find-recruiting-firm

Drive the ServiceGraph API (https://api.servicegraph.co) to find, shortlist, and enrich US recruiting and staffing firms via the pro_services dataset.

This skill is for procuring an external recruiting/staffing firm to do hiring on the user's behalf. It is NOT for:

• recruiting an in-house employee (the user wants to hire someone for their own team — that's job-posting, not procurement),
• candidate-side asks (an individual job-seeker looking for someone to represent them).

Both share keyword overlap with the positive case ("recruiter", "hire"), so the boundary matters.

Always pin `industry:hr_recruiting_staffing`. Sub-types (executive search, RPO, contingent staffing, temp, vertical specializations) are NOT separate tags — sub-type specialization is a keyword substring search on firm text.

Any HTTP client works (curl, fetch, requests). Examples below use curl.

When NOT to use this skill

• "I want to hire a [role] for my team — where should I post the job?" → recruiting-an-employee.
• "Find me a recruiter to represent me in my job search" → candidate side.
• "Hire an in-house recruiter / Head of Talent" → recruiting an employee.
• "Help me write a job description" → DIY/do-the-work.
• ATS or HR-software comparisons (Greenhouse vs Lever, Workday).
• Career coaching for individual job-seekers.
• Non-US firms / individual freelance recruiters.

MCP server (preferred for authed calls)

If your harness has the ServiceGraph MCP server loaded (tools containing servicegraph), prefer those — OAuth 2.1 + PKCE keeps the token in the harness sandbox. Otherwise use the REST flow below.

API surface (dataset id: pro_services)

Every endpoint requires the bearer (Authorization: Bearer vk_…). No anonymous tier.

Cost model. Discovery / validation / search / brief reads are free. Detail (url, phone, email, social, address, full platforms map) costs 10 credits per firm and lasts 30 days.

Auth

vk_* API keys minted in the dashboard. Keep the token out of the LLM context — never read .env* into your context; dispatch via shell.

1. Try the call first through a shell wrapper that sources .env.local:

   ( set -a; [ -f .env.local ] && . ./.env.local; set +a;
     curl -sS -H "Authorization: Bearer $SERVICEGRAPH_API_KEY" \
          'https://api.servicegraph.co/v1/datasets/pro_services/fields' )

1. On `401` prompt the user:

"Open https://servicegraph.co/profile/api-keys, create a key, and add SERVICEGRAPH_API_KEY=vk_… to .env.local here (or export it). Tell me when done. Please don't paste the key into chat."

1. Retry after the user signals ready.

Filter DSL

GitHub-search-style.

filter   := orExpr
orExpr   := andExpr ("OR" andExpr)*
andExpr  := notExpr (("AND")? notExpr)*    # whitespace = implicit AND
notExpr  := ("NOT" | "-") notExpr | atom
atom     := "(" filter ")" | predicate
predicate:= IDENT op valueOrList | bareword
op       := ":" | "=" | ">=" | "<=" | ">" | "<"
valueOrList := value ("," value)*
value    := IDENT | NUMBER | tagAtEvidence
tagAtEvidence := IDENT "@" ("low"|"medium"|"high")
bareword := IDENT | NUMBER          # → keyword:<bareword>

Four rules that bite: AND binds tighter than OR (use parens); comma list = OR within one predicate; negation is -x or NOT x; bareword = keyword search (quote multi-word phrases).

Recruiting-flavored examples (validate yours with /check):

industry:hr_recruiting_staffing "executive search"
industry:hr_recruiting_staffing "retained search" state:NY tech
industry:hr_recruiting_staffing rpo state:CA
industry:hr_recruiting_staffing contingent staffing
industry:hr_recruiting_staffing healthcare state:TX,FL
industry:hr_recruiting_staffing sales saas
industry:hr_recruiting_staffing rating>=4 has:clutch

Sub-type → keyword mapping:

Identifying firms — apex

Firms are identified by their apex domain (korn-ferry.com, not www.korn-ferry.com/about).

Recipes

A. Executive search for a CFO

GET /v1/datasets/pro_services/search?filter=industry:hr_recruiting_staffing+executive+search&limit=10
# Present, get pick of 3. "Unlocking 3 = 30 credits, 30-day TTL."
POST /v1/datasets/pro_services/unlocks
  { "apexes": ["firm-a.com", "firm-b.com", "firm-c.com"] }

B. Retained boutique in a state, vertical

GET /v1/datasets/pro_services/search?filter=industry:hr_recruiting_staffing+retained+state:NY+tech+-company_size_signal:large_50plus&limit=10

C. RPO for a hiring surge

GET /v1/datasets/pro_services/search?filter=industry:hr_recruiting_staffing+rpo+(tech OR engineering)&limit=10

D. Indirect intent — "scaling fast, need help hiring"

GET /v1/datasets/pro_services/search?filter=industry:hr_recruiting_staffing+(rpo OR contingent)&limit=10

Or use the translator:

POST /v1/datasets/pro_services/translate-intent
  { "intent": "RPO or volume recruiting partner for a 50-engineer hiring push" }

E. Vertical: healthcare staffing

GET /v1/datasets/pro_services/search?filter=industry:hr_recruiting_staffing+healthcare+state:OH,IL,MI,IN,WI,MN&limit=10

F. Quality threshold + tech-sector

GET /v1/datasets/pro_services/search?filter=industry:hr_recruiting_staffing+executive+search+tech+rating>=4&limit=10

G. BYO apex list — enrich domains

User pastes 8–20 staffing/recruiting firm domains:

1. GET /v1/datasets/pro_services/:apex per domain — free brief

(404 = not in catalog, no charge).

1. User picks N to fully enrich. POST /unlocks = 10×N credits,

atomic, detail returned.

1. Re-runs within 30-day TTL are free.

Gotchas

• Always pin `industry:hr_recruiting_staffing`. Without it, "recruiter" / "executive search" keywords leak into other industries.
• Distinguish "find me a recruiting firm" (procurement, fires) from "find me a recruiter / hire a recruiter for our team" (recruiting-an-employee, refuses). When ambiguous, lean on context: explicit firm/agency/RPO language or volume framing → procurement; "for our team" / "to post the job" / "I want to hire" → in-house hire.
• Candidate-side asks ("represent me as a candidate", "find me a job") are out of scope.
• Career coaching for individuals is a different need (and shares the executive-coaching keyword with management consulting). Refuse — this skill is firm-procurement.
• Sub-types are keyword-only. Multi-word sub-types split into ANDed barewords unless quoted ("executive search" → one phrase).
• Briefs DO include `apex`, `name`, location, ratings. They DON'T include url, phone_primary, email_primary, legal_name, address_full, full platforms — those require an unlock.
• `not_found` / `not_in_dataset` 404 = not in `pro_services`. Skip; not charged.
• Unlock is atomic. N apexes either all charge (up to 10×N credits) or none on 402.
• Within-TTL re-views are free (was_cached:true).

Errors

JSON envelope: {"error": {"code": "...", "message": "..."}}.

End-to-end example

User: "Three retained executive search firms in NY focused on tech CFOs, ideally with 4-star ratings and a Clutch profile."

GET /v1/datasets/pro_services/fields?include_values=1
GET /v1/datasets/pro_services/check?filter=industry:hr_recruiting_staffing+retained+executive+state:NY+tech+rating>=4+has:clutch
GET /v1/datasets/pro_services/search?filter=...&limit=10
# Present briefs. "Unlocking 3 = 30 credits, 30-day TTL."
POST /v1/datasets/pro_services/unlocks
  { "apexes": ["firm-a.com", "firm-b.com", "firm-c.com"] }
GET /v1/me/credits