Scrape Strategy

Purpose

Use this skill when the bottleneck is site access rather than report writing. Focus on deciding whether to stay in scrape-capable modes or pivot to external research.

Workflow

1. Read primr://research/modes to compare scrape, deep, full, and premium behavior.
2. Review current run state through primr://research/status or check_jobs.
3. Use references/tiers.md only when you need tier-level scraping context.
4. Recommend the smallest viable change: retry, change mode, or accept partial coverage.

Decision Rules

• Prefer deep when the target site is heavily protected or first-party signal is sparse.
• Stay with scrape or full when first-party pages are the core evidence source.
• Do not promise exact success percentages unless the run data already shows them.
• Escalate from site troubleshooting to mode selection quickly; avoid over-explaining scrape internals unless the user asks.

Example

User: The site seems blocked

1. Read primr://research/status
2. Read primr://research/modes
3. Explain whether deep mode is the better fit
4. If needed, estimate_run(company_url="https://example.com", mode="deep")