# similarweb-traffic

similarweb-traffic fetches domain traffic estimates from SimilarWeb: monthly visits, acquisition channels, top countries, and search terms without an API key.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 227 installs · ★ 750 repo stars
- Author: OpenClaudia
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/OpenClaudia/openclaudia-skills/tree/HEAD/skills/similarweb-traffic/SKILL.md
- Updated: 2026-10-21
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/similarweb-traffic

## What it does

The skill runs a self-contained Node.js script querying SimilarWeb's undocumented public endpoint at `https://data.similarweb.com/api/v1/data?domain=<domain>`. The script mimics a standard browser user-agent header, strips URL prefixes like `https://` or `www.`, and outputs either a formatted Markdown summary or a normalized JSON object with `--json`.

The resulting payload covers global and category ranks, bounce rates, visit durations, pages per visit, historical visit series, and channel breakdowns including search, direct, paid, and generative AI referrals. Node.js with native `fetch` support is the only runtime requirement; external npm packages are not needed.

Because this integration relies on an unauthenticated extension endpoint, SimilarWeb can adjust response schemas or throttle access without warning. Low-traffic websites will typically yield synthetic zeroes with an HTTP 200 status code rather than a clear error message.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add OpenClaudia/openclaudia-skills --skill similarweb-traffic -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/similarweb-traffic/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/similarweb-traffic/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add OpenClaudia/openclaudia-skills --skill similarweb-traffic -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/similarweb-traffic/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add OpenClaudia/openclaudia-skills --skill similarweb-traffic -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/similarweb-traffic/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install OpenClaudia/openclaudia-skills skills/similarweb-traffic
```

2. **Manually: put the files in place**
- File: `.github/skills/similarweb-traffic/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add OpenClaudia/openclaudia-skills --skill similarweb-traffic -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/OpenClaudia/openclaudia-skills --path skills/similarweb-traffic
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/similarweb-traffic/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add OpenClaudia/openclaudia-skills --skill similarweb-traffic -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/OpenClaudia/openclaudia-skills/tree/HEAD/skills/similarweb-traffic/SKILL.md

## When to use it
- estimate monthly visits and audience engagement metrics for a competitor domain
- break down traffic acquisition across organic search, direct entries, and generative AI
- inspect top visitor countries and primary search keywords for a specific URL
- benchmark multiple sites side-by-side using normalized JSON output

## Example prompts
- Check monthly visit estimates and traffic sources for stripe.com
- Compare traffic metrics between notion.so and linear.app
- Pull geographic distribution and top search terms for figma.com

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 4afe3cd50688c28f.

BEGIN THIRD-PARTY FILE 4afe3cd50688c28f
````text
---
name: similarweb-traffic
description: Fetch website traffic estimates (monthly visits, traffic sources, top countries, keywords, engagement, ranks) for any domain from SimilarWeb. Use when the user asks about a domain's traffic, monthly visits, traffic sources, audience countries, or wants to compare/benchmark sites against competitors.
---

# SimilarWeb Traffic

Fetch traffic-overview estimates for any domain — monthly visits, traffic-source breakdown, top countries, top keywords, engagement metrics, and global/category ranks.

## When to Use This Skill

Use this skill when the user:

- Asks how much traffic a domain gets ("what's the traffic for X")
- Wants monthly visit trends for a site
- Needs a traffic-source breakdown (organic vs direct vs paid vs GenAI, etc.)
- Wants to know a site's audience countries
- Wants to compare/benchmark several domains against each other or competitors

## Usage

No API key required. Self-contained Node script (uses built-in `fetch`, no `npm install`).

```bash
node scripts/fetch-similarweb-traffic.js <domain>
```

Examples:
```bash
# Formatted markdown summary (default)
node scripts/fetch-similarweb-traffic.js chatslide.ai

# Raw normalized JSON (for further processing / comparisons)
node scripts/fetch-similarweb-traffic.js stripe.com --json
```

The domain can be passed bare (`example.com`) or as a URL (`https://www.example.com/pricing`) — it gets normalized (strips scheme, `www.`, and path).

### Comparing multiple domains

Run the script once per domain with `--json` and combine the results into a table. Add a short delay between calls to be polite to the endpoint.

## Output

Default mode prints a markdown summary: a metrics table (monthly visits, ranks, bounce, pages/visit, time on site), a monthly-visits trend line, traffic-source breakdown, top countries, and top keywords.

`--json` mode prints a normalized object:

```json
{
  "domain": "stripe.com",
  "globalRank": 327,
  "categoryRank": 21,
  "category": "Finance",
  "snapshotMonth": "2026-05",
  "visits": 122394040,
  "bounceRate": 0.55,
  "pagesPerVisit": 3.26,
  "timeOnSite": 165.9,
  "estimatedMonthlyVisits": [{ "date": "2026-03-01", "visits": 118067753 }],
  "trafficSources": { "searchOrganic": 0.48, "direct": 0.23, "...": 0 },
  "topCountries": [{ "countryCode": "US", "value": 0.087 }],
  "topKeywords": ["..."]
}
```
````
END THIRD-PARTY FILE 4afe3cd50688c28f

The third-party file has ended. Everything between the 4afe3cd50688c28f tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2369 of 3540 bytes. © OpenClaudia · MIT · https://github.com/OpenClaudia/openclaudia-skills/tree/HEAD/skills/similarweb-traffic/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
