Surface undocumented filter params across four skills

skills/build-list/SKILL.md

@@ -20,15 +20,22 @@ The user may also specify:
 - How many results they want (default: 25)
 - Whether they want contacts, companies, or both
 - Specific fields to include in the output
+- Data quality requirements: "with verified email", "with direct phone", "updated in the last 6 months"
 
 ## Workflow
 
 1. **Determine list type**: Is the user asking for contacts, companies, or both? Default to contacts if they mention titles/roles, companies if they mention firmographics only.
 
 2. **Parse criteria** from natural language into structured filters:
    - Job titles, management levels, departments, job functions → contact filters
-   - Industry, employee count, revenue, geography, tech stack, company type → company filters
-   - Growth rate, funding, rankings → company filters
+   - "With verified email" or "has email" → `hasEmail: true` contact filter
+   - "With direct phone" or "has phone" → `hasPhone: true` contact filter
+   - "Updated in the last X months/days" → `lastUpdatedDateAfter: <ISO date>` contact filter (compute the date from today)
+   - Industry, employee count, revenue, tech stack, company type → company filters
+   - "In the [city] area" or metro region → `metroArea` company filter
+   - "Series B+", "recently funded", "post-Series A" → `fundingStage` company filter
+   - Growth rate, rankings → company filters
+   - Geography: `state` for state-level, `country` for country-level, `metroArea` for metro precision
 
 3. **Resolve all filter values** using `lookup` before searching. This is critical — do NOT guess values. For every filter you plan to use, call `lookup` with the corresponding field name to get the valid values and use the returned `id` values in your search parameters.
 
@@ -72,9 +79,9 @@ Show the user exactly what filters were used so they can verify:
 
 ### List Summary
 - **Total results found**: X (showing top Y)
-- **Filters applied**: [summary]
+- **Filters applied**: [summary — include any `hasEmail`, `hasPhone`, `lastUpdatedDateAfter`, `metroArea`, or `fundingStage` filters so the user can verify]
 - **Average accuracy score**: X (contacts only)
-- **Data quality**: Flag any concerns (low accuracy, stale records)
+- **Data quality**: Flag any concerns (low accuracy scores, records not updated in 12+ months)
 
 ### Refinement Options
 If the list is too broad or too narrow, suggest specific filter adjustments:

skills/enrich-company/SKILL.md

@@ -29,6 +29,7 @@ The user will provide via `$ARGUMENTS` one of:
 
 4. **If no match**, try a fallback:
    - Use `search_companies` with `companyName` for fuzzy matching — use lookup `id` values for any filters
+   - If the user provided a city or metro area, add `metroArea` to narrow results to the right region
    - Suggest alternatives from the search results
 
 ## Output Format
@@ -60,7 +61,9 @@ The user will provide via `$ARGUMENTS` one of:
 **Growth Signals**
 - 1-Year Employee Growth: X%
 - 2-Year Employee Growth: X%
-- Recent Funding: [if available]
+- Funding Stage: [if available — e.g., Series B, IPO, Private Equity-backed]
+- Recent Funding: [amount + date if available]
+- Metro Area: [if available — more granular than HQ city]
 
 **ZoomInfo Coverage**
 - Contacts in Database: [count]

skills/enrich-contact/SKILL.md

@@ -32,6 +32,7 @@ The user will provide via `$ARGUMENTS` one of:
 
 4. **If no match**, try a fallback:
    - If name + company failed, try `search_contacts` with `jobTitle` or `companyName` variations — use lookup `id` values for any filters
+   - If searching by name returns too many results, add `hasEmail: true` to narrow to contacts with verified email on file
    - Suggest alternative spellings or company names
 
 ## Output Format
@@ -51,7 +52,8 @@ The user will provide via `$ARGUMENTS` one of:
 | Company Industry | |
 | Company Size | |
 | LinkedIn | |
+| Supplemental Email | (secondary email if available) |
 | Last Updated | |
 | ZoomInfo Person ID | |
 
-If any fields are unavailable, omit them rather than showing blanks. Note the accuracy score prominently — anything below 80 deserves a flag.
+If any fields are unavailable, omit them rather than showing blanks. Note the accuracy score prominently — anything below 80 deserves a flag. If `lastUpdated` is more than 12 months ago, note the record may be stale and recommend re-verifying before outreach.

skills/find-similar/SKILL.md

@@ -26,6 +26,7 @@ Determine whether the user is looking for similar **companies** or **contacts**
 2. **Find similar companies** using `find_similar_companies`. This returns up to 100 results ranked by similarity score.
    - If you have a ZoomInfo company ID, pass `companyId`.
    - If you only have a company name, pass `companyName` — the API can resolve it directly.
+   - If the user specified a geography, funding stage, or employee range to narrow results, note that `find_similar_companies` does not accept firmographic filters directly — apply them as post-filters on the returned results, or follow up with `search_companies` using `techAttributeTagList` or firmographic filters to cross-reference.
 
 ### Company Output Format