← Back to Skills Marketplace
169
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install data-enrichment
Description
Enrich company and contact lists with public data — firmographics, technographics, social profiles, funding history, and employee count estimates. Clean, ded...
README (SKILL.md)
Data Enrichment Skill
Transform raw company/contact lists into enriched, scored, CRM-ready datasets.
What It Does
- Company Enrichment — Add firmographic data (industry, size, revenue range, funding, tech stack)
- Contact Enrichment — Find titles, social profiles, recent activity
- Data Cleaning — Deduplicate, normalize, fix formatting issues
- Lead Scoring — Score enriched records on custom criteria
- Export — Output in CSV, JSON, or CRM-import format
Usage
Enrich a Company List
Enrich this list of companies:
1. Acme Corp
2. Widget Labs
3. DataFlow Inc
4. CloudScale
5. GrowthLab
For each, find:
- Industry and sub-industry
- Employee count (estimated range)
- Funding status and last round
- Tech stack (if detectable)
- Key decision makers (CEO, CTO, CMO)
- LinkedIn company page
- Recent news (last 90 days)
Clean and Deduplicate
Clean this CSV:
[Paste CSV or provide file]
Tasks:
- Remove exact and fuzzy duplicates
- Normalize company names (Inc/LLC/Ltd variations)
- Fix email formatting issues
- Flag incomplete records
- Standardize phone number format
- Fill missing fields where possible from public data
CRM Enrichment
I'm importing these contacts into [HubSpot/Salesforce/Pipedrive]:
[Paste contact list]
Enrich each record with:
- Company info (size, industry, revenue)
- Contact title and seniority level
- LinkedIn profile URL
- Lead score (1-100 based on: company size 10-500, SaaS industry, recent funding)
- Tag: hot/warm/cold
Output as CSV with CRM-compatible column headers.
Technographic Profiling
For these companies, identify their tech stack:
- What CMS do they use? (WordPress, Shopify, custom)
- What analytics? (GA4, Mixpanel, Amplitude)
- What email platform? (Mailchimp, SendGrid, HubSpot)
- What payment processor? (Stripe, PayPal, Square)
- Any AI/automation tools visible?
Companies: [list]
Output Format
Enriched Company Record
## [Company Name]
| Field | Value |
|-------|-------|
| Industry | [Industry / Sub-industry] |
| Employees | [Range estimate] |
| Revenue | [Range estimate] |
| Founded | [Year] |
| Funding | [Total raised / Last round] |
| Location | [HQ city, country] |
| Website | [URL] |
| LinkedIn | [URL] |
| Tech Stack | [Detected tools] |
| Recent News | [Last 90 days highlights] |
### Key Contacts
| Name | Title | LinkedIn | Seniority |
|------|-------|----------|-----------|
| [Name] | [Title] | [URL] | [C-level/VP/Director/Manager] |
CSV Export Format
company_name,industry,employees,revenue_range,funding,location,website,linkedin,tech_stack,news,contact_name,contact_title,contact_linkedin,lead_score,tag
Data Sources
- Public websites and About pages
- LinkedIn (public profiles)
- Crunchbase (public funding data)
- BuiltWith / Wappalyzer (tech stack)
- News aggregators (recent activity)
- Job postings (growth signals)
Best Practices
- Provide clean input data (company names, domains, or LinkedIn URLs)
- Specify which fields matter most — enrichment is faster when focused
- For large lists (100+), process in batches of 25
- Always verify enriched data before importing to CRM
- Pair with
lead-gen-researchfor full qualification + enrichment pipeline
References
references/field-definitions.md— What each enrichment field meansreferences/scoring-model.md— Default lead scoring weights
Usage Guidance
This skill is internally consistent with public-data enrichment, but consider the following before installing: (1) Several named data sources (Crunchbase, BuiltWith, LinkedIn) often require API keys or paid access and may impose rate limits — plan how you'll supply and protect any keys if you use them. (2) The instructions allow broad web lookups/scraping; ensure you have permission and are compliant with provider Terms of Service and privacy laws (e.g., GDPR) before enriching personal contact data. (3) Because it's instruction-only, the agent will decide how to gather data — restrict scope in prompts (use approved APIs, rate limits, and only public sources) and verify results before importing into CRMs. (4) If you need automated, reliable access to those third-party services, add explicit, minimal environment variables for needed API keys rather than letting the agent attempt ad-hoc scraping.
Capability Analysis
Type: OpenClaw Skill
Name: data-enrichment
Version: 1.0.1
The data-enrichment skill bundle consists entirely of documentation and instructions for an AI agent to perform lead research and data cleaning. There is no executable code, and the instructions in SKILL.md and the reference files are strictly aligned with the stated purpose of processing firmographic and contact data from public sources. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description (company/contact enrichment, firmographics, technographics, scoring) matches the instructions and reference docs. The skill only uses public sources (LinkedIn, Crunchbase, BuiltWith/Wappalyzer, news), which is consistent with enrichment.
Instruction Scope
SKILL.md is instruction-only and stays focused on enrichment/cleaning/scoring tasks. It assumes the agent will fetch public web data but does not prescribe reading unrelated local files or environment secrets. However, instructions are fairly open-ended about how to collect public data (scraping vs API), which could lead to broad web queries or scraping behavior if not constrained.
Install Mechanism
No install spec and no code files are present, so nothing will be written to disk or executed by an installer. This is the lowest-risk pattern for a skill of this type.
Credentials
The skill requests no environment variables or credentials, which is proportionate for an instruction-only public-data enrichment skill. One caveat: some listed data sources (Crunchbase, BuiltWith, LinkedIn) often require API keys or paid access in practice; the SKILL.md does not request or document those credentials, so an implementer would likely need to supply them externally.
Persistence & Privilege
Skill is not always-enabled, does not require system-level changes, and contains no installation logic. It does not request elevated or persistent privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install data-enrichment - After installation, invoke the skill by name or use
/data-enrichment - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Updated metadata formatting in SKILL.md to comply with current best practices.
- Added explicit version, author, category, and tags fields at the top.
- No changes to functionality or usage; documentation and skill behavior remain the same.
v1.0.0
Initial release — company/contact list enrichment with firmographics, technographics, lead scoring, CRM export
Metadata
Frequently Asked Questions
What is Data Enrichment?
Enrich company and contact lists with public data — firmographics, technographics, social profiles, funding history, and employee count estimates. Clean, ded... It is an AI Agent Skill for Claude Code / OpenClaw, with 169 downloads so far.
How do I install Data Enrichment?
Run "/install data-enrichment" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Data Enrichment free?
Yes, Data Enrichment is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Data Enrichment support?
Data Enrichment is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Data Enrichment?
It is built and maintained by tktk-ai (@tktk-ai); the current version is v1.0.1.
More Skills