Systems Lab

Agent skill

company-enrichment

Enrich company data in Clay with firmographics, technographics, revenue, headcount, and industry.

slowingReaches the webInstructions only484 words

Filed under Prospecting and list building.

From Frontal-so/outbound-skills · 73 skills · 4 · pushed 2026-07-14

What it does when it runs

Enrich company data in Clay with firmographics, technographics, revenue, headcount, and industry. Use when the user asks about company enrichment, firmographic data, tech stack detection, company revenue, employee count, industry classification, or company research workflows. Triggers on "company data", "firmographics", "technographics", "company enrichment", "revenue data", "headcount", "tech stack", "company research", "industry data". Do NOT use for people/contact enrichment, email finding, or phone number discovery.

Read from the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
  • frontal.so
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about company-enrichment

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/Frontal-so/outbound-skills.git /tmp/outbound-skills
git -C /tmp/outbound-skills sparse-checkout set "master-skills/clay/.claude/skills/company-enrichment"
mkdir -p ~/.claude/skills/company-enrichment
cp -R "/tmp/outbound-skills/master-skills/clay/.claude/skills/company-enrichment/." ~/.claude/skills/company-enrichment/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from Frontal-so/outbound-skills/blob/27cd847be5ce7e9b749b1d672cbfb29935d911db/master-skills/clay/.claude/skills/company-enrichment/SKILL.md, which is licensed MIT (repository). 484 words, 8 headings.

Company Enrichment

You help users enrich company records in Clay with firmographic, technographic, and contextual data using the optimal provider sequence.

References

  • Read {SKILL_BASE}/resources/core-concepts.md for Clay table fundamentals and column types.
  • Read {SKILL_BASE}/resources/templates/clay-enrichment-workflows.md for the 9-step pipeline and company enrichment templates.

Company Enrichment Waterfall (Recommended Order)

  1. Apollo (2-3 credits) -- employee count, revenue, industry, founding year
  2. Ocean.io (2-3 credits) -- fills gaps in firmographic data
  3. LinkedIn Company Enrichment (2 credits) -- recent updates, description, specialties
  4. Claygent (1-3 credits) -- funding news, press mentions, custom research
  5. HG Insights (3-5 credits) -- deep tech stack data (enterprise-grade)

Always add conditional runs: only call the next provider if the previous one left gaps.

Key Data Points to Collect

Data PointBest ProviderCredits
Employee countApollo, LinkedIn2-3
RevenueApollo, PDL, HG Insights2-5
IndustryApollo, LinkedIn2-3
Tech stackHG Insights, BuiltWith3-5
FundingClaygent, Harmonic.ai1-3
Company descriptionLinkedIn, Claygent1-2
Location/HQApollo, Clearbit2-3

Minimum Required Input

  • Best: Company domain (e.g., acme.com)
  • Fallback: Company name + location (less accurate)
  • From people table: Use a formula to extract domain from email: {{email}}.split("@")[1]

Setup Steps

  1. Import company list (CSV with domain column, or CRM import)
  2. Add Apollo enrichment with conditional: "Only run if /employee_count is empty"
  3. Add LinkedIn enrichment with conditional: "Only run if /industry is empty"
  4. Add tech stack enrichment if needed (HG Insights or BuiltWith)
  5. Use Claygent for custom data not in standard databases
  6. Test on 50 rows before running full table

Credit Optimization

  • Apollo covers 60-70% of standard firmographic fields in one call
  • Only run expensive providers (HG Insights) on rows where Apollo returned empty
  • Use formulas (0 credits) to derive data: e.g., company size category from headcount
  • Save all results to CRM or Supabase -- never pay twice for the same company

Examples

Example 1: "I have 2,000 company domains and need revenue + headcount" --> Apollo enrichment first (covers most). Conditional Ocean.io for gaps. Formula to bucket revenue ranges. Estimated cost: 2,000 x 3 credits = ~6,000 credits.

Example 2: "I need to know what tech stack my target accounts use" --> HG Insights for enterprise-grade tech data (3-5 credits/row). Conditional: only run on companies with 50+ employees. Alternative: BuiltWith for website tech only (cheaper).

Example 3: "I imported 30K companies from Salesforce with only names, no domains" --> Use Google Search via Claygent to find domains first. Then run standard company enrichment waterfall. Save enriched data back to Salesforce via CRM sync.


Part of Frontal — free, open GTM skills for your AI agent. Browse the library →

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what company-enrichment does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.