← Common RoomCONTENT HISTORY

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.

WHAT CHANGED

Instructions updated for prospect

Full description — Now says: 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...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Common Room and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Full description

Before

Sep 30, 2026 · 22:52 UTC

Prospector. Triggers on 'find companies that match [criteria]', 'build a prospect list', 'find contacts at [type of company]', 'show me companies hiring [role]',

After

Nov 11, 2026 · 00:08 UTC

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 Com...

Skill instructions

Before

Sep 30, 2026 · 22:52 UTC

Prospector. Triggers on 'find companies that match [criteria]', 'build a prospect list', 'find contacts at [type of company]', 'show me companies hiring [role]', or any list-building request." Build targeted account and contact lists usi...

After

Nov 11, 2026 · 00:08 UTC

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 Com...

Supporting files

Before

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":433},{"relative_path":"references/me-context.md","size_in_bytes":2103},{"relative_pat...

After

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":430},{"relative_path":"references/prospect-guide.md","size_in_bytes":1940}]

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,11 +1,11 @@
 ---
 name: prospect
-description: "Build targeted account or contact lists using Common Room's Prospector. Triggers on 'find companies that match [criteria]', 'build a prospect list', 'find contacts at [type of company]', 'show me companies hiring [role]', or any list-building request."
+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
 
-Build targeted account and contact lists using Common Room's Prospector. Supports iterative refinement through natural conversation, intent-based discovery, and both net-new prospecting and signal-based queries against existing accounts.
+**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
 
@@ -13,59 +13,35 @@
 
 ## Critical Distinction: Two Object Types
 
-Common Room's Prospector operates against two fundamentally different object types. Always clarify which one is in play before running a query:
+Settle which one is in play before running a query:
 
-**`ProspectorOrganization`** — Companies **not yet in Common Room**
-- Net-new companies that match specified criteria
-- Available fields are firmographic only: name, domain, size, industry, capital raised, annual revenue, location
-- Fewer filter options — no signal-based filters, no scores, no activity history
-- Use when: building a brand-new target list, territory planning, top-of-funnel expansion
-
-**`Organization`** (in Common Room) — Companies **already in your CR workspace**
-- Full signal data available: product usage, community activity, CRM fields, scores, custom fields
-- Much richer filter set — includes signal-based, score-based, segment-based, and firmographic filters
-- Use when: finding warm accounts to prioritize, identifying expansion candidates, surfacing intent signals within existing pipeline
+- **`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 user's request could apply to both (e.g., "Show companies hiring AI engineers this month"), clarify:
+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?"
 
-The catalog should make this distinction explicit so the LLM can select the right Prospector endpoint.
-
 ## 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 kind of accounts or contacts are you looking for? For example: company size, industry, job titles, signals like recent product activity or community engagement, geographic region, or specific intent signals like recent funding or job postings."
-
-Use the Common Room object catalog to see available filters for each object type. The key distinction:
-- **ProspectorOrganization** — firmographic and technographic filters only (industry, size, geography, funding, tech stack)
-- **Organization** — all firmographic filters plus signal-based, score-based, segment-based, and CRM filters
+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.
 
-**Lookalike search:** If the user asks to "find companies like [X]", first look up the reference company in Common Room (or via web search if not in CR). Extract its key attributes — industry, employee range, tech stack, funding stage, geography — and propose those as filter criteria. Present the derived criteria to the user for confirmation before running the search, since lookalike targeting works best when the user can refine which attributes matter most.
+Check commonroom_get_catalog for the filters each object type has.
 
-## Step 2: Support Iterative Refinement
+**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.
 
-Prospecting is conversational. Support multi-turn refinement naturally:
+## Step 2: Refine
 
-1. Run initial query with provided criteria
-2. If results are large (50+), summarize and offer: "I found [N] results. Want to narrow by [suggested filter]?"
-3. If results are too few (< 5), suggest: "Only [N] results with those filters — I can broaden by relaxing [specific criterion]."
-4. Apply each refinement as a follow-up query, not a new search from scratch
-
-Example flow:
-- Rep: "Find cybersecurity companies in California." → 500 results
-- Rep: "Only show ones over 300 employees using AWS." → 47 results
-- Rep: "Focus on the ones with recent hiring activity." → 12 results ✓
+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
 
-Execute the Prospector query with confirmed criteria. Sort by signal strength or fit score where available (not alphabetically).
+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 `ProspectorOrganization` (net-new) results:**
+**For `ProspectorCompany` (net-new) results:**
 
 | Company | Domain | Industry | Size | Capital Raised | Revenue | Location |
 |---------|--------|----------|------|---------------|---------|----------|
@@ -77,28 +53,43 @@
 
 Flag any results where data is thin or the most recent signal is older than 90 days.
 
