Skill

analyze-url

npx claudepluginhub roxabi/roxabi-plugins --plugin web-intel

Tool Access

This skill is limited to using the following tools:

BashRead

Preview

Scrape URL → deep technical and strategic analysis.

SKILL.md

Similar Skills

compete

Compares your production site to a competitor's URL, benchmarking performance, tech stack, SEO, security, and providing strategic analysis on moats, positioning gaps, and advantages.

4 tools

ultraship

product-teardown

Analyzes products' strategy, UX decisions, business model, and growth loops in structured teardowns. Useful for understanding how and why products work.

4 tools

claude-code-pm-skills

skill-content-pipeline

3.3k

Extracts structural, psychological, and mechanical patterns from up to 5 URLs via multi-stage pipeline to synthesize anatomy guides and recreation interview questions.

1 file

octo

Stats

Parent Repo Stars6

Parent Repo Forks1

Last CommitApr 2, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Analyze URL

Scrape URL → deep technical and strategic analysis.

Entry

/analyze-url https://example.com

¬U → → DP(B)to get one.

Step 1 — Locate Plugin

PLUGIN_ROOT=$(find ~/projects -maxdepth 4 -path "*/web-intel/pyproject.toml" -print -quit 2>/dev/null | xargs dirname)
if [ -z "$PLUGIN_ROOT" ]; then
  echo "ERROR: web-intel plugin not found. Install: claude plugin install web-intel"
  exit 1
fi

First Use

First invocation in session only:

cd "$PLUGIN_ROOT" && uv run python scripts/doctor.py

exit 1 → show output, stop, guide install. Optional warnings → inform user, continue.
Skip on subsequent invocations.

Step 2 — Scrape

cd "$PLUGIN_ROOT" && SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt REQUESTS_CA_BUNDLE=/etc/ssl/certs/ca-certificates.crt uv run python scripts/scraper.py "$URL"

Step 3 — Deep Analysis

SaaS / Product URLs

Product overview — what, audience, value prop
Tech stack signals — frameworks, infra, CDN, visible APIs
Architecture patterns — SPA vs SSR, API-first, microservices signals
Business model — pricing, freemium, enterprise, self-serve
Competitive positioning — market category, differentiation, moat
Growth signals — community size, hiring, funding, integrations
Strengths (3-5 bullets) | Weaknesses (3-5 bullets)

GitHub Repos

Project health — stars, forks, recent activity, contributor count
Architecture — language, framework, project structure
Code quality signals — CI/CD, tests, linting, type safety
Documentation — README quality, docs site, examples
Community — issues, PRs, discussions activity
Notable patterns worth adopting

YouTube Videos

Run full video analysis pipeline:

cd "$PLUGIN_ROOT" && SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt uv run python scripts/video_analyzer.py "$URL" --output /tmp/video_analysis.json

Pipeline: scrape metadata + transcript → download video (yt-dlp, 1080p max) → extract frames at 1fps (ffmpeg) → auto-detect best local VLM by GPU VRAM (qwen3-vl via Ollama) → batch-describe frames → output JSON.

Read /tmp/video_analysis.json → analyze:

Video overview — title, channel, duration, views, engagement rate
Content analysis — thesis, structure, rhetorical techniques (from transcript)
Visual analysis — techniques (3D/2D/photography), palette, composition, transitions (from frames)
Production quality — animation, visual variety, text/typography, pacing
Scene breakdown — visual timeline mapped to narration
Strengths (3-5) | Weaknesses (3-5)

video_analyzer fails (¬GPU ∨ ¬Ollama) → fall back to transcript-only via standard scraper.

Articles / Content

Thesis — main argument or claim
Evidence quality — data, sources, methodology
Implications — what this means for the field
Counter-arguments — what the author missed
Actionable insights

Step 4 — Present

Output structured markdown with clear headers. Include confidence (high|medium|low) for inferred info. success: false → fall back to WebFetch.

$ARGUMENTS