agentleFS
Sign inStart free
Layneformalized225Layneformalized225/ai-cofounder/skills/exa-company-research/SKILL.md

exa-company-research

Skill1 starsChanged 8 months agoMITView on GitHub

Company research using Exa search. Finds company info, competitors, news, tweets, financials, LinkedIn profiles, builds company lists. Use when researching companies, doing competitor analysis, market research, or building company lists.

2 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use exec to call: mcporter call exa-search.web_search_advanced_exa <params>

    line 11
  2. Distinctive:

    All searches run via mcporter CLI.

    line 13
  3. Very specific:

    Never run searches in main context: Always spawn subagents via llm_task or run in sequence with isolated results.

    line 17
  4. Very specific:

    If Exa returns insufficient results or content is auth-gated → use browser tool as fallback.

    line 79

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Company Research (Exa)

Tool

Use exec to call: mcporter call exa-search.web_search_advanced_exa <params>

All searches run via mcporter CLI. Never call Exa directly — always use mcporter.

Critical Rules

  • Never run searches in main context. Always spawn subagents via llm_task or run in sequence with isolated results.
  • Query variation: generate 2-3 phrasings, run in parallel, merge + deduplicate.
  • Dynamic numResults: "a few" → 10-20, "comprehensive" → 50-100, explicit number → match it.

Categories

CategoryUse for
companyHomepages, metadata (headcount, location, funding)
newsPress coverage, announcements
tweetSocial presence
peopleLinkedIn profiles
(none)General web, deep dives

Start with category=company for discovery, then use other categories for deeper research.

Category Restrictions

With category=company: do NOT use includeDomains, excludeDomains, or date filters — causes errors. includeText/excludeText: only single-value strings.

Call Syntax

# Company discovery
mcporter call exa-search.web_search_advanced_exa \
  query="AI infrastructure startups San Francisco" \
  category=company \
  numResults=20 \
  type=auto

# Deep dive on specific company
mcporter call exa-search.web_search_advanced_exa \
  query="Anthropic funding rounds valuation 2024" \
  type=neural \
  livecrawl=fallback \
  numResults=10 \
  includeDomains='["techcrunch.com","crunchbase.com","bloomberg.com"]'

# News coverage
mcporter call exa-search.web_search_advanced_exa \
  query="Anthropic AI safety 2024" \
  category=news \
  numResults=15 \
  startPublishedDate=2024-01-01

# Tweets/social
mcporter call exa-search.web_search_advanced_exa \
  query="Anthropic Claude new features" \
  category=tweet \
  numResults=20

Output Format

Return:

  1. Results — structured list, one company per row (name, URL, description, key facts)
  2. Sources — URLs with 1-line relevance
  3. Notes — any uncertainty or conflicts

Browser Fallback

If Exa returns insufficient results or content is auth-gated → use browser tool as fallback.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free