-## Step 3.5: Enrich Net-New Results with Web Search
+## Step 3.5: Fill In Net-New Results
+
+For `ProspectorCompany` results, request `primaryWebsite`, `employees`, `revenueRange`, `subIndustry`, `technologies`, `raised` and `location` in the query itself (defaults are only `id` and `name`), so no second call is needed.
 
-For `ProspectorOrganization` results (net-new companies not in CR), run a quick web search on the top 3–5 companies to add context beyond firmographics. CR has no behavioral signals for these companies, so web search fills the gap — look for recent funding, product launches, leadership changes, or news coverage. Include findings as brief annotations next to each company in the results.
+Then run a quick web search on the top 3–5 for recent news — funding, product launches, leadership changes — which Prospector doesn't cover. Include findings as brief annotations next to each company.
 
 ## Step 4: Offer Next Steps
 
-- "Want me to draft outreach for the top 3–5 prospects?"
-- "Should I run a full account brief on any of these?"
-- "Want to refine the criteria or add another filter?"
-- "I can format this as a CSV if you'd like to export it."
-- "For any net-new companies here, I can add them to Common Room for enrichment." *(future capability)*
-
-## Quality Standards
-
-- Always confirm which object type (ProspectorOrg vs Organization) before running the query
-- Default to "My Segments" when querying Organization records, unless user specifies otherwise
-- Support iterative refinement — treat each follow-up as a filter adjustment, not a fresh start
-- Never mix result fields from ProspectorOrganization and Organization in the same list
-- Fewer high-quality results beat a long unqualified list
-- **Only show data the query returned** — leave blank or "—" for missing fields, don't invent values
+Offer to save the results to Common Room and a segment (Step 5), draft outreach for the top 3–5, run a full account brief on any of them, refine the criteria, or format the list as CSV.
+
+## Step 5: Save the List (When the Seller Asks)
+
+Nothing is saved or segmented without the seller's approval. Show what will be written: the records, the fields and the segment.
+
+1. **Dedupe.** Check each net-new company by domain with commonroom_list_objects. Mark each result as new or already in Common Room; for existing ones, show the owner and segments.
+2. **Check fit.** For each new result, say whether it meets the seller's criteria and the ICP from the company context, naming the fields that decided it. Recommend save or skip.
+3. **Save.** Create the approved companies and contacts with commonroom_create_object, passing prospectorCompanyId or prospectorContactId so name, domain, title and firmographics fill in.
+4. **Segment.** Ask whether to use an existing segment or create one.
+   - If the criteria map to Common Room filters, offer a segment built from those filters with commonroom_create_segment, so it stays current as companies start or stop matching.
+   - Otherwise create a segment with no filter and add the saved records with commonroom_update_object, up to 100 per call.
+   - For a team segment, ask which teams it's for and which owner field matches records to reps, and whether to pin it to each assignee's Home and to their "My segments" (the tool needs both answers). Set personaIds, assignment, addToHome and addToMySegments.
+5. **Report.** Saved, already existed, added to segment, skipped, failed.
+
+## List Mode: Qualify a List the Seller Brings
+
+When the seller pastes or attaches emails, LinkedIn URLs or domains — event attendees, webinar registrants, inbound domains — instead of criteria:
+
+1. **Read the list.** Find one identifier per row: email, LinkedIn URL or domain. Report rows without one; never guess an email or domain from a name.
+2. **Split known from new.** Check each row with commonroom_list_objects (contacts by email, organizations by domain). Known records keep their scores, owner, segments and signals.
+3. **Look up the new ones in Prospector.** Domains: `ProspectorCompany` with `groupWebsite` `eq` the domain (exact match; `like` returns unrelated companies), requesting `description`, `employees`, `revenueRange`, `subIndustry`, `technologies` and `location`, plus `primaryWebsite`, with up to 25 domains per query as an `or` group of `eq` clauses; match results back to rows by `primaryWebsite`. People: `ProspectorContact` by `fullName` and `companyDomain` when the row has both; Prospector can't be searched by email or LinkedIn URL alone, so label those rows "not looked up". Keep not-found rows, labeled.
+4. **Score fit** against the ICP from the company context or the seller's criteria: Strong, Possible, Poor or Unknown, naming the one or two fields that decided it. Never score from a company name alone.
+5. **Present** Strong first, with counts:
+   | Name / Company | Identifier | In CR? | Fit | Why | Proposed action |
+6. **Save** the approved rows with Step 5, creating each from its own email, LinkedIn URL or domain or its Prospector ID when step 3 found one, and offer to enroll the Strong-fit contacts or add them to a call list (contact-actions).
+
+Large lists: work in batches of 25 and report progress.
 
