Competitor Spy

Analyze a website or business to extract tech stack, pricing, features, SEO data, social proof, and generate a competitive intelligence report.

Security Scan

The skill's instructions, requirements, and behavior are coherent with a competitive-intelligence web-scraping tool and do not request unrelated credentials or installs.

Purpose & Capability

Name and description match the instructions: fetching public pages, extracting tech, pricing, SEO, and producing reports. No unrelated binaries, env vars, or installs are requested.

Instruction Scope

Runtime instructions are focused on public web scraping and analysis (web_fetch, web_search, Google cache, LinkedIn/Twitter, SimilarWeb). One noteworthy guidance suggests trying Google cache if scraping is blocked — this is a minor red flag because it explicitly recommends a means to bypass site blocks; otherwise instructions do not ask the agent to read local files, secrets, or unrelated system state.

Install Mechanism

Instruction-only skill with no install spec or packaged code. This minimizes on-disk risk — nothing is downloaded or installed by the skill itself.

Credentials

No environment variables, credentials, or config paths are requested, which is proportionate for a tool that analyzes public web pages. The skill does suggest consulting third-party services (SimilarWeb/Alexa) but does not request API keys.

Persistence & Privilege

always is false and the skill does not request system-wide changes or persistent presence. Default autonomous invocation is allowed (platform default) but not escalated.

Assessment

This skill appears internally consistent for public competitive research: it only instructs fetching public pages and synthesizing findings and doesn't ask for credentials or install anything. Things to consider before installing: (1) the SKILL.md suggests using Google cache to access pages that block scraping — that may violate some sites' terms of service or legal restrictions, so avoid using it against targets you don't have permission to analyze; (2) the source and owner are unknown and there's no homepage—if you need provenance, ask the publisher for more info; (3) if you plan to analyze sites behind logins or use paid third-party APIs (SimilarWeb, Alexa), those will require credentials that the skill does not request now — be cautious about supplying any secrets later; (4) consider keeping this skill user-invocable only (do not grant broad autonomous scopes) to prevent large-scale automated scraping. If the package later includes code, install steps, or requests credentials, re-evaluate as those would materially change the risk profile.

Analyze any website or business and extract competitive intelligence in seconds.

---

When to Use

Trigger when the user says:

• "spy on [website/domain]"
• "analyze competitor [name]"
• "competitor research [url]"
• "what are [competitor]'s tech stack"
• "reverse engineer [website]"

How It Works

1. User provides a domain, URL, or business name
2. Agent scrapes the target website
3. Extracts: tech stack, pricing, features, SEO keywords, content strategy, social proof
4. Generates a competitive intelligence report

Commands

Primary: Full Spy Report

User says: "spy on example.com"

Agent workflow:

1. Use web_fetch to grab the homepage
2. Use web_fetch on /pricing, /about, /features, /blog
3. Extract and analyze:
   • Tech Stack: Check for common frameworks (Next.js, React, WordPress, etc.), hosting (Vercel, Netlify, AWS), analytics (GA4, PostHog), fonts, CDNs
   • Pricing: Extract all pricing tiers, features per tier, free trial info
   • Features: Main product features, unique selling points
   • SEO: Meta tags, headings, schema markup, sitemap
   • Content Strategy: Blog topics, content frequency, tone
   • Social Proof: Testimonials, logos, case studies, review counts
   • Monetization: Revenue model (SaaS, freemium, ads, marketplace)
   • Weaknesses: Missing features, poor UX, slow pages, thin content
4. Output a structured markdown report

Secondary: Quick Tech Stack Check

User says: "tech stack of example.com"

Agent workflow:

1. Use web_fetch on the homepage
2. Look for framework signatures, CDN headers, meta generators
3. Output a compact tech stack summary

Tertiary: Pricing Comparison

User says: "compare pricing for example.com and competitor.com"

Agent workflow:

1. Fetch /pricing from both sites
2. Extract all tiers and features
3. Create side-by-side comparison table
4. Highlight gaps and opportunities

Report Format

# 🔍 Competitor Spy Report: [domain]

## 🏢 Business Overview
- **Name:** [extracted]
- **Tagline:** [extracted]
- **Industry:** [inferred]

## 🛠️ Tech Stack
| Layer | Technology |
|-------|-----------|
| Framework | [detected] |
| Hosting | [detected] |
| Analytics | [detected] |
| CDN | [detected] |
| Fonts | [detected] |

## 💰 Pricing
| Tier | Price | Key Features |
|------|-------|-------------|
| ... | ... | ... |

## ✅ Strengths
- ...

## ❌ Weaknesses & Opportunities
- ...

## 📈 SEO Score
| Metric | Value |
|--------|-------|
| Title tag | ... |
| Meta description | ... |
| H1 tag | ... |
| Schema markup | ... |
| Sitemap | ... |
| Robots.txt | ... |

## 💡 Recommendations
- ...

Tips

• If the site blocks scraping, try the Google cache version
• Check LinkedIn/Twitter for additional business info
• Use web_search to find reviews and mentions
• Cross-reference with SimilarWeb/Alexa if needed
• Always cite sources for claims

Limitations

• Cannot access paywalled content
• JavaScript-heavy SPAs may need browser automation
• Pricing pages behind login walls are inaccessible
• Results depend on site structure and accessibility