Skip to content

nostrband/ServiceGraph / skills/find-software-developer

find-software-developer

Unverified

Use whenever the user wants to find, shortlist, vet, or enrich US software development firms — custom software, web development, mobile app development, backend/API development, DevOps/cloud, system integration, and hosting. Triggers on "find a software dev shop in Austin", "shortlist three custom-software firms with healthcare experience", "we need a mobile app developer for our iOS launch", or "pull contact info for these 10 dev shop domains", even when described indirectly (build a tool, ship a feature, technical partner). Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog filterable by industry, services, location, size, ratings. Defer to find-web-developer for strictly website/landing-page projects. Defer AI/ML, ML pipelines, model building, and data-engineering asks — those are a sibling industry, not software development. Skip in-house engineer hires, code-writing/debugging tasks, cloud-product comparisons, hardware/civil engineering, non-US firms, individual freelancers.

find-software-developer

Drive the ServiceGraph API (https://api.servicegraph.co) to find, shortlist, and enrich US software development firms via the pro_services dataset. The catalog has tens of thousands of US IT-services firms tagged across ~21 service sub-tags including web-development, mobile-app-development, api-integration (singular), devops-services, cloud-services, system-integration, application-modernization, staff-augmentation, and managed-services.

The catalog has no custom-software, devops, api-integrations (plural), or hosting tag — for those user-facing concepts, pin application-modernization + web-development (for custom software), devops-services, or api-integration (singular) as the closest tags and add the keyword.

Always pin industry:it_services. This skill exists to do that automatically — the user shouldn't have to think about catalog taxonomy.

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

Sibling skills — defer when scope is narrow

  • Strictly website / landing-page work (build or refresh a marketing site, simple WordPress) → find-web-developer. If unsure, this skill is the safer default — it covers web dev too.
  • AI/ML modeling specifically (recommendation engines, LLM apps, ML pipelines as the core deliverable) → find-ai-consultancy. Those firms live in a sibling industry (data_ai_consulting), not it_services.
  • Strictly marketing work (SEO, paid media, branding, content) → find-marketing-agency or find-seo-agency.

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.

EndpointCostUse it for
GET /v1/datasets/pro_services/fields[?include_values=1]freeConfirm it_services industry value and sub-tag names.
GET /v1/datasets/pro_services/check?filter=…freeValidate filter.
POST /v1/datasets/pro_services/translate-intentfree{intent} → DSL filter + sanity count.
GET /v1/datasets/pro_services/search?filter=…&limit=freeBrief firm cards + per-row unlock hint + total.
GET /v1/datasets/pro_services/:apexfreeOne row brief; detail only if unlocked.
POST /v1/datasets/pro_services/unlocks10 credits / firm{apexes:[...]} ≤100; atomic; 30-day TTL on detail.
GET /v1/me/creditsfreeBalance.

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' )
    
  2. 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."

  3. 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).

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

industry:it_services custom software state:TX
industry:it_services service_provided:mobile-app-development
industry:it_services service_provided:devops-services aws
industry:it_services service_provided:api-integration fintech
industry:it_services python aws state:CA
industry:it_services service_provided:system-integration@high rating>=4 has:clutch
industry:it_services service_provided:application-modernization legacy

Tech stack / vertical → keyword mapping (the catalog tags services, not languages or industries served):

User mentionsAdd as keyword
Python / Django / Flaskpython
Node.js / TypeScript / Reactnode, react
Go / Rust / Java / .NETgo, rust, java, .net
AWS / GCP / Azureaws, gcp, azure
Fintech / healthcare / govtech / SaaSfintech, healthcare, govtech, saas
SOC 2 / HIPAA / compliancesoc2, hipaa, compliance

Identifying firms — apex

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

Recipes

A. Custom-software shop in a state

GET /v1/datasets/pro_services/search?filter=industry:it_services+service_provided:application-modernization+custom+software+state:TX&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. Mobile app — vertical and platform

GET /v1/datasets/pro_services/search?filter=industry:it_services+service_provided:mobile-app-development+ios&limit=10

iOS / Android distinctions aren't separate tags — use barewords.