 ## Reference Files
 
 - **`references/prospect-guide.md`** — filter types, signal-based sorting, object type distinctions, and list-building strategies
-- **`references/me-context.md`** — current-user and My Segments scoping
Full technical diff · 3 changed fields

changed /description

BEFORE
"Build targeted account or contact lists using Common Room's Prospector. Triggers on 'find companies that match [criteria]', 'build a prospect list', 'find contacts at [type of company]', 'show me companies hiring [role]', or any list-building request."
AFTER
"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."

changed /included_files

BEFORE
[
  {
    "relative_path": "LICENSE",
    "size_in_bytes": 11358
  },
  {
    "relative_path": "NOTICE",
    "size_in_bytes": 173
  },
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 433
  },
  {
    "relative_path": "references/me-context.md",
    "size_in_bytes": 2103
  },
  {
    "relative_path": "references/prospect-guide.md",
    "size_in_bytes": 1963
  }
]
AFTER
[
  {
    "relative_path": "LICENSE",
    "size_in_bytes": 11358
  },
  {
    "relative_path": "NOTICE",
    "size_in_bytes": 173
  },
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 430
  },
  {
    "relative_path": "references/prospect-guide.md",
    "size_in_bytes": 1940
  }
]

changed /skill_md_contents

BEFORE
"---\nname: prospect\ndescription: \"Build targeted account or contact lists using Common Room's Prospector. Triggers on 'find companies that match [criteria]', 'build a prospect list', 'find contacts at [type of company]', 'show me companies hiring [role]', or any list-building request.\"\n---\n\n# Prospecting\n\nBuild targeted account and contact lists using Common Room's Prospector. Supports iterative refinement through natural conversation, intent-based discovery, and both net-new prospecting and signal-based queries against existing accounts.\n\n## Data Source\n\nUse 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.\n\n## Critical Distinction: Two Object Types\n\nCommon Room's Prospector operates against two fundamentally different object types. Always clarify which one is in play before running a query:\n\n**`ProspectorOrganization`** — Companies **not yet in Common Room**\n- Net-new companies that match specified criteria\n- Available fields are firmographic only: name, domain, size, industry, capital raised, annual revenue, location\n- Fewer filter options — no signal-based filters, no scores, no activity history\n- Use when: building a brand-new target list, territory planning, top-of-funnel expansion\n\n**`Organization`** (in Common Room) — Companies **already in your CR workspace**\n- Full signal data available: product usage, community activity, CRM fields, scores, custom fields\n- Much richer filter set — includes signal-based, score-based, segment-based, and firmographic filters\n- Use when: finding warm accounts to prioritize, identifying expansion candidates, surfacing intent signals within existing pipeline\n\nWhen a user's request could apply to both (e.g., \"Show companies hiring AI engineers this month\"), clarify:\n> \"Are you looking for net-new companies not yet in Common Room, or filtering accounts already in your workspace?\"\n\nThe catalog should make this distinction explicit so the LLM can select the right Prospector endpoint.\n\n## Step 0: Load User Context (Me)\n\nFetch 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.\n\n## Step 1: Gather Targeting Criteria\n\nIf criteria are already provided, proceed. Otherwise ask:\n\n> \"What kind of accounts or contacts are you looking for? For example: company size, industry, job titles, signals like recent product activity or community engagement, geographic region, or specific intent signals like recent funding or job postings.\"\n\nUse the Common Room object catalog to see available filters for each object type. The key distinction:\n- **ProspectorOrganization** — firmographic and technographic filters only (industry, size, geography, funding, tech stack)\n- **Organization** — all firmographic filters plus signal-based, score-based, segment-based, and CRM filters\n\n**Lookalike search:** If the user asks to \"find companies like [X]\", first look up the reference company in Common Room (or via web search if not in CR). Extract its key attributes — industry, employee range, tech stack, funding stage, geography — and propose those as filter criteria. Present the derived criteria to the user for confirmation before running the search, since lookalike targeting works best when the user can refine which attributes matter most.\n\n## Step 2: Support Iterative Refinement\n\nProspecting is conversational. Support multi-turn refinement naturally:\n\n1. Run initial query with provided criteria\n2. If results are large (50+), summarize and offer: \"I found [N] results. Want to narrow by [suggested filter]?