Inputs
Provide these when prompted. The skill asks for anything missing before it runs.
Required
- Company names or records
Optional
- Your offering or angle for relevance scoring
- Industries of interest
- Fields you want prioritized
Agent Skill
Company Research
Turn company records into a structured research summary: overview, market position, and relevance.
Version 1.0 Updated June 2026 SKILL.md MIT 6 min read
Overview
What this skill does
Researching companies one at a time produces notes in inconsistent shapes, which makes accounts hard to compare and slows account planning.
This skill converts each company record into the same structured profile — overview, industry, offering, target customers, market position — and explicitly flags what is still unknown, so a researcher can trust the gaps as much as the findings.
When to use it
Best used for
- Building account research before outreach
- Producing comparable company profiles at scale
- Summarizing a target account list
- Flagging what still needs manual research
Know the limits
When not to use this skill
- The records contain no usable company signal
- You need real-time financials or news the data lacks
- You want verified contact details rather than a profile
Outputs
One profile per company with a consistent, inspectable schema.
company_overviewA concise factual summary of the company.
industryPrimary industry/category.
products_or_servicesWhat the company offers.
target_customersWho they appear to serve.
market_positionPositioning relative to the category.
research_gapsUnknowns that need manual research.
relevance_assessmentWhy the company matters to your goal.
Example
Example
A profile built from a short company record.
Input
Goal: Find ICP-fit accounts for our DevOps tool.
Company: Lumen Robotics — industrial automation SaaS, Austin TX, ~180 employees, sells to manufacturers.Output
company_overview: Industrial automation SaaS for manufacturers, ~180 employees, Austin TX.
industry: Industrial automation / SaaS
products_or_services: Automation software for factory operations
target_customers: Mid-market manufacturers
market_position: Vertical SaaS in a niche category
research_gaps: Engineering team size; current DevOps stack
relevance_assessment: Likely ICP fit; confirm engineering footprintThe profile is complete enough to judge fit, and the research_gaps make clear what to confirm (engineering size and stack) before prioritizing.
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 Research
Purpose
Turn company records into a structured research summary: overview, market position, and relevance.
When to use this skill
- Building account research before outreach
- Producing comparable company profiles at scale
- Summarizing a target account list
- Flagging what still needs manual research
When not to use this skill
- The records contain no usable company signal
- You need real-time financials or news the data lacks
- You want verified contact details rather than a profile
Required inputs
- Company names or records
Optional inputs
- Your offering or angle for relevance scoring
- Industries of interest
- Fields you want prioritized
Rules
- Use only supplied information and clearly marked context.
- Do not invent financials, headcounts, or customers.
- Separate facts from inferences.
- List research gaps rather than filling them.
- Keep the structure identical across companies.
Process
- Parse each company record.
- Summarize overview, industry, offering, and customers.
- Assess market position from available signal.
- List research gaps.
- Assess relevance to the stated goal.
Output format
Return one profile per company with the following fields:
- company_overview
- industry
- productsorservices
- target_customers
- market_position
- research_gaps
- relevance_assessment
Validation
- Confirm each field is supported or marked as a gap.
- Confirm no invented figures appear.
- Confirm relevance ties to the stated goal.
Limitations
- Profiles are only as current as the input data.
- Market position is an interpretation, not a ranking.
Before you rely on it
Safety and limitations
- Profiles are only as current as the input data.
- Market position is an interpretation, not a ranking.
- 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
Does it pull live data from the web?
No. It structures and interprets the company records you provide. For real-time financials or news, add that data to the input — the skill will not invent facts it cannot see.
Can it research many companies at once?
Yes. Provide a list and it returns one structured profile per company using the same schema for easy comparison.
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.