agentsclimarketplace

Competitor

Skill josezuma/ai-visibility-geo-toolkit/.claude/skills/competitor

Competitor GEO tracking — monitors a list of competitors, scores their GEO readiness weekly, reports who improved or declined.From its SKILL.md

Install
npx -y skills add josezuma/ai-visibility-geo-toolkit --skill competitor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.4 KB, 568 tokens by cl100k_base, as published. Nobody here has run it

Competitor GEO Watch

Tracks how your competitors' AI-search visibility changes over time. Get weekly delta reports showing who improved, who declined, and what they changed.

Quick Start

# Watch competitors from a CSV
ai-visibility-geo-toolkit watch competitors.csv

# CSV format:
# name,url
# BrandVirality,https://brandvirality.com
# CompetitorA,https://competitor-a.com

# JSON report
ai-visibility-geo-toolkit watch competitors.csv --json

Agent Instructions (manual mode)

1. Build Competitor List

Take a list of competitor names and URLs. If the user doesn't provide one, identify 3-5 key competitors for their niche.

2. Score Each Competitor

For each competitor URL, perform a quick GEO readiness check using the audit instructions:

  • llms.txt: does /.well-known/llms.txt exist? (20 pts)
  • Schema: JSON-LD with high-value types like Article, FAQPage? (25 pts)
  • EEAT: named author, publish dates, external refs? (25 pts)
  • Content depth: 1000+ words, statistics, heading structure? (15 pts)
  • AI Crawler Access: GPTBot, ClaudeBot allowed in robots.txt? (15 pts)

3. Compare with Previous Results

If this is not the first run, compare current scores with stored history (check for data/history.json in the repo).

4. Generate Delta Report

## Competitor GEO Watch — Week 28, 2026

### 📈 Improved
| Competitor | Before | After | Change | What Changed |
|-----------|:------:|:-----:|:------:|-------------|
| CompetitorA | 45 | 62 | +17 | Added llms.txt, improved schema |
| CompetitorB | 32 | 48 | +16 | Added FAQPage schema |

### 📉 Declined
| Competitor | Before | After | Change | What Changed |
|-----------|:------:|:-----:|:------:|-------------|
| CompetitorC | 78 | 72 | -6 | Removed FAQ schema |

### Unchanged
- BrandVirality: 45/100
- CompetitorD: 38/100

5. Store Results

Save current scores to data/history.json with the week number for next comparison.

Related

  • geo-max/audit — Full GEO audit for individual URLs
  • geo-max/monitor — Continuous monitoring with alerts
  • geo-max/report — Analytics and trend reports

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,645. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.