Inputs
Provide these when prompted. The skill asks for anything missing before it runs.
Required
- Company records
Optional
- A canonical industry taxonomy
- A location format standard
- Known aliases to map
Agent Skill
Company Data Normalization
Normalize company names, domains, industries, and locations into consistent values.
Version 1.0 Updated June 2026 SKILL.md MIT 6 min read
Overview
What this skill does
The same company appears as "ACME Inc.", "Acme", and "acme.com" across sources, which fragments reporting, joins, and de-duplication.
This skill produces canonical company fields — name, domain, industry, location — with a confidence level on each and an explicit list of fields it could not resolve, so downstream joins and analysis are reliable.
When to use it
Best used for
- Standardizing company fields before a join or merge
- Cleaning a multi-source company list
- Preparing data for segmentation or analysis
- Resolving inconsistent industry labels
Know the limits
When not to use this skill
- You need to detect duplicates (use Duplicate Record Review)
- The records contain no company identifiers
- You need verified, authoritative registry data
Outputs
One record per company with a consistent, inspectable schema.
normalized_company_nameCanonical company name.
normalized_domainClean root domain, no protocol.
standardized_industryIndustry mapped to your taxonomy.
standardized_locationLocation in a consistent format.
normalization_confidencePer-record confidence level.
unresolved_fieldsFields that could not be normalized.
Example
Example
One record normalized.
Input
company: ACME Inc.
website: https://www.acme.com/about
industry: software
location: SFOutput
normalized_company_name: Acme
normalized_domain: acme.com
standardized_industry: Software
standardized_location: San Francisco, CA, USA
normalization_confidence: high
unresolved_fields: noneName, domain, industry, and location are now consistent and join-ready, with confidence reported so low-confidence rows can be reviewed.
Setup
How to use the skill
General steps first, then notes for specific clients where verified.
- 1Download the file using the button below, or copy the Markdown.
- 2Place it in a directory named after the skill (e.g. skill-name/).
- 3Make sure the filename stays exactly SKILL.md.
- 4Add any references or assets included with the package.
- 5Load the skill into a compatible agent and provide the required inputs.
Claude Code
- 1Create a folder for the skill and save SKILL.md inside it.
- 2Place the folder where your project's skills are discovered.
- 3Reference the skill when you want it applied to your data.
Other compatible clients
- 1Confirm the client supports the open Agent Skills format.
- 2Load the SKILL.md file as instructed by that client.
- 3If skills are not auto-loaded, paste the Markdown as instructions.
Source
Full SKILL.md source
Read the rendered skill or copy the complete Markdown. The download is generated from this exact source.
Version 1.0 SKILL.md ~2 KB MIT
Company Data Normalization
Purpose
Normalize company names, domains, industries, and locations into consistent values.
When to use this skill
- Standardizing company fields before a join or merge
- Cleaning a multi-source company list
- Preparing data for segmentation or analysis
- Resolving inconsistent industry labels
When not to use this skill
- You need to detect duplicates (use Duplicate Record Review)
- The records contain no company identifiers
- You need verified, authoritative registry data
Required inputs
- Company records
Optional inputs
- A canonical industry taxonomy
- A location format standard
- Known aliases to map
Rules
- Produce canonical values; do not invent unknown fields.
- Map industries only to the supplied taxonomy when given.
- Report a confidence level per record.
- List unresolved fields explicitly.
- Preserve originals alongside normalized values.
Process
- Parse each company record.
- Normalize name and domain.
- Map industry and standardize location.
- Assign confidence.
- List unresolved fields.
Output format
Return one record per company with the following fields:
- normalizedcompanyname
- normalized_domain
- standardized_industry
- standardized_location
- normalization_confidence
- unresolved_fields
Validation
- Confirm domains are root domains without protocol.
- Confirm industries match the taxonomy when provided.
- Confirm low-confidence rows are flagged.
Limitations
- Normalization is heuristic without an authoritative registry.
- Ambiguous names may need manual disambiguation.
Before you rely on it
Safety and limitations
- Normalization is heuristic without an authoritative registry.
- Ambiguous names may need manual disambiguation.
- Review the output before acting on it.
- Do not upload confidential datasets to an external model without authorization.
- Outputs depend on the model and the source data and are not guaranteed to be accurate.
History
Changelog
- v1.0June 2026
- Initial release.
Questions
Agent Skill FAQ
What does the confidence score mean?
How certain the normalization is for each field. Low-confidence values are flagged so you can review ambiguous names or domains instead of trusting a silent guess.
Does it merge duplicate companies?
No. It standardizes fields so duplicates become detectable; use Duplicate Record Review to merge them.
Do I need ProfileSpider to use this skill?
No. The skill works on any compatible data. ProfileSpider is one convenient way to produce that structured input.
Does running this skill send data to ProfileSpider?
No. Downloading or copying the file does not send any data to ProfileSpider. What happens afterward depends on the AI service you load it into.
Are Agent Skills the same as prompts?
No. A skill is a structured, reusable package — task, inputs, rules, process, and output format — so the workflow runs consistently and can be shared, versioned, and edited.