people-company-search-fiber
People, company, investor, and job search with LinkedIn data enrichment
npx skills add gooseworks-ai/goose-skills --skill people-company-search-fiber --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Comprehensive search and enrichment for people, companies, investors, and jobs using Fiber endpoints and specialized lookups.
How it works
- Capabilities include: search profiles from text, search companies from text, find person by email, live fetch LinkedIn profile, validate a single email, kitchen sink person lookup, kitchen sink company lookup, investor search, fetch LinkedIn profile posts, live fetch LinkedIn company, people search, fetch LinkedIn post comments, company search, convert text into company search filters, convert text into profile search filters, job postings search, fetch LinkedIn post reactions.
- Each capability provides parameters and curl examples showing API path and body structure. The workflow relies on posting to $GOOSEWORKS_API_BASE with path /v1/proxy/orthogonal/run and the fiber API endpoints such as /v1/natural-language-search/profiles, /v1/natural-language-search/companies, /v1/kitchen-sink/person, /v1/kitchen-sink/company, /v1/investor-search, /v1/linkedin-live-fetch/profile, /v1/linkedin-live-fetch/profile-posts, /v1/linkedin-live-fetch/company/single, /v1/validate-email/single, and others.
- Examples show how to pass query, identifiers, or searchParams in the request body and how to paginate with pageSize or cursor.
- Authentication is via Bearer token from a credentials file; the setup mentions reading API key and base from ~/.gooseworks/credentials.json and suggests login with
npx gooseworks loginif missing.
When to use it
- Use when you need enriched LinkedIn data for people, companies, investors, or jobs, including live fetches and kitchen-sink lookups to maximize match accuracy.
- Use when performing free-form text searches for profiles or companies and when you require pagination or filtering by parameters like job_titles, locations, or investment stages.
What it can touch
- Endpoints under the Fiber API exposed via the orthogonal proxy, including:
- /v1/natural-language-search/profiles
- /v1/natural-language-search/companies
- /v1/kitchen-sink/person
- /v1/kitchen-sink/company
- /v1/investor-search
- /v1/linkedin-live-fetch/profile
- /v1/linkedin-live-fetch/profile-posts
- /v1/linkedin-live-fetch/company/single
- /v1/validate-email/single
- /v1/people-search
- /v1/linkedin-live-fetch/post-comments
- /v1/… (other listed capabilities)
Caveats
- Pricing is endpoint-specific per record, with notes on cost per call and possible default minimums; exact costs are provided in the Cost Reference and are endpoint-wide.
- Requires credentials from ~/.gooseworks/credentials.json; if missing, run
npx gooseworks login. Bearer authentication must be used in headers. - Some capabilities mention that “liveFetch” and detailed flags may incur additional costs or rely on cached data; the boolean flag is deprecated in favor of an object configuration.
- The text includes several curl examples; ensure proper JSON structure and correct path usage when integrating.
# Fiber AI - People & Company Intelligence ## Cost Reference | Endpoint | Cost | Notes | |----------|------|-------| | `/v1/natural-language-search/profiles` | **$0.02/record** (pageSize × $0.02) | Default $0.50 if no pageSize | | `/v1/people-search` | **$0.02/record** (pageSize × $0.02) | Default $0.50 if no pageSize | | `/v1/natural-language-search/companies` | Varies | | | `/v1/kitchen-sink/person` | Varies | Single lookup | | `/v1/validate-email/single` | ~$0.02 | | **Cheaper alternative for people search:** Apollo `mixed_people/search` costs **$0.01 flat** per call regardless of result count. Use `$GOOSEWORKS_API_BASE/v1/proxy/apollo/mixed_people/search` when possible. **Tip:** Use the dedicated proxy route `$GOOSEWORKS_API_BASE/v1/proxy/fiber/...` instead of the generic orthogonal proxy for cleaner billing tracking. ## Setup Read your credentials from ~/.gooseworks/credentials.json: ```bash export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])") export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))") ```
- Cost Reference
- Setup
- Capabilities
- Usage
- Search profiles from text
- Search companies from text
- Find person by email
- Live fetch LinkedIn profile
- Validate a single email
- Kitchen sink person lookup
- Kitchen sink company lookup
- Investor search
- Fetch LinkedIn profile posts
- Live fetch LinkedIn company
export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/search \
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/details \What does the people-company-search-fiber skill do?
People, company, investor, and job search with LinkedIn data enrichment
How do I install it?
Run `npx skills add gooseworks-ai/goose-skills --skill people-company-search-fiber --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From gooseworks-ai/goose-skills, a repository with 1,091 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.