Skip to main content
skill CX Codex

tavily-entity — Claude Code skill: what it does, how to install

tavily-entity — a skill for Claude Code and Codex that enriches company, person, or organization profiles with Tavily web data. Populates CRM records and CSV spreadsheets while resolving name collisions.

MIT 2,500 installs ★ 497 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add tavily-ai/skills --skill tavily-entity -a claude-code
Open on GitHub

What tavily-entity does

The skill extracts verified entity data using the tvly command-line utility. Before writing any values, it isolates the target from common name matches. An entity is considered identified only when two separate identifiers agree, such as a company name combined with its verified domain, or a person paired with their confirmed workplace.

Every field value originates from primary sources, including official company sites, regulatory filings, and personal profiles. Empty fields remain blank whenever an authoritative page lacks the fact. When reliable sources show conflicting metrics, the skill keeps the more direct source and logs the discrepancy in a note.

Execution requires Bash tool access with the tvly binary configured. When processing CSV files containing over 25 rows, the agent reports the count and awaits approval before saving results to an enriched CSV file.

What it helps with

  • enrich CRM records with verified company details from authoritative sites
  • resolve ambiguous company or person names using two matching identifiers
  • populate missing columns across an existing list of leads in CSV format
  • gather recent milestone signals like funding rounds or leadership changes

Example prompts for the agent

  • Enrich the company rows in leads.csv with headcount and headquarters
  • Find the current employer, title, and verified profile for John Doe at Acme
  • Who is Dario Amodei and what company does he run?

How to install tavily-entity

1Skills CLI (Vercel)

npx skills add tavily-ai/skills --skill tavily-entity -a claude-code

2Manually: put the files in place

~/.claude/skills/tavily-entity/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/tavily-entity/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about tavily-entity

How to install tavily-entity in Claude Code?

Run npx skills add tavily-ai/skills --skill tavily-entity -a claude-code. The setup saves instructions into ~/.claude/skills/tavily-entity/SKILL.md.

What does tavily-entity require to run?

It relies on access to Bash tool execution and the installed tvly CLI utility connected to Tavily search.

How does tavily-entity handle identical names?

It verifies candidates against at least two identifiers, such as a company domain or verified employer, and halts with candidate options if ambiguity remains.

Source text

SKILL.md · MIT
---
name: tavily-entity
description: |
  Fill in a company, person, or organization for a CRM from the web, using Tavily, including a CSV of rows the user already has. Identifies the right entity when others share the name, then fills the fields from authoritative sources. Use when the user wants to enrich an account, a spreadsheet, or a pasted list of known names, or says "enrich", "CRM", or "who is". For discovering matches use tavily-list. For a deep comprehensive report use tavily-research.
allowed-tools: Bash(tvly *)
---

# Tavily entity

Resolve one entity and return a CRM record. The name is not the identity.
Confirm which entity it is, then fill the record from authoritative sources.
Every value comes from a page you read. An empty field stays empty.

Search and extract as `tavily-search` describes; load it only if it isn't
loaded yet. To discover new matches use `tavily-list`; for a deep report use
`tavily-research`.

## Identify the entity first

People and companies share names. A record that mixes two of them is worse
than an empty one. Isolate a single entity before you fill any field.

1. Take the type (company, person, or organization) and every identifier the
   user already gave: a domain, a city, an employer, a title, a product.
2. Search the name and look for other entities that use it. A common name, a
   name that is also a product or a place, or a person with a common name is a
   collision until you prove otherwise.
3. You have the right entity only when two identifiers agree. For a company,
   the name plus its own domain. For a person, the name plus an employer, a
   location, or a profile they control, and the organization on that profile
   has to match. One page that mentions the name is not identification.
4. If more than one entity still fits, stop and return the candidates. Do not
   pick the one with more results, and do not copy a field from one candidate
   onto another.
5. Put a stable identifier, the domain or the employer, into every later
   search, not the bare name.

## Read authoritative sources

Fill a field from the page that owns the fact. Extract that page. A snippet is
not enough for a number.