\"\n3. If results are too few (< 5), suggest: \"Only [N] results with those filters — I can broaden by relaxing [specific criterion].\"\n4. Apply each refinement as a follow-up query, not a new search from scratch\n\nExample flow:\n- Rep: \"Find cybersecurity companies in California.\" → 500 results\n- Rep: \"Only show ones over 300 employees using AWS.\" → 47 results\n- Rep: \"Focus on the ones with recent hiring activity.\" → 12 results ✓\n\n## Step 3: Run the Query and Present Results\n\nExecute the Prospector query with confirmed criteria. Sort by signal strength or fit score where available (not alphabetically).\n\n**For `ProspectorOrganization` (net-new) results:**\n\n| Company | Domain | Industry | Size | Capital Raised | Revenue | Location |\n|---------|--------|----------|------|---------------|---------|----------|\n\n**For `Organization` (in CR) results:**\n\n| Company | Industry | Size | Top Signal | Signal Date | Score | CRM Stage |\n|---------|----------|------|-----------|-------------|-------|-----------|\n\nFlag any results where data is thin or the most recent signal is older than 90 days.\n\n## Step 3.5: Enrich Net-New Results with Web Search\n\nFor `ProspectorOrganization` results (net-new companies not in CR), run a quick web search on the top 3–5 companies to add context beyond firmographics. CR has no behavioral signals for these companies, so web search fills the gap — look for recent funding, product launches, leadership changes, or news coverage. Include findings as brief annotations next to each company in the results.\n\n## Step 4: Offer Next Steps\n\n- \"Want me to draft outreach for the top 3–5 prospects?\"\n- \"Should I run a full account brief on any of these?\"\n- \"Want to refine the criteria or add another filter?\"\n- \"I can format this as a CSV if you'd like to export it.\"\n- \"For any net-new companies here, I can add them to Common Room for enrichment.\" *(future capability)*\n\n## Quality Standards\n\n- Always confirm which object type (ProspectorOrg vs Organization) before running the query\n- Default to \"My Segments\" when querying Organization records, unless user specifies otherwise\n- Support iterative refinement — treat each follow-up as a filter adjustment, not a fresh start\n- Never mix result fields from ProspectorOrganization and Organization in the same list\n- Fewer high-quality results beat a long unqualified list\n- **Only show data the query returned** — leave blank or \"—\" for missing fields, don't invent values\n\n## Reference Files\n\n- **`references/prospect-guide.md`** — filter types, signal-based sorting, object type distinctions, and list-building strategies\n- **`references/me-context.md`** — current-user and My Segments scoping\n"
AFTER
"---\nname: prospect\ndescription: \"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.\"\n---\n\n# Prospecting\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 Source\n\nUse 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.\n\n## Critical Distinction: Two Object Types\n\nSettle which one is in play before running a query:\n\n- **`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.\n- **`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.\n\nWhen a request could mean either (\"Show companies hiring AI engineers this month\"), ask:\n> \"Are you looking for net-new companies not yet in Common Room, or filtering accounts already in your workspace?\"\n\n## Step 0: Load User Context (Me)\n\nFetch 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.\n\n## Step 1: Gather Targeting Criteria\n\nIf 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.\n\nCheck commonroom_get_catalog for the filters each object type has.\n\n**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.\n\n## Step 2: Refine\n\nWith 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.\n\n## Step 3: Run the Query and Present Results\n\nSort 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.\n\n**For `ProspectorCompany` (net-new) results:**\n\n| Company | Domain | Industry | Size | Capital Raised | Revenue | Location |\n|---------|--------|----------|------|---------------|---------|----------|\n\n**For `Organization` (in CR) results:**\n\n| Company | Industry | Size | Top Signal | Signal Date | Score | CRM Stage |\n|---------|----------|------|-----------|-------------|-------|-----------|\n\nFlag any results where data is thin or the most recent signal is older than 90 days.\n\n## Step 3.5: Fill In Net-New Results\n\nFor `ProspectorCompany` results, request `primaryWebsite`, `employees`, `revenueRange`, `subIndustry`, `technologies`, `raised` and `location` in the query itself (defaults are only `id` and `name`), so no second call is needed.\n\nThen run a quick web search on the top 3–5 for recent news — funding, product launches, leadership changes — which Prospector doesn't cover. Include findings as brief annotations next to each company.