Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Progressive four-tier URL content scraping with automatic fallback strategy. USE WHEN user says "scrape this URL", "fetch this page", "get content from", "can't access this site", "use Bright Data", "pull content from URL", or needs to retrieve web content that may have bot detection or access restrictions.
.claude/skills/microck-brightdata/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 21% | 0% |
CRITICAL: This workflow implements progressive escalation for URL content retrieval.
When user requests scraping/fetching URL content: Examples: "scrape this URL", "fetch this page", "get content from URL]", "pull content from this site", "retrieve URL]", "can't access this site", "this site is blocking me", "use Bright Data to fetch" → READ: ${PAI_DIR}/skills/brightdata/workflows/four-tier-scrape.md → EXECUTE: Four-tier progressive scraping workflow (WebFetch → Curl → Browser Automation → Bright Data MCP)
Progressive Escalation Strategy:
Key Features:
four-tier-scrape.md - Complete URL content scraping with four-tier fallback strategy
Integration Points:
mcp__Brightdata__scrape_as_markdown for advanced scrapingWhen Each Tier Is Used:
Configuration: No configuration required - all tools are available by default in Claude Code
Example 1: Simple Public Website
User: "Scrape https://example.com"
Skill Response:
Example 2: Site with JavaScript Requirements
User: "Can't access this site https://dynamic-site.com"
Skill Response:
Example 3: Site with Advanced Bot Detection
User: "Scrape https://protected-site.com"
Skill Response:
Example 4: Explicit Bright Data Request
User: "Use Bright Data to fetch https://difficult-site.com"
Skill Response:
Related Documentation:
${PAI_DIR}/skills/CORE/SKILL-STRUCTURE-AND-ROUTING.md - Canonical structure guide${PAI_DIR}/skills/CORE/CONSTITUTION.md - Overall Kai philosophyLast Updated: 2025-11-23
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-17 | fail→fail | 9,568 | 8,741 | -9% | 1 | 1 | 0% | 1,660 | 2,043 | +23% | 0 | 0 | — |
case-01 | fail→fail | 2,417 | 6,663 | +176% | 1 | 1 | 0% | 371 | 1,817 | +390% | 0 | 0 | — |
case-02 | fail→fail | 6,182 | 7,243 | +17% | 1 | 1 | 0% | 946 | 1,788 | +89% | 0 | 0 | — |
case-03 | fail→fail | 3,249 | 6,067 | +87% | 1 | 1 | 0% | 471 | 1,859 | +295% | 0 | 0 | — |
case-04 | fail→fail | 10,726 | 18,983 | +77% | 1 | 1 | 0% | 712 | 3,285 | +361% | 0 | 0 | — |
case-18 | fail→fail | 48,743 | 7,063 | -86% | 1 | 1 | 0% | 1,544 | 1,863 | +21% | 0 | 0 | — |
case-05 | pass→pass | 10,749 | 4,797 | -55% | 1 | 1 | 0% | 1,761 | 2,126 | +21% | 0 | 0 | — |
case-06 | pass→pass | 14,941 | 6,653 | -55% | 1 | 1 | 0% | 2,651 | 2,697 | +2% | 0 | 0 | — |
case-07 | fail→pass | 11,012 | 2,510 | -77% | 1 | 1 | 0% | 1,922 | 1,810 | -6% | 0 | 0 | — |
case-08 | fail→pass | 11,752 | 5,988 | -49% | 1 | 1 | 0% | 1,885 | 2,303 | +22% | 0 | 0 | — |
case-09 | fail→pass | 9,883 | 2,596 | -74% | 1 | 1 | 0% | 1,635 | 1,769 | +8% | 0 | 0 | — |
case-10 | pass→pass | 4,753 | 2,837 | -40% | 1 | 1 | 0% | 675 | 1,770 | +162% | 0 | 0 | — |
case-11 | pass→pass | 5,185 | 4,174 | -19% | 1 | 1 | 0% | 926 | 2,114 | +128% | 0 | 0 | — |
case-12 | pass→pass | 7,953 | 5,331 | -33% | 1 | 1 | 0% | 1,296 | 2,271 | +75% | 0 | 0 | — |
case-13 | pass→pass | 6,020 | 5,348 | -11% | 1 | 1 | 0% | 1,208 | 2,149 | +78% | 0 | 0 | — |
case-14 | fail→fail | 11,656 | 2,178 | -81% | 1 | 1 | 0% | 1,911 | 1,684 | -12% | 0 | 0 | — |
case-15 | pass→pass | 9,811 | 10,716 | +9% | 1 | 1 | 0% | 1,987 | 3,326 | +67% | 0 | 0 | — |
case-16 | fail→fail | 5,217 | 4,464 | -14% | 1 | 1 | 0% | 828 | 1,593 | +92% | 0 | 0 | — |
case-19 | fail→fail | 8,914 | 2,519 | -72% | 1 | 1 | 0% | 1,357 | 1,725 | +27% | 0 | 0 | — |
case-20 | pass→pass | 13,606 | 8,872 | -35% | 1 | 1 | 0% | 2,071 | 2,775 | +34% | 0 | 0 | — |
case-21 | fail→pass | 8,772 | 3,234 | -63% | 1 | 1 | 0% | 1,375 | 1,858 | +35% | 0 | 0 | — |
case-22 | pass→pass | 5,751 | 1,810 | -69% | 1 | 1 | 0% | 850 | 1,652 | +94% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 17 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +18 percentage points is the difference between those two pass rates over the 17 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.