sync. This is supplementary — CR data drives the prep; web search only adds recency.\n\n**Company news:** Search `\"[company name]\" news` filtered to the last 14 days. Look for funding announcements, product launches, leadership changes, layoffs, partnerships, or press coverage.\n\n**Attendee presence:** For each external attendee, search `\"[full name]\" \"[company name]\"` — look for recent articles, LinkedIn posts, conference talks, podcasts, or published opinions.\n\nIf a company news item is significant (e.g., just raised a round, announced a major hire), flag it in Signal Highlights. Otherwise, include findings briefly — don't let web search results overshadow CR signals.\n\n## Output Format\n\nThe output adapts to how much data Common Room returned. Only include sections where you have real data. Never fill a section with invented details.\n\n### When data is rich (multiple field groups returned, activity history, scores, signals):\n\n```\n## Call Prep: [Company] — [Date/Time if known]\n\n**Meeting Context**\n[Attendees, meeting type, and any known agenda]\n\n---\n\n### Company Snapshot\n[4–6 bullets: key account status, signals, and recent activity]\n\n---\n\n### Attendee Profiles\n\n**[Attendee Name] — [Title]**\n[3–4 bullets: role, recent activity, Spark persona if available, personal hook]\n\n[Repeat for each attendee]\n\n---\n\n### Signal Highlights\n[Top 3 signals most relevant to this specific call]\n\n---\n\n### Talking Points\n1. [Point tied to a specific signal]\n2. [Point tied to a specific signal]\n3. [Point tied to a specific signal]\n\n### Likely Topics / Objections to Prepare For\n- [Topic or objection + suggested response]\n- [Topic or objection + suggested response]\n\n### Recommended Call Outcome\n[1–2 sentences: what success looks like for this meeting]\n```\n\n### When data is sparse (few fields returned, no activity, null sparkSummary):\n\n```\n## Call Prep: [Company] — [Date/Time if known]\n\n**Data available:** [List exactly what Common Room returned — e.g., \"Name, title, email, two tags. No activity history, no scores, no Spark data.\"]\n\n### What I Found\n[Only the fields actually returned, presented as-is]\n\n### Web Search Results\n[Findings from web search on the company and attendees — or \"No significant results\"]\n\n### Suggested Next Steps\n- I can pull [specific field groups] from Common Room if available\n- I can run deeper web searches on [specific topics]\n- You may want to check Common Room directly for [what's missing]\n```\n\nDo not generate a full call prep brief from sparse data. A short honest output is always better than a long fabricated one.\n\n## Quality Standards\n\n- Ground every talking point in a real signal — no generic filler\n- Keep the brief tight — it should be readable in 5 minutes or less\n- Flag unknowns explicitly — if attendee research is thin, say so\n- Time-box the research — don't over-research at the expense of speed\n- **Never invent deal context** — no fabricated proposals, competitor comparisons, pricing, trial terms, or objections not returned by a tool call\n\n## Reference Files\n\n- **`references/call-types-guide.md`** — guidance for different call types (discovery, expansion, renewal, QBR) and how to tailor prep accordingly\n"
"---\nname: call-prep\ndescription: \"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.\"\n---\n\n# Call Prep\n\n**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.\n\n## Data Sources\n\nUse 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.\n\n## Prep Process\n\n### Step 1: Identify the Account and Attendees\n\nThe company name is required; attendee names are optional.\n\n**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.\n\nIf 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.\"\n\n### Step 2: Run Account Research\n\nFollow 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).\n\nIn 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.\n\n### Step 3: Run Contact Research for Each Attendee\n\nFollow 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.\n\n### Step 4: Synthesize Talking Points and Objectives\n\n- The **call objective** (discovery, demo, expansion, renewal, QBR)\n- **3–5 talking points**, each grounded in a specific signal and, with company context, tied to the user's product\n- **2–3 likely objections or topics** the customer may raise\n- A **recommended outcome** for the call\n\n### Step 5: Recency Check (Web Search)\n\nAfter the Common Room research, check for anything newer than its data. Common Room drives the prep; web search only adds recency.