\n\n## Step 4: Offer Next Steps\n\nOffer to save the results to Common Room and a segment (Step 5), draft outreach for the top 3–5, run a full account brief on any of them, refine the criteria, or format the list as CSV.\n\n## Step 5: Save the List (When the Seller Asks)\n\nNothing is saved or segmented without the seller's approval. Show what will be written: the records, the fields and the segment.\n\n1. **Dedupe.** Check each net-new company by domain with commonroom_list_objects. Mark each result as new or already in Common Room; for existing ones, show the owner and segments.\n2. **Check fit.** For each new result, say whether it meets the seller's criteria and the ICP from the company context, naming the fields that decided it. Recommend save or skip.\n3. **Save.** Create the approved companies and contacts with commonroom_create_object, passing prospectorCompanyId or prospectorContactId so name, domain, title and firmographics fill in.\n4. **Segment.** Ask whether to use an existing segment or create one.\n   - If the criteria map to Common Room filters, offer a segment built from those filters with commonroom_create_segment, so it stays current as companies start or stop matching.\n   - Otherwise create a segment with no filter and add the saved records with commonroom_update_object, up to 100 per call.\n   - For a team segment, ask which teams it's for and which owner field matches records to reps, and whether to pin it to each assignee's Home and to their \"My segments\" (the tool needs both answers). Set personaIds, assignment, addToHome and addToMySegments.\n5. **Report.** Saved, already existed, added to segment, skipped, failed.\n\n## List Mode: Qualify a List the Seller Brings\n\nWhen the seller pastes or attaches emails, LinkedIn URLs or domains — event attendees, webinar registrants, inbound domains — instead of criteria:\n\n1. **Read the list.** Find one identifier per row: email, LinkedIn URL or domain. Report rows without one; never guess an email or domain from a name.\n2. **Split known from new.** Check each row with commonroom_list_objects (contacts by email, organizations by domain). Known records keep their scores, owner, segments and signals.\n3. **Look up the new ones in Prospector.** Domains: `ProspectorCompany` with `groupWebsite` `eq` the domain (exact match; `like` returns unrelated companies), requesting `description`, `employees`, `revenueRange`, `subIndustry`, `technologies` and `location`, plus `primaryWebsite`, with up to 25 domains per query as an `or` group of `eq` clauses; match results back to rows by `primaryWebsite`. People: `ProspectorContact` by `fullName` and `companyDomain` when the row has both; Prospector can't be searched by email or LinkedIn URL alone, so label those rows \"not looked up\". Keep not-found rows, labeled.\n4. **Score fit** against the ICP from the company context or the seller's criteria: Strong, Possible, Poor or Unknown, naming the one or two fields that decided it. Never score from a company name alone.\n5. **Present** Strong first, with counts:\n   | Name / Company | Identifier | In CR? | Fit | Why | Proposed action |\n6. **Save** the approved rows with Step 5, creating each from its own email, LinkedIn URL or domain or its Prospector ID when step 3 found one, and offer to enroll the Strong-fit contacts or add them to a call list (contact-actions).\n\nLarge lists: work in batches of 25 and report progress.\n\n## Reference Files\n\n- **`references/prospect-guide.md`** — filter types, signal-based sorting, object type distinctions, and list-building strategies\n"
Full snapshot data
{
  "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.",
  "included_files": [
    {
      "relative_path": "LICENSE",
      "size_in_bytes": 11358
    },
    {
      "relative_path": "NOTICE",
      "size_in_bytes": 173
    },
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 430
    },
    {
      "relative_path": "references/prospect-guide.md",
      "size_in_bytes": 1940
    }
  ],
  "name": "prospect",
  "skill_md_contents": "---\nname: prospect\ndescription: \"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.\"\n---\n\n# Prospecting\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 Source\n\nUse 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.\n\n## Critical Distinction: Two Object Types\n\nSettle which one is in play before running a query:\n\n- **`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.\n- **`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.\n\nWhen a request could mean either (\"Show companies hiring AI engineers this month\"), ask:\n> \"Are you looking for net-new companies not yet in Common Room, or filtering accounts already in your workspace?\"\n\n## Step 0: Load User Context (Me)\n\nFetch 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.\n\n## Step 1: Gather Targeting Criteria\n\nIf 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.\n\nCheck commonroom_get_catalog for the filters each object type has.