gtm-pipeline:company-search
Skill1 starsChanged 5 months agoMITView on GitHub
Build a list of companies matching ICP criteria. Use when a client needs a company list — no existing list, wants to expand, or signal-based discovery needs enrichment. Providers: Sales Navigator + PhantomBuster, Parallel FindAll, Firecrawl Agent, BC/FE byproduct, web scraping. Also triggers on "build company list", "find companies", "company search".
- Reads credentials
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- keinsaasforever/gtm-pipeline-skillsedited, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- keinsaasforever/gtm-pipeline-skills★ 7571% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- article-writingSkill
- brand-voiceSkill
- deep-researchSkill
- email-personalizationSkill
- exa-searchSkill
- gtm-pipeline:company-enrichmentSkill
- gtm-pipeline:contact-filterSkill
- gtm-pipeline:demoSkill
- gtm-pipeline:outreachSkill
- gtm-pipeline:people-enrichmentSkill
- gtm-pipeline:people-searchSkill
- gtm-pipeline:pipelineSkill
- gtm-pipeline:setupSkill
- gtm-pipeline:signal-searchSkill
- investor-materialsSkill
- investor-outreachSkill
- lead-intelligenceSkill
- marketing-campaignSkill
- market-researchSkill
- research-opsSkill
- social-graph-rankerSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 42
When you want contacts directly (skip separate people search)
- Distinctive: line 71
Write like a research brief — detailed, with source guidance
- Very specific: line 87
Always include company_website and linkedin_company_url in output schema.
- Very specific: line 89
Always check latest docs via context7 (libraryName: parallel-web).
- Distinctive: line 100
When running people search via BC Lead Finder or FE Finder, company data is returned as a byproduct — no extra API cost:
- Distinctive: line 105
Use this when you already need contacts AND want to build/verify the company list simultaneously.
- Distinctive: line 170
Always spot-check domains — SerpAPI returns wrong results for generic names and global brands.
- Distinctive: line 190
Before searching, ensure these are defined:
- Distinctive: line 206
Check company names, domains, LinkedIn URLs, industries
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Company Search
Build a list of companies matching ICP criteria. Returns a CSV with domains and LinkedIn URLs.
Read .agents/skills/_shared/conventions.md before executing.
When to Use
- Workflow 1 (Company-First): Client needs a company list — no existing list, or wants to expand beyond what they have
- Workflow 2 (Signal-First): Signal-based discovery has found companies — this skill enriches the initial list with domains/LinkedIn URLs if missing
Inputs
| Input | Required | Source |
| ICP definition | Yes | User prompt, context/icp.md, or discovery questions |
| SN search URL | Optional | Sales Navigator saved search |
| Existing partial list | Optional | User-provided CSV |
Provider Selection
Ask the user which provider to use.
From Sales Navigator (most comprehensive B2B data)
- SN Account Search → PhantomBuster SN Account Scraper
- Rich data: name, industry, headcount, location, LinkedIn URL, SN URL, employee search URLs, revenue range, growth metrics, department headcounts
- PhantomBuster agent:
Sales Navigator Account Scraper - Input: SN search URL
- Output: full company profile data
- SN Lead Search → PhantomBuster Employee Export
- When you want contacts directly (skip separate people search)
- PhantomBuster agent:
Sales Navigator Employee Export - Input: spreadsheet of company URLs
From Parallel FindAll (signal-based discovery)
Endpoint: POST https://api.parallel.ai/v1beta/findall/runs
Required header: parallel-beta: findall-2025-09-15
Auth: x-api-key: $PARALLEL_API_KEY
Always ask which processor to use: core, core2x, pro, ultra
Best when combined with signal criteria in the objective. Returns matched companies with reasoning and confidence.
{
"objective": "Find all DACH-based B2B SaaS companies with 10-200 employees that have shown signals of operational scaling challenges, digital transformation initiatives, or recent funding in the last 4 months. Focus on non-technical sectors: e-commerce, professional services, recruiting agencies, marketing agencies.",
"entity_type": "companies",
"match_conditions": [
{"name": "location", "description": "Company must be headquartered in DACH region (Germany, Austria, Switzerland)"},
{"name": "size", "description": "Company must have between 10 and 200 employees"},
{"name": "recent_signals", "description": "Company must have shown at least one buying signal in the last 4 months"}
],
"generator": "core",
"match_limit": 25
}Writing good objectives:
- Write like a research brief — detailed, with source guidance
- Describe what signals/sources to start from
- Include geographic, industry, and size constraints in text AND as match_conditions
- Include a LinkedIn URL condition if needed downstream
Polling:
GET /v1beta/findall/runs/{findall_id} # status
GET /v1beta/findall/runs/{findall_id}/result # resultsTimeout: 15 min for core/core2x, 30 min for pro/ultra
Enrich FindAll results to add missing fields:
POST /v1beta/findall/runs/{findall_id}/enrichAlways include company_website and linkedin_company_url in output schema.