C. DevOps + cloud migration

GET /v1/datasets/pro_services/search?filter=industry:it_services+service_provided:devops-services+aws+migration&limit=10

If thin, drop migration first — it's a vertical keyword, not a service tag.

D. Indirect intent — "technical partner to build out tooling"

User: "We need a technical partner to build out our internal tooling, Northeast preferred."

GET /v1/datasets/pro_services/search?filter=industry:it_services+custom+software+state:NY,MA,CT,NJ,PA&limit=10

Or use the translator:

POST /v1/datasets/pro_services/translate-intent
  { "intent": "technical partner to build internal tooling, Northeast preferred" }

E. Vertical + cert (fintech + SOC 2)

GET /v1/datasets/pro_services/search?filter=industry:it_services+custom+software+fintech+soc2&limit=10

F. Quality threshold + third-party signals

GET /v1/datasets/pro_services/search?filter=industry:it_services+service_provided:application-modernization+custom+software+rating>=4+review_count_total>=50&limit=10

G. API/backend specialty + remote

User: "API/backend team to extend our SaaS — Bay Area or remote-friendly."

remote-friendly isn't structured. Use geography_served:national_US (national-scope firms typically serve remotely) plus keywords:

GET /v1/datasets/pro_services/search?filter=industry:it_services+service_provided:api-integration+(state:CA OR geography_served:national_US)+saas&limit=10

H. BYO apex list — enrich domains

User pastes 8–20 domains:

  1. GET /v1/datasets/pro_services/:apex per domain — free brief (404 = not in catalog, no charge).
  2. User picks N to fully enrich. POST /unlocks = 10×N credits, atomic, detail returned.
  3. Re-runs within 30-day TTL are free.

Gotchas

  • Always pin industry:it_services. Without it, web-development / mobile-app-development keywords leak into marketing or design firms.
  • Tag drift: there is no custom-software, devops, api-integrations (plural), or hosting tag. Map to application-modernization + web-development, devops-services, api-integration (singular) plus keywords.
  • industry:data_ai_consulting is a sibling industry, not a sub-tag. AI/ML-focused firms live there — defer to find-ai-consultancy.
  • Defer to find-web-developer for strictly website/landing-page projects. This skill covers web dev as a sub-service, but the dedicated skill ranks higher on narrow web-only asks.
  • Programming language and tech stack are NOT structured tags. python, react, aws, kubernetes, rust are keyword substring matches. Multi-word stacks split into ANDs unless quoted ("ruby on rails").
  • Client-vertical (fintech, healthcare, govtech) is NOT a structured tag. Keyword it.
  • Catalog is US-only B2B. Refuse offshore asks ("a software firm in Bangalore"), individual freelancers, in-house engineering hires, and DIY/code tasks ("debug this", "review this PR").
  • Cloud product comparisons aren't procurement. "Which is better, AWS or GCP?" is a knowledge question.
  • 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": "..."}}.

StatusCodeWhat to do
400filter_parse_errorposition included; fix and re-validate with /check.
400kind_in_filterStrip any kind: from filter.
400field_not_in_datasetDrop the disallowed field.
400invalid_apexRe-normalize.
401unauthorized / invalid_audienceRe-prompt for fresh vk_….
402insufficient_creditsneeded and balance; nothing charged.
404not_found / not_in_datasetSkip; not charged.
429rate_limitedHonor Retry-After.

End-to-end example

User: "Three custom software firms with healthcare-industry experience, SOC 2-ready, ideally with at least a 4-star rating."

GET /v1/datasets/pro_services/fields?include_values=1
GET /v1/datasets/pro_services/check?filter=industry:it_services+service_provided:application-modernization+custom+software+healthcare+soc2+rating>=4
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
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 318kUpdated Claude CodeCodexUnverifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 117kUpdated Claude CodeCodexUnverifiedInstall