\n\n- **Company news:** `\"[company name]\" news`, last 14 days: funding, launches, leadership changes, layoffs, partnerships.\n- **Attendees:** `\"[full name]\" \"[company name]\"`: recent articles, posts, talks or podcasts.\n\nPut a significant item (a new round, a major hire) in Signal Highlights; mention the rest briefly.\n\n### Step 6: After the Call\n\nWhen the seller asks to log the call or what came out of it. Nothing is written without the seller's approval.\n\n1. **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.\n2. **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.\n3. **Pull out what happened,** with a quote or timestamp for each: meeting type, each attendee's role (only when the source shows it), product feedback and feature requests, objections, commitments with owners and dates, and the next meeting if one was booked.\n4. **Propose updates, grouped by record:**\n - An activity per attendee with commonroom_create_object: demo → UserInputAttendedDemoAdded; other meeting → UserInputAttendedMeetingAdded; next meeting booked → UserInputBookedMeetingAdded; product feedback → UserInputProvidedProductFeedbackAdded; feature request → UserInputSubmittedFeatureRequestAdded. Body: one or two sentences from the source; occurredAt: the meeting time.\n - One note on the organization: summary, objections, next steps with owners and dates.\n - Role tags such as \"Champion\": look up existing tags with commonroom_list_objects (objectType Tag) and reuse them; create a missing one with commonroom_create_object (objectType Tag, entityType contact); apply them with commonroom_update_object.\n5. **Write what's approved,** one approval per group, and report what was written and anything rejected, with the reason. Then offer a follow-up email (compose-outreach) or adding attendees to a segment.\n\n## Output Format\n\nInclude only sections you have real data for. Never invent deal context: no proposals, competitor comparisons, pricing, trial terms or objections that a tool call didn't return.\n\n```\n## Call Prep: [Company] — [Date/Time if known]\n\n**Meeting Context**\n[Attendees, meeting type, and any known agenda]\n\n---\n\n### Company Snapshot\n[4–6 bullets: key account status, signals, and recent activity]\n\n---\n\n### Attendee Profiles\n\n**[Attendee Name] — [Title]**\n[3–4 bullets: role, recent activity, Spark persona if available, personal hook]\n\n[Repeat for each attendee]\n\n---\n\n### Signal Highlights\n[Top 3 signals most relevant to this specific call]\n\n---\n\n### Talking Points\n1. [Point tied to a specific signal]\n2. [Point tied to a specific signal]\n3. [Point tied to a specific signal]\n\n### Likely Topics / Objections to Prepare For\n- [Topic or objection + suggested response]\n- [Topic or objection + suggested response]\n\n### Recommended Call Outcome\n[1–2 sentences: what success looks like for this meeting]\n```\n\n**Sparse data** (few properties returned, no activity, null `sparkSummary`): show only what was returned plus any web findings, list what's missing, and say what you can look up next. Don't fill the template.\n\n**After the call (Step 6):**\n\n```\n## [Company] — [Meeting type], [date]\n\n**Activities**\n| Attendee | Activity type | Body | Source |\n|---|---|---|---|\n\n**Account note**\n[Summary · Objections · Next steps with owners and dates]\n\n**Tags**\n| Attendee | Tag | Evidence |\n|---|---|---|\n```\n\n## Reference Files\n\n- **`references/call-types-guide.md`** — guidance for different call types (discovery, expansion, renewal, QBR) and how to tailor prep accordingly\n"
Full snapshot data
{
"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.",
"included_files": [
{
"relative_path": "LICENSE",
"size_in_bytes": 11358
},
{
"relative_path": "NOTICE",
"size_in_bytes": 173
},
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 437
},
{
"relative_path": "references/call-types-guide.md",
"size_in_bytes": 2224
}
],
"name": "call-prep",