Always check latest docs via context7 (libraryName: parallel-web).
From Firecrawl Agent (web agent)
POST https://api.firecrawl.dev/v2/agent with spark-1-pro
- Include structured schema with citation fields for traceability
- Good for niche criteria or specific industry directories
From BetterContact or FullEnrich (people search as company source)
When running people search via BC Lead Finder or FE Finder, company data is returned as a byproduct — no extra API cost:
- BC Lead Finder:
company_name,company_domain,company_linkedin_urlper lead result - FE Finder:
current_company_name,current_company_domainper result
Use this when you already need contacts AND want to build/verify the company list simultaneously.
Both tools also offer free dashboard search for one-time manual company lookups.
From Pipe0 Amplemarket (company search)
Endpoint: POST https://api.pipe0.com/v1/searches/run/sync
Search ID: companies:profiles:amplemarket@1
Auth: Authorization: Bearer $PIPE0_API_KEY
{
"config": {"environment": "production", "dedup": {"strategy": "default"}},
"searches": [{
"search_id": "companies:profiles:amplemarket@1",
"config": {
"limit": 100,
"filters": {}
}
}]
}Response fields:
results = response.get("results", [])
for r in results:
name = r.get("company_name", {}).get("value", "")
website = r.get("company_website_url", {}).get("value", "")
desc = r.get("company_description", {}).get("value", "")
li_url = r.get("company_profile_url", {}).get("value", "")
match = r.get("amplemarket_company_match", {}).get("value", "")Cost: 2.00 credits per page (100 results), per-search billing
From Web Scraping
- Industry directories, association member lists, competitor customer lists
- Firecrawl scrape or manual collection
Missing Data Recovery
| Have | Missing | Solution |
| Names / LinkedIn URLs | Domains | SerpAPI domain lookup (see people-search Step 0) |
| Names / domains | LinkedIn URLs | PhantomBuster URL Finder |
| LinkedIn company URLs | SN URLs | PhantomBuster can derive |
SerpAPI Domain Lookup
GET https://serpapi.com/search
?engine=google_light
&q={company_name}
&location={target_country}
&google_domain={country_google}
&api_key=$SERPAPI_API_KEYExtract: urllib.parse.urlparse(organic_results[0]["link"]).netloc.lstrip("www.")
Always spot-check domains — SerpAPI returns wrong results for generic names and global brands.
PhantomBuster API
Auth: X-Phantombuster-Key-1: <key>
Launch: POST /api/v2/agents/launch (agent ID + override arguments)
Poll: GET /api/v2/agents/fetch?id=<agent_id> (status == "finished")
Result: GET /api/v2/containers/fetch-result-object (or download S3 CSV)Agent IDs and detailed API: see PhantomBuster API learnings doc (requested at runtime if needed).
Execution Protocol
1. Clarify ICP
Before searching, ensure these are defined:
- Industry / vertical
- Company size (headcount range)
- Location / geography
- Revenue range (if relevant)
- Exclusions (e.g. no software companies)
2. Select Provider
Present options to user with estimated costs. Get approval.
3. Test Run
- For FindAll: start with
match_limit: 10, review results - For SN+PB: export 10–20 companies, verify data quality
- For Firecrawl Agent: test with a small prompt
4. Review
- Check company names, domains, LinkedIn URLs, industries
- Flag mismatches or low confidence results
- Get approval for full run
5. Full Run
- Submit full search
- Save results to
csv/input/companies_raw.csv
Output
CSV at csv/input/companies_raw.csv:
company_name, company_domain, company_linkedin_url,
industry, location, country, headcount, headcount_range,
sourceAdditional fields from SN (if available):
salesNavigatorCompanyUrl, employeeSearchUrl, decisionMakersSearchUrl,
yearFounded, revenue_range, growth_6m, growth_1y, growth_2y,
headcount_engineering, headcount_sales, headcount_operations, headcount_ITWhat's Missing (To Document)
- PhantomBuster API: full launch/poll/download flow for each agent (SN Account Scraper, Employee Export, URL Finder)
- Firecrawl Agent (
POST /v2/agent): request/response format with structured schema - Exa Websets via Pipe0: company discovery endpoint
- n8n workflow API: export/import existing flows for new client instances
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

