Traffic Analyzer

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 2515ce9634da · 15 Oct 2026Report an issue or request a re-scan

• PublisherAffitor GitHub organizationOwner of the repository this skill is read from
• Source folderAffitor/affiliate-skills/skills/research/traffic-analyzerThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict2515ce9634daA new audit runs when the source changes
• Repository statusNot archivedLast push 2 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Analyze website traffic, global rank, engagement metrics, and traffic sources for any domain. Use this skill to evaluate affiliate program websites, compare competitor traffic, assess advertiser strength, or understand…

---
name: traffic-analyzer
description: >
  Analyze website traffic, global rank, engagement metrics, and traffic sources for any domain.
  Use this skill to evaluate affiliate program websites, compare competitor traffic,
  assess advertiser strength, or understand where an audience comes from. Triggers on:
  "analyze traffic for [domain]", "how much traffic does [site] get", "compare traffic
  between [site A] and [site B]", "is [program] worth promoting based on traffic",
  "traffic analysis", "website analytics for [domain]", "where does [site] get traffic",
  "check if [advertiser] is legit", "evaluate [program] website health", "SimilarWeb
  analysis", "traffic sources for [domain]", "how popular is [site]", "website rank",
  "domain authority check", "compare affiliate program websites".
license: MIT
version: "1.0.0"
tags: ["affiliate-marketing", "research", "traffic", "analytics", "competitor-analysis", "advertiser-evaluation"]
compatibility: "Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent"
metadata:
  author: affitor
  version: "1.0"
  stage: S1-Research
---

# Traffic Analyzer

Analyze website traffic, engagement, and traffic sources for any domain. Goes beyond
raw data — scores the domain, interprets what the traffic patterns mean for affiliate
promotion, and recommends whether the program is worth your time.

A tool returns numbers. This skill returns a verdict.

**Use cases:**
- Is this affiliate program's website healthy? (High traffic = more brand awareness = easier conversions)
- Where does a competitor get their traffic? (Find channels they're ignoring)
- Compare 2-3 affiliate programs by advertiser website strength
- Validate a niche by checking traffic to the top programs in it

## Stage

This skill belongs to Stage S1: Research

## When to Use

- Before committing to promote an affiliate program — check if the advertiser is legit
- When comparing multiple programs — traffic is a proxy for brand strength
- When `competitor-spy` identifies competitor sites — analyze their traffic sources
- When evaluating a niche — check if the top programs have healthy traffic
- When an advertiser claims "millions of users" — verify with data

## Input Schema

```yaml
domains: string[]             # (required) 1-5 domains to analyze — "heygen.com", "synthesia.io"
compare: boolean              # (optional, default: true if 2+ domains) Side-by-side comparison
focus: string                 # (optional, default: "affiliate") 
                              # "affiliate" — score from promoter perspective
                              # "competitor" — analyze as a competitor site
                              # "advertiser" — evaluate advertiser health
```

## Workflow

### Step 1: Gather Traffic Data

**With SimilarWeb API (see `shared/references/social-data-providers.md`):**

If `social_data_config.similarweb` is configured:
- Call SimilarWeb API for each domain
- Returns: global rank, country rank, visits, pages/visit, avg duration, bounce rate, traffic sources

**Without API (web_search fallback):**

For each domain:
1. `web_search "[domain] traffic similarweb"` → often shows rank and visit estimates in snippets
2. `web_search "[domain] site traffic statistics"` → third-party reports
3. `web_search "site:[domain]"` → Google index count as proxy for content depth
4. `web_search "[domain] alexa rank"` OR `"[domain] semrush traffic"` → alternative sources
5. `web_fetch "https://www.similarweb.com/website/[domain]/"` → extract visible data from SimilarWeb free page (may be limited)

Note: web_search data is approximate. SimilarWeb API provides exact metrics.

### Step 2: Analyze Core Metrics

For each domain, analyze and interpret:

**Traffic Volume:**
```yaml
global_rank: number            # Lower = better. <10K = major site, <100K = solid, <1M = niche
country_rank: number           # Rank in primary country
monthly_visits: string         # "1.2M", "350K", "45K"
visits_trend: string           # "growing" | "stable" | "declining" (if historical data available)
```

**Engagement Quality:**
```yaml
pages_per_visit: number        # >3 = good engagement, <2 = bouncy
avg_visit_duration: string     # ">3 min" = engaged, "<1 min" = low quality
bounce_rate: number            # <40% = excellent, 40-60% = normal, >60% = concerning
```

**Traffic Sources Breakdown:**
```yaml
direct: number                 # % — brand strength indicator
search: number                 # % — SEO strength
social: number                 # % — social media presence
referral: number               # % — partnership/affiliate ecosystem
paid: number                   # % — ad spend (high paid = advertiser invests in acquisition)
```

### Step 3: Interpret for Use Case

**For affiliate promoters (`focus: "affiliate"`):**

Score the domain as an affiliate promotion target:

| Signal | Good (8-10) | OK (5-7) | Red Flag (1-4) |
|--------|-------------|----------|-----------------|
| Monthly visits | >500K | 50K-500K | <50K |
| Bounce rate | <40% | 40-60% | >70% |
| Search traffic | >30% | 15-30% | <10% (overly dependent on ads) |
| Brand (direct) | >30% | 15-30% | <10% (nobody knows them) |
| Pages/visit | >4 | 2-4 | <2 |

**Why this matters for affiliates:**
- High traffic = people already search for this brand → easier to convert your referrals
- Strong brand (high direct traffic) = trust → higher conversion rate
- Good engagement = product delivers value → lower refund rate → your commissions stick
- Healthy search traffic = sustainable business → long-term commission potential
- High paid traffic = advertiser invests in growth → good sign for program longevity

**For competitor analysis (`focus: "competitor"`):**

- Identify their strongest traffic channel → where are they winning?
- Find their weakest channel → opportunity for you
- Compare bounce rate → are they retaining visitors better than you?
- Check referral traffic → which sites link to them? (potential partnership targets)

**For advertiser e

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-15
   ✓SAFE B 89 / 100

   first audit · source 2515ce9634da

Questions about Traffic Analyzer

• github.com/Affitor/affiliate-skills/tree/main/skills/research/tr — the audited source at commit 2515ce9634da and every finding aboveObserved · 15 Oct 2026

Spotted something wrong? Report a correction · Methodology