agentleFS
TehseenTechTehseenTech/manus-skills/skills/analysis-skills/similarweb-analytics/SKILL.md

similarweb-analytics

Skill0 starsChanged 3 months agoMITView on GitHub

Analyze websites and domains using SimilarWeb traffic data. Get traffic metrics, engagement stats, global rankings, traffic sources, and geographic distribution for comprehensive website research. Apply automatically when the request matches; the user does not need to mention this skill.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the task-specific instructions in this file before acting.

    line 15
  2. Very specific:

    All APIs use ApiClient from /opt/.manus/.sandbox-runtime.

    line 33

≈ “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

Overview

Analyze websites and domains using SimilarWeb traffic data. Get traffic metrics, engagement stats, global rankings, traffic sources, and geographic distribution for comprehensive website research. Apply automatically when the request matches; the user does not need to mention this skill.

This skill should apply automatically when the request matches; the user does not need to mention this skill.

Workflow

  1. Read the task-specific instructions in this file before acting.
  2. Apply the documented constraints, resources, and verification steps.
  3. Confirm the result against the requested outcome before completion.

SimilarWeb Analytics

Comprehensive website and domain analysis using SimilarWeb traffic data.

Core Capabilities

  • Traffic Analysis: Total visits, unique visitors, traffic trends
  • Engagement Metrics: Bounce rate, pages per visit, average visit duration
  • Global Ranking: Website ranking over time
  • Traffic Sources: Marketing channels (desktop and mobile)
  • Geographic Distribution: Traffic breakdown by country

API Usage

All APIs use ApiClient from /opt/.manus/.sandbox-runtime. Common parameters:

  • domain: Website domain (e.g., "google.com")
  • start_date: Start date (YYYY-MM). Max 12 months ago
  • end_date: End date (YYYY-MM). Max 12 months ago, default is 1 month ago (most recent complete month)
  • main_domain_only: Exclude subdomains if True (default: False)

Default time ranges vary by API:

  • Global Rank, Visits Total, Unique Visit, Bounce Rate: default 6 months
  • Traffic Sources (Desktop/Mobile), Traffic by Country: default 3 months

Get Global Rank

import sys
sys.path.append('/opt/.manus/.sandbox-runtime')
from data_api import ApiClient

client = ApiClient()
result = client.call_api('SimilarWeb/get_global_rank', path_params={'domain': 'amazon.com'})

Get Website Visits Total

import sys
sys.path.append('/opt/.manus/.sandbox-runtime')
from data_api import ApiClient

client = ApiClient()
result = client.call_api('SimilarWeb/get_visits_total',
    path_params={'domain': 'amazon.com'},
    query={'country': 'world', 'granularity': 'monthly', 'start_date': '2025-07', 'end_date': '2025-12'})

Get Unique Visit

import sys
sys.path.append('/opt/.manus/.sandbox-runtime')
from data_api import ApiClient

client = ApiClient()
result = client.call_api('SimilarWeb/get_unique_visit',
    path_params={'domain': 'amazon.com'},
    query={'start_date': '2025-07', 'end_date': '2025-12'})

Get Bounce Rate

import sys
sys.path.append('/opt/.manus/.sandbox-runtime')
from data_api import ApiClient

client = ApiClient()
result = client.call_api('SimilarWeb/get_bounce_rate',
    path_params={'domain': 'amazon.com'},
    query={'country': 'world', 'granularity': 'monthly', 'start_date': '2025-07', 'end_date': '2025-12'})

Get Traffic Sources - Desktop

Returns breakdown by channel: Organic Search, Paid Search, Direct, Display Ads, Email, Referrals, Social Media.

import sys
sys.path.append('/opt/.manus/.sandbox-runtime')
from data_api import ApiClient

client = ApiClient()
result = client.call_api('SimilarWeb/get_traffic_sources_desktop',
    path_params={'domain': 'amazon.com'},
    query={'country': 'world', 'granularity': 'monthly', 'start_date': '2025-07', 'end_date': '2025-12'})

Get Traffic Sources - Mobile

import sys
sys.path.append('/opt/.manus/.sandbox-runtime')
from data_api import ApiClient

client = ApiClient()
result = client.call_api('SimilarWeb/get_traffic_sources_mobile',
    path_params={'domain': 'amazon.com'},
    query={'country': 'world', 'granularity': 'monthly', 'start_date': '2025-07', 'end_date': '2025-12'})

Get Total Traffic by Country

Returns traffic share, visits, pages per visit, average time, bounce rate and rank by country.

  • limit: Number of countries to return (default: 1, max: 10)
  • Date range limit: max 3 months (unlike other APIs)
import sys
sys.path.append('/opt/.manus/.sandbox-runtime')
from data_api import ApiClient

client = ApiClient()
result = client.call_api('SimilarWeb/get_total_traffic_by_country',
    path_params={'domain': 'amazon.com'},
    query={'start_date': '2025-10', 'end_date': '2025-12', 'limit': '10'})

When to Use

Invoke APIs when users mention:

  • Domain names: "google.com", "amazon.com"
  • Traffic queries: "traffic", "visits", "visitors"
  • Ranking queries: "rank", "ranking", "how popular"
  • Engagement queries: "bounce rate", "engagement"
  • Source queries: "traffic sources", "marketing channels"
  • Geographic queries: "countries", "geographic"
  • Comparison queries: "compare", "vs"

Data Limitations

  • Historical data: max 12 months
  • Geography: worldwide only
  • Granularity: monthly only
  • Latest data: last complete month

Important: Save Data to Files

API calls may fail mid-execution due to credit depletion. Always save all retrieved data to files immediately to avoid data loss and prevent redundant API calls.

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.