firecrawl-lead-research Skill for Claude: What It Does and How to Install It

Makes your agent research people and companies you name, fill missing CSV columns and prepare meeting briefs.

Installs: 31.6K; on skills.sh
Stars: 214; on GitHub
Files: 1; besides SKILL.md
Updated: Nov 2026; last repo commit

This skill makes your agent look up the people and companies you give it. Fields such as role, headcount, funding and location come from Firecrawl's Alexandria providers, and the web only adds context like recent news.

It handles a single person, a single company, a whole CSV that keeps your rows and order, role checks, and meeting briefs. It needs a Firecrawl API key, the Firecrawl CLI and authenticated Alexandria access, and it does not create CRM records or send outreach.

Good for

Sales teams enriching a list of leads or accounts
Anyone preparing for a call with a named person or company
Ops people who need missing columns filled in a people or company CSV

Install firecrawl-lead-research

Claude Code

Copy this prompt.

Install the firecrawl-lead-research skill in Claude Code. Run this command:

/plugin marketplace add firecrawl/firecrawl-workflows
/plugin install firecrawl-workflows@firecrawl-workflows

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Pick one route. The plugin routes install the whole firecrawl-workflows plugin: 16 skills (counted from the skills list in its plugin.json), and the repo tree has no hooks, agents or MCP config files. The skills-only routes install just firecrawl-lead-research. The skill drives the Firecrawl CLI and needs a Firecrawl API key. Install the Firecrawl CLI first, since the skill runs firecrawl commands: npm install -g firecrawl-cli (Firecrawl CLI docs), or npx -y firecrawl-cli@latest init -y --browser to install it, sign in and add the shared skills in one step. Then run firecrawl login or export FIRECRAWL_API_KEY. Who pays: the Firecrawl account that owns the key. Every call uses credits; a new account starts on the free plan with 1,000 credits a month and no card. Per Firecrawl's billing docs: Alexandria data tools cost the price listed on each tool, while discovery is free; search 2 credits per 10 results; scrape 1 credit per page.

Built from the package data we hold. Not yet tested by us. Source.

What's in the skill

When it loads

Enrich and research the people and companies the user names or supplies with Firecrawl Alexandria data: background on a person, a professional profile URL to look up, whether someone still holds a role, missing columns in a table or CSV of people or companies, firmographics for company domains (industry, headcount, funding, location), and pre-call or meeting briefs. Use whenever the request is about specific named people or companies, even without the word enrich, since roles, headcount and funding change faster than training data. Not for finding new prospects (use firecrawl-lead-gen) or a company's published press, sales or support contacts (use firecrawl-business-contacts).

Sections in SKILL.md

Workflow
Output
Weekly refresh
Rules

Key facts

Author: Firecrawl (frontmatter author, and the repo owner)
License: ISC (frontmatter and the README)
Installs on skills.sh: 31,568 (Nov 2, 2026)
GitHub stars: 214 for the whole firecrawl/firecrawl-workflows repo (Nov 2, 2026)
Last repo commit: Nov 1, 2026
What it includes: 2 files including SKILL.md: references/meeting-brief.md (bundles no scripts)
Needs: A Firecrawl API key (FIRECRAWL_API_KEY) with credits, and the Firecrawl CLI (npm install -g firecrawl-cli)
Part of: The firecrawl-workflows plugin: 16 skills in its Claude plugin.json (counted), 19 skill folders in the repo tree
Works in: AI coding agents, per the README. The repo also ships plugin manifests for Claude Code, Codex and Cursor

What it includes

Lists people or company providers that accept the identifiers you gave
Uses firecrawl find-tools with the people or companies category.
Runs code · Find the provider
Runs firecrawl list for a provider's capabilities, inputs and response
Checks what the capability accepts before running it.
Runs code · Read the contract
Runs firecrawl scrape <provider>/<capability> with JSON options and no URL
Uses a bulk capability for lists and checks every item in the result, since one item can fail while the request succeeds.
Runs code · Run the lookup
Searches and scrapes for recent news, talks or published context
Not used to fill fields the providers did not return.
Network · Add web context
Keeps every input column, row and row order, then adds fields, match_status and sources
match_status is matched, not_found or error. CSV files are written with a CSV writer.
Write · CSV enrichment
Company, People, Recent activity, Talking points and Likely priorities
Follows references/meeting-brief.md. Likely priorities are labeled as hypotheses.
Network · Meeting brief
Re-runs on an earlier file and reports only what changed
New titles or employers, and headcount or funding changes.
Write · Weekly refresh