\n\n**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.\n\n## Step 2: Refine\n\nWith 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.\n\n## Step 3: Run the Query and Present Results\n\nSort 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.\n\n**For `ProspectorCompany` (net-new) results:**\n\n| Company | Domain | Industry | Size | Capital Raised | Revenue | Location |\n|---------|--------|----------|------|---------------|---------|----------|\n\n**For `Organization` (in CR) results:**\n\n| Company | Industry | Size | Top Signal | Signal Date | Score | CRM Stage |\n|---------|----------|------|-----------|-------------|-------|-----------|\n\nFlag any results where data is thin or the most recent signal is older than 90 days.\n\n## Step 3.5: Fill In Net-New Results\n\nFor `ProspectorCompany` results, request `primaryWebsite`, `employees`, `revenueRange`, `subIndustry`, `technologies`, `raised` and `location` in the query itself (defaults are only `id` and `name`), so no second call is needed.\n\nThen run a quick web search on the top 3–5 for recent news — funding, product launches, leadership changes — which Prospector doesn't cover. Include findings as brief annotations next to each company.\n\n## Step 4: Offer Next Steps\n\nOffer to save the results to Common Room and a segment (Step 5), draft outreach for the top 3–5, run a full account brief on any of them, refine the criteria, or format the list as CSV.\n\n## Step 5: Save the List (When the Seller Asks)\n\nNothing is saved or segmented without the seller's approval. Show what will be written: the records, the fields and the segment.\n\n1. **Dedupe.** Check each net-new company by domain with commonroom_list_objects. Mark each result as new or already in Common Room; for existing ones, show the owner and segments.\n2. **Check fit.** For each new result, say whether it meets the seller's criteria and the ICP from the company context, naming the fields that decided it. Recommend save or skip.\n3. **Save.** Create the approved companies and contacts with commonroom_create_object, passing prospectorCompanyId or prospectorContactId so name, domain, title and firmographics fill in.\n4. **Segment.** Ask whether to use an existing segment or create one.\n   - If the criteria map to Common Room filters, offer a segment built from those filters with commonroom_create_segment, so it stays current as companies start or stop matching.\n   - Otherwise create a segment with no filter and add the saved records with commonroom_update_object, up to 100 per call.\n   - For a team segment, ask which teams it's for and which owner field matches records to reps, and whether to pin it to each assignee's Home and to their \"My segments\" (the tool needs both answers). Set personaIds, assignment, addToHome and addToMySegments.\n5. **Report.** Saved, already existed, added to segment, skipped, failed.\n\n## List Mode: Qualify a List the Seller Brings\n\nWhen the seller pastes or attaches emails, LinkedIn URLs or domains — event attendees, webinar registrants, inbound domains — instead of criteria:\n\n1. **Read the list.** Find one identifier per row: email, LinkedIn URL or domain. Report rows without one; never guess an email or domain from a name.\n2. **Split known from new.** Check each row with commonroom_list_objects (contacts by email, organizations by domain). Known records keep their scores, owner, segments and signals.\n3. **Look up the new ones in Prospector.** Domains: `ProspectorCompany` with `groupWebsite` `eq` the domain (exact match; `like` returns unrelated companies), requesting `description`, `employees`, `revenueRange`, `subIndustry`, `technologies` and `location`, plus `primaryWebsite`, with up to 25 domains per query as an `or` group of `eq` clauses; match results back to rows by `primaryWebsite`. People: `ProspectorContact` by `fullName` and `companyDomain` when the row has both; Prospector can't be searched by email or LinkedIn URL alone, so label those rows \"not looked up\". Keep not-found rows, labeled.\n4. **Score fit** against the ICP from the company context or the seller's criteria: Strong, Possible, Poor or Unknown, naming the one or two fields that decided it. Never score from a company name alone.\n5. **Present** Strong first, with counts:\n   | Name / Company | Identifier | In CR? | Fit | Why | Proposed action |\n6. **Save** the approved rows with Step 5, creating each from its own email, LinkedIn URL or domain or its Prospector ID when step 3 found one, and offer to enroll the Strong-fit contacts or add them to a call list (contact-actions).\n\nLarge lists: work in batches of 25 and report progress.\n\n## Reference Files\n\n- **`references/prospect-guide.md`** — filter types, signal-based sorting, object type distinctions, and list-building strategies\n"
}

SHA-256 of public snapshot: 32f3895f18fb3304dab743c0c793133a4ab1947b9956579239e6e8c075eb311e