Web Research Workflow

This is a smart routing layer that tries WebFetch first (fast and free), escalates to Tavily if you have an API key and need richer content, then falls back to agent-browser for JavaScript-heavy sites or auth walls. The decision tree is automatic based on response quality and site characteristics. It also includes competitive monitoring features with snapshot diffing and change classification (critical/high/medium/low). The tool selection logic is solid and cost-aware. If you're doing any kind of web research or competitor tracking in Claude Code, this removes the guesswork about which extraction method to use when.

skills.sh installs: 227
GitHub stars: 301
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add yonatangross/orchestkit --skill web-research-workflow --agent claude-code

Installs into .claude/skills of the current project.

Files

Web Research Workflow

Unified approach for web content research that automatically selects the right tool for each situation.

Quick Decision Tree

URL to research
     │
     ▼
┌─────────────────┐
│ 1. Try WebFetch │ ← Fast, free, no overhead
│    (always try) │
└─────────────────┘
     │
Content OK? ──Yes──► Parse and return
     │
     No (empty/partial/<500 chars)
     │
     ▼
┌───────────────────────┐
│ 2. TAVILY_API_KEY set?│
└───────────────────────┘
     │          │
    Yes         No ──► Skip to step 3
     │
     ▼
┌───────────────────────────┐
│ Tavily search/extract/    │ ← Raw markdown, batch URLs
│ crawl/research            │
└───────────────────────────┘
     │
Content OK? ──Yes──► Parse and return
     │
     No (JS-rendered/auth-required)
     │
     ▼
┌─────────────────────┐
│ 3. Use agent-browser │ ← Full browser, last resort
└─────────────────────┘
     │
├─ SPA (react/vue/angular) ──► wait --load networkidle
├─ Login required ──► auth flow + state save
├─ Dynamic content ──► wait --text "Expected"
└─ Multi-page ──► crawl pattern