Ethical people-finding and identity verification via parallel research agents across people-search sites, social media, public records, and reverse phone/email/image/username lookups, with confidence-scored results requiring 3+ matching identifiers
When you're trying to find someone — a lost contact, an old colleague, someone who called from an unknown number — a generic AI will either refuse outright or give you a list of websites to manually search yourself. It has no systematic method for cross-referencing sources, no confidence scoring to tell you when a match is solid vs. shaky, and no understanding of which search strategy fits which starting point (a name, a phone number, an email address, an image). You end up doing the work the tool should be doing.
PrivateInvestigator deploys 15 parallel research agents — 5 types times 3 each — against public data sources simultaneously, not sequentially. Each agent type covers different ground: people search aggregators (TruePeopleSearch, FastPeopleSearch, Spokeo), social media x-ray searches via Google dorking, public records (voter registration, property records, PACER court portals, professional licenses), and reverse lookup services for phones (CallerID, NumLookup), emails (Epieos, Holehe, Hunter.io), images (PimEyes, TinEye), and usernames (Sherlock, WhatsMyName). Results get confidence-scored at four levels — HIGH requires 3+ matching identifiers across independent sources. The five workflows (FindPerson, SocialMediaSearch, PublicRecordsSearch, ReverseLookup, VerifyIdentity) handle distinct starting points. Everything stays in the public-data green zone — no pretexting, no auth bypass, no PI-licensed databases.
What you say to your DA, and what the PrivateInvestigator skill actually does.
The thinking, frameworks, and architecture that distinguish this skill from a generic version of the same task.
Finds people and verifies identities using public data only. It covers people-search aggregators, social media, public records, and reverse lookups in parallel, then scores results by confidence (HIGH/MEDIUM/LOW/POSSIBLE) and trusts a match only when 3+ independent identifiers align.
Finding a real person from a name, a phone number, or an email is scattered across dozens of sources — people-search sites, county records, court portals, social platforms, reverse-lookup services — and no single one gives you the answer. Common names make it worse: search "John Smith" and you get thousands of people, most of them the wrong one. Run the searches one at a time and you either give up before you've covered enough sources or you act on a single weak match and contact the wrong person. This skill runs the sources in parallel and refuses to call a match real until several independent identifiers line up.
Public data only. No hacking, pretexting, or authentication bypass — every technique here is legal and ethical. The work runs as a parallel investigation across the source categories below; findings get cross-checked and confidence-scored before anything is reported. Choose the fan-out breadth the case needs — a common name across many states wants wide parallel coverage, a rare name in one city wants far less.
Done = broad, independent coverage. Every source category below is worked, and no key identifier (address, employer, DOB, family, social handle) rests on a single source. Run the categories in parallel — dispatch research agents concurrently in one message — and scale the fan-out to the case: a common name across many states justifies many parallel agents and spelling/location variants; a rare name in one city needs only a few. Independence is the point, not headcount: aggregators that resell the same database count as one source, so weight toward genuinely distinct origins (social the subject created, government records, unrelated aggregators).
| Service | Type | Best For |
|---|---|---|
| TruePeopleSearch | Free | Best free option, fresh data |
| FastPeopleSearch | Free | Basic lookups, no signup |
| Spokeo | Freemium | Social media aggregation (120+ networks) |
| BeenVerified | Paid | Comprehensive background data |
site:linkedin.com "John Smith" "Software Engineer"
site:facebook.com "lives in" "Austin" "marketing"
filetype:pdf resume "Jane Doe" "San Francisco"
Anchor on whatever foundation identifiers the request gives — full name (and variations/maiden names), approximate age or DOB, last known location, context (school, workplace, relationship) — then pull from every source category until identifiers corroborate. Each discovered fact (phone, email, username, address, relative) is itself a new lead to run back through the sources, and every candidate gets a timeline-consistency and cross-source check before it earns a confidence score. The order is yours; the finish line is a match that survives the 3+-independent-identifier bar below.
| Level | Criteria | Action |
|---|---|---|
| HIGH | 3+ unique identifiers match across independent sources | Safe to contact |
| MEDIUM | 2 identifiers match, timeline consistent | Verify before contact |
| LOW | Single source or name-only match | Needs more investigation |
| POSSIBLE | Partial match, requires verification | Do not act without more data |
✅ Search public records (property, court, voter, business) ✅ Access publicly posted social media content ✅ Use people search aggregator sites ✅ Perform reverse lookups on public data ✅ Google dorking with public search operators
❌ Access data behind login walls without authorization ❌ Bypass authentication or security measures ❌ Use pretexting or impersonation ❌ Access private databases (credit, financial, medical) ❌ Stalk, harass, or intimidate subjects ❌ Access PI-only databases without license
Example 1: Finding an Old College Friend
User: "Help me find my college roommate from 2005, John Smith from Austin"
→ Routes to FindPerson.md
→ Fans out parallel research across the source categories
→ Cross-references people search + LinkedIn alumni + property records
→ Verifies identity through timeline analysis
→ Reports findings with HIGH confidence
Example 2: Reverse Phone Lookup
User: "Who called from 512-555-1234?"
→ Routes to ReverseLookup.md
→ Runs phone through CallerID, NumLookup
→ Cross-references with people search aggregators
→ Reports owner name, location, carrier
Example 3: Social Media Investigation
User: "Find Jane Doe's social media, she's a marketing professional in Denver"
→ Routes to SocialMediaSearch.md
→ LinkedIn Boolean search + Google x-ray
→ Username enumeration if handle discovered
→ Reports all accounts with MEDIUM/HIGH confidence
Related Documentation:
Workflows/ directoryEach workflow is one job the skill runs. The trigger phrases route your request to the right one — this is the skill's routing table.
Workflows/FindPerson.md find person, locate, search for [person], reconnect, lost contact — full parallel-agent investigation
Workflows/SocialMediaSearch.md social media search — cross-platform social media investigation
Workflows/PublicRecordsSearch.md public records — government and official records search
Workflows/ReverseLookup.md reverse lookup — phone, email, image, username searches
Workflows/VerifyIdentity.md verify identity — confirm correct person match
Say any of these to your DA and LifeOS activates the PrivateInvestigator skill automatically:
Or invoke explicitly:
Skill("PrivateInvestigator")Install LifeOS on your machine — your DA gets the PrivateInvestigator skill plus 46 others, all hooked into one Life OS.