Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Research LinkedIn professional profiles and public business-contact data, including email/phone lookup, people search, and YouTube channel business-email discovery.
.claude/skills/sickn33-people-data/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 21% | 0% |
Perform authorized professional-profile and public business-contact research through the Agent Body MCP server at /mcp/people-data. It covers LinkedIn profile retrieval, email and phone lookup, filtered people search, and YouTube channel business-email discovery.
Read references/tool-reference.md for exact tool names and input fields.
linkedin_person_profile with linkedin_url retrieves one professional profile.linkedin_email_lookup with profileUrl looks up one profile email address.linkedin_phone_lookup with profileUrl looks up one profile phone number.linkedin_people_search accepts optional filters and returns a nextPageToken for continuation.youtube_email_finder takes channels (1-1000 channel URLs) and optional scrape_fresh_emails to find public business emails.Use canonical profile or channel URLs when available. For name-only searches, add explicit role, company, location, or keyword filters. companyFilter must be current, past, or all.
Confirm that returned identities match the request, deduplicate search results by canonical profile identity, and never construct or guess an email address or phone number. Preserve per-channel found/not-found state from YouTube results.
Call linkedin_person_profile with:
json{ "linkedin_url": "https://www.linkedin.com/in/example-person" }
Call youtube_email_finder with:
json{ "channels": ["https://www.youtube.com/@example"], "scrape_fresh_emails": false }
nextPageToken unchanged when continuing a linkedin_people_search./mcp/people-data MCP server; results depend on the live tool schema.youtube_email_finder only finds public business emails and may report channels where no email is found.Solution: Profile lookup uses linkedin_url; email and phone lookup use profileUrl.
Solution: Report the missing result and stop; never invent contact data.
Solution: Pass the returned nextPageToken unchanged to continue instead of replaying the initial query.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | pass→fail | 10,509 | 2,633 | -75% | 1 | 1 | 0% | 1,668 | 1,371 | -18% | 0 | 0 | — |
case-01 | fail→fail | 7,649 | 17,802 | +133% | 1 | 1 | 0% | 1,109 | 1,530 | +38% | 0 | 0 | — |
case-02 | fail→fail | 6,940 | 7,612 | +10% | 1 | 1 | 0% | 1,141 | 1,433 | +26% | 0 | 0 | — |
case-03 | fail→fail | 15,493 | 8,024 | -48% | 1 | 1 | 0% | 1,575 | 1,584 | +1% | 0 | 0 | — |
case-04 | fail→pass | 10,719 | 8,459 | -21% | 1 | 1 | 0% | 1,833 | 2,334 | +27% | 0 | 0 | — |
case-05 | fail→pass | 11,870 | 6,414 | -46% | 1 | 1 | 0% | 2,185 | 2,126 | -3% | 0 | 0 | — |
case-06 | pass→pass | 3,497 | 3,763 | +8% | 1 | 1 | 0% | 561 | 1,515 | +170% | 0 | 0 | — |
case-07 | fail→fail | 6,426 | 2,528 | -61% | 1 | 1 | 0% | 1,112 | 1,502 | +35% | 0 | 0 | — |
case-08 | fail→pass | 6,372 | 1,670 | -74% | 1 | 1 | 0% | 1,157 | 1,252 | +8% | 0 | 0 | — |
case-09 | fail→pass | 9,818 | 2,470 | -75% | 1 | 1 | 0% | 1,661 | 1,467 | -12% | 0 | 0 | — |
case-10 | fail→pass | 6,647 | 2,605 | -61% | 1 | 1 | 0% | 1,161 | 1,405 | +21% | 0 | 0 | — |
case-12 | fail→pass | 9,005 | 3,352 | -63% | 1 | 1 | 0% | 1,608 | 1,541 | -4% | 0 | 0 | — |
case-13 | fail→pass | 16,109 | 5,044 | -69% | 1 | 1 | 0% | 2,593 | 1,868 | -28% | 0 | 0 | — |
case-14 | fail→pass | 19,807 | 2,339 | -88% | 1 | 1 | 0% | 3,351 | 1,389 | -59% | 0 | 0 | — |
case-15 | pass→pass | 12,439 | 4,894 | -61% | 1 | 1 | 0% | 1,912 | 1,731 | -9% | 0 | 0 | — |
case-16 | pass→pass | 8,875 | 3,827 | -57% | 1 | 1 | 0% | 1,415 | 1,561 | +10% | 0 | 0 | — |
case-17 | pass→pass | 8,376 | 5,546 | -34% | 1 | 1 | 0% | 1,356 | 1,857 | +37% | 0 | 0 | — |
case-18 | fail→pass | 9,245 | 3,655 | -60% | 1 | 1 | 0% | 1,677 | 1,635 | -3% | 0 | 0 | — |
case-19 | fail→fail | 10,056 | 2,317 | -77% | 1 | 1 | 0% | 1,384 | 1,339 | -3% | 0 | 0 | — |
case-20 | fail→pass | 13,733 | 4,917 | -64% | 1 | 1 | 0% | 2,100 | 1,771 | -16% | 0 | 0 | — |
case-21 | fail→pass | 11,224 | 3,112 | -72% | 1 | 1 | 0% | 1,891 | 1,485 | -21% | 0 | 0 | — |
case-22 | fail→pass | 9,303 | 4,755 | -49% | 1 | 1 | 0% | 1,553 | 1,720 | +11% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 19 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +50 percentage points is the difference between those two pass rates over the 19 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.