From the official docs

Permissions

Medium risk

It sends names and company details about real people to third-party providers through your Firecrawl account. Only research people you are allowed to look up, and check the provider terms before you accept them.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Names you supply are sent to data providers
Each lookup passes the identifiers you gave, such as a name and company, a profile URL, an email or a domain, to a provider. Only supply people you are allowed to research (our advice). github.com
Provider data terms need an admin to accept them
On THIRD_PARTY_DATA_TERMS_REQUIRED the agent shows you the dashboard link and the provider name. An organization admin accepts the terms, then you tell it to continue. github.com
Meeting briefs are limited to professional context
references/meeting-brief.md says not to collect private personal details or infer sensitive traits. github.com
It spends your Firecrawl credits
Every call is billed in credits to the account behind the key. Per Firecrawl's billing docs: Alexandria data tools cost the price listed on each tool, while discovery is free; search 2 credits per 10 results; scrape 1 credit per page. A free account has 1,000 credits a month, so a large run can use it up. docs.firecrawl.dev

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	No read-only mode is documented in SKILL.md. Use version control for files it writes.
Talks to	Firecrawl hosted service and its Alexandria data providers. Web pages it searches for recent news and talks
Sign-in and keys	SKILL.md declares FIRECRAWL_API_KEY as a required input. The README says Alexandria access requires an authenticated Firecrawl account. Neither says where credentials are kept.
Scopes	Runs Firecrawl find-tools, list, scrape and search commands with your API key Looks up named people and companies in Alexandria providers Can write an enriched CSV Spends credits on the Firecrawl account that owns your API key

Questions

What does the firecrawl-lead-research skill do?

It makes your agent enrich people and companies you already have. It fills in roles, firmographics and missing CSV columns from Alexandria data and writes pre-meeting briefs.

How do I install it in Claude Code or Codex?

Use the install box at the top of this page. Each client has a plugin route and skills CLI commands. The README says Alexandria access requires an authenticated Firecrawl account, Install the Firecrawl CLI first (npm install -g firecrawl-cli, per its docs), then run firecrawl login or set FIRECRAWL_API_KEY.

Who pays for it?

You do, through the Firecrawl account that owns your API key. Firecrawl bills in credits, and a new account starts on the free plan with 1,000 credits a month and no card. Per its billing docs: Alexandria data tools cost the price listed on each tool, while discovery is free; search 2 credits per 10 results; scrape 1 credit per page. Check your balance with firecrawl credit-usage.

firecrawl-lead-research vs firecrawl-lead-gen?

Lead-research works on people and companies you supply. Lead-gen finds new prospects, and the lead-research description points that job there.

What does a meeting brief contain?

A company summary, each attendee's role and background, dated recent activity with links, talking points grounded in the evidence, and likely priorities labeled as hypotheses. The reference file says to keep to professional context and not to collect private personal details or infer sensitive traits.

Does it change my CSV?

It keeps every input column, row and row order and adds the requested fields plus match_status and sources. Fields no provider returned stay empty.

Is it safe to install?

It has two Markdown files and bundles no scripts. When it runs, your agent sends names and company domains to data providers through your Firecrawl account. Treat the results as personal data and check the provider terms you accept.

Information

updated Nov 2, 2026

Repository: firecrawl/firecrawl-workflows
Folder: skills/firecrawl-lead-research

firecrawl/firecrawl-workflows skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 9

firecrawl-lead-research SKILL.md · github.com
firecrawl-workflows README · github.com
firecrawl-workflows plugin.json · github.com
firecrawl-workflows marketplace.json · github.com
firecrawl-workflows Codex plugin.json · github.com
meeting-brief.md · github.com
Firecrawl CLI docs · docs.firecrawl.dev
Firecrawl billing and credits · docs.firecrawl.dev
firecrawl/cli README · github.com