- The entity's own site, an official profile, and a filing or registry come
  first for facts the entity publishes: what it is, where it is, who leads it,
  what it sells. For a person, the employer's team page or a profile the person
  controls comes before a people-search site.
- A directory, a data broker, or a roundup is a lead to that page. Use it as
  the source of a field only when no authoritative page states the fact, and
  say so in the source note.
- When two authoritative pages disagree on a number, keep the more direct one
  and record the other in the source note. Do not average them.
- Include a published email or phone number only when a page shows it.

Extract the pages that own the fields you need in one call. Search for recent
news, with the domain or employer in the query, only when the user wants recent
signals or a full record.

## A CSV of known rows

When the user already has the entities, in a file or a pasted table, enrich
those rows. Do not go looking for new names.

1. Read the rows and count them. Use the fields they named. If they did not
   name fields, ask once, then use the same fields on every row.
2. Above 25 rows, tell them the count and the fields and wait for a go-ahead.
3. For each row, follow Identify the entity first and Read authoritative
   sources. A row you cannot isolate stays unresolved: blank new fields, a note
   on what collided, and no guessed values.
4. Write the original columns plus the new fields, a source for each new
   field, and a status of `filled` or `unresolved` to
   `{name}-enriched-{YYYY-MM-DD}.csv`. Use a CSV writer.

The CSV is the result. In the reply, give the number filled, the number
unresolved, and the path. Do not paste a record per row.

## Output

When the user asked specific questions, answer those in the reply, with a source
for each value, and skip the template. For a full record, use this:

```markdown
# {Name}

type: company | person | organization
identified by: {domain, employer, or other stable identifier}
as_of: {YYYY-MM-DD}

| Field | Value | Source |
|---|---|---|
| website | | |
| description | | |
| industry | | |
| headquarters | | |
| founded | | |
| employees | | |
| funding | | |
| revenue | | |
| linkedin | | |

## People
| Name | Title | Source |
|---|---|---|

## Recent signals
- {YYYY-MM-DD}: {fact} — {url}

## Unknown
- {field}: {what you tried}
```

For a person, the field rows are title, organization, location, and profile URL,
and People appears only when the user asked for related people. Drop a field
row that does not apply to this type. A field that applies and could not be
filled stays in the table with a blank value and a line under Unknown.
Description is one or two sentences grounded in the about page or profile.
Recent signals are at most five dated items: funding, a launch, a leadership
change, hiring. Omit a section that has no rows.

When you cannot pick one entity:

```markdown
# {Query}

| Name | Website | What separates it from the others |
|---|---|---|
```

© tavily-ai · MIT · tavily-ai/skills

Similar skills

All skills for Data and databases →

From the same set13

The whole set →
tavily-best-practices The tavily-best-practices skill gives an agent guidance for Tavily web search, content extraction, site crawling, and research. Use it when adding current web data to an agent workflow or RAG system. CX Codex +1 21,100installs tavily-extract tavily-extract extracts clean text or Markdown from specified pages with Tavily CLI. Use it for JavaScript-rendered content or query-focused page chunks. CX Codex +1 18,600installs tavily-crawl tavily-crawl is a Claude Code skill that crawls websites and extracts documentation as Markdown files or focused text chunks for an agent. CX Codex +1 17,900installs tavily-map tavily-map — a skill that has the agent walk a site and hand back the list of addresses, leaving page text alone. Useful when you know the domain but not the page. CX Codex +1 17,600installs tavily-dynamic-search tavily-dynamic-search is a Claude Code skill that saves raw Tavily search results to disk and filters excerpts before they enter the model context, especially for full-page extraction or multiple queries. CX Codex +1 13,900installs tavily-list The tavily-list Claude Code skill builds a deduplicated table of search matches for a set. Before searching, it asks for the inclusion rule, columns, and row cap. CX Codex +1 2,500installs tavily-monitor The tavily-monitor Claude Code skill sets up recurring searches or page checks and stores a baseline. The agent uses it to track new search results or changes to known pages over time. CX Codex +1 2,400installs tavily A set of skills for web search, content extraction, site crawling and deep research, powered by the Tavily CLI. ★ 497repo stars

Project sponsors

Companies that keep this analytics open