"skill_md_contents": "---\nname: call-prep\ndescription: \"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.\"\n---\n\n# Call Prep\n\n**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.\n\n## Data Sources\n\nUse 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.\n\n## Prep Process\n\n### Step 1: Identify the Account and Attendees\n\nThe company name is required; attendee names are optional.\n\n**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.\n\nIf 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.\"\n\n### Step 2: Run Account Research\n\nFollow 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).\n\nIn 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.\n\n### Step 3: Run Contact Research for Each Attendee\n\nFollow 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.\n\n### Step 4: Synthesize Talking Points and Objectives\n\n- The **call objective** (discovery, demo, expansion, renewal, QBR)\n- **3–5 talking points**, each grounded in a specific signal and, with company context, tied to the user's product\n- **2–3 likely objections or topics** the customer may raise\n- A **recommended outcome** for the call\n\n### Step 5: Recency Check (Web Search)\n\nAfter the Common Room research, check for anything newer than its data. Common Room drives the prep; web search only adds recency.\n\n- **Company news:** `\"[company name]\" news`, last 14 days: funding, launches, leadership changes, layoffs, partnerships.\n- **Attendees:** `\"[full name]\" \"[company name]\"`: recent articles, posts, talks or podcasts.\n\nPut a significant item (a new round, a major hire) in Signal Highlights; mention the rest briefly.\n\n### Step 6: After the Call\n\nWhen the seller asks to log the call or what came out of it. Nothing is written without the seller's approval.\n\n1. **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.\n2. **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.\n3. **Pull out what happened,** with a quote or timestamp for each: meeting type, each attendee's role (only when the source shows it), product feedback and feature requests, objections, commitments with owners and dates, and the next meeting if one was booked.\n4. **Propose updates, grouped by record:**\n - An activity per attendee with commonroom_create_object: demo → UserInputAttendedDemoAdded; other meeting → UserInputAttendedMeetingAdded; next meeting booked → UserInputBookedMeetingAdded; product feedback → UserInputProvidedProductFeedbackAdded; feature request → UserInputSubmittedFeatureRequestAdded. Body: one or two sentences from the source; occurredAt: the meeting time.\n - One note on the organization: summary, objections, next steps with owners and dates.\n - Role tags such as \"Champion\": look up existing tags with commonroom_list_objects (objectType Tag) and reuse them; create a missing one with commonroom_create_object (objectType Tag, entityType contact); apply them with commonroom_update_object.\n5. **Write what's approved,** one approval per group, and report what was written and anything rejected, with the reason. Then offer a follow-up email (compose-outreach) or adding attendees to a segment.\n\n## Output Format\n\nInclude only sections you have real data for. Never invent deal context: no proposals, competitor comparisons, pricing, trial terms or objections that a tool call didn't return.\n\n```\n## Call Prep: [Company] — [Date/Time if known]\n\n**Meeting Context**\n[Attendees, meeting type, and any known agenda]\n\n---\n\n### Company Snapshot\n[4–6 bullets: key account status, signals, and recent activity]\n\n---\n\n### Attendee Profiles\n\n**[Attendee Name] — [Title]**\n[3–4 bullets: role, recent activity, Spark persona if available, personal hook]\n\n[Repeat for each attendee]\n\n---\n\n### Signal Highlights\n[Top 3 signals most relevant to this specific call]\n\n---\n\n### Talking Points\n1. [Point tied to a specific signal]\n2. [Point tied to a specific signal]\n3. [Point tied to a specific signal]\n\n### Likely Topics / Objections to Prepare For\n- [Topic or objection + suggested response]\n- [Topic or objection + suggested response]\n\n### Recommended Call Outcome\n[1–2 sentences: what success looks like for this meeting]\n```\n\n**Sparse data** (few properties returned, no activity, null `sparkSummary`): show only what was returned plus any web findings, list what's missing, and say what you can look up next. Don't fill the template.\n\n**After the call (Step 6):**\n\n```\n## [Company] — [Meeting type], [date]\n\n**Activities**\n| Attendee | Activity type | Body | Source |\n|---|---|---|---|\n\n**Account note**\n[Summary · Objections · Next steps with owners and dates]\n\n**Tags**\n| Attendee | Tag | Evidence |\n|---|---|---|\n```\n\n## Reference Files\n\n- **`references/call-types-guide.md`** — guidance for different call types (discovery, expansion, renewal, QBR) and how to tailor prep accordingly\n"
}SHA-256 of public snapshot: d7a5d4b8d1c2c2149bd73352afc3f5cb051025b4983f2c3225e3a3445d99f798