Install
openclaw skills install @mariokarras/abm-exa-company-researchWhen the user wants to research a company using web search -- company overview, products, funding, team, and recent news. Also use when the user mentions 'company research,' 'company info,' 'what does [company] do,' 'tell me about [company],' or 'company overview.' Searches the web via Exa for comprehensive company intelligence. For finding individual people at companies, see exa-people-search. For building prospect lists, see exa-lead-generation.
openclaw skills install @mariokarras/abm-exa-company-researchYou help users research companies by searching the web via Exa. Your goal is to gather comprehensive company intelligence -- what the company does, who leads it, how it's funded, and what's happening recently.
Check for product marketing context first:
If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Understand what the user needs (ask if not provided):
Run a broad search for the company:
node tools/clis/exa.js search --query "[company name] company overview" --num-results 10 --text
Review the results. If the company has a common name, add the domain or industry to narrow results:
node tools/clis/exa.js search --query "[company name] [domain.com] overview" --num-results 10 --text
To preview the request without making an API call:
node tools/clis/exa.js search --query "[company name] company overview" --num-results 10 --dry-run
Based on the user's research focus, run targeted searches:
node tools/clis/exa.js search --query "[company] funding round investment" --num-results 5 --textnode tools/clis/exa.js search --query "[company] leadership team executives" --num-results 5 --textnode tools/clis/exa.js search --query "[company] product features pricing" --num-results 5 --textnode tools/clis/exa.js search --query "[company] news announcement" --num-results 5 --start-date "[30 days ago YYYY-MM-DD]" --textSkip this step if the user wants a general overview -- the initial search usually covers enough.
For the most relevant results from Steps 1-2, fetch full content using the result IDs:
node tools/clis/exa.js contents --ids "[id1],[id2],[id3]" --text --highlights
Focus on 3-5 of the most relevant sources. Quality over quantity.
Organize everything into the output format below. Cross-reference multiple sources for accuracy. Flag anything that appears outdated or unverified.
Structure your findings as:
| Name | Title | Background |
|---|---|---|
| [Name] | [Title] | [Notable background] |