AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Scrape Strategy

skill-blisspixel-primr-scrape-strategy · by blisspixel

Guide mode selection when site scraping is weak, blocked, or low quality. Use when the user asks why scraping failed or how Primr should proceed on a protected site.

↗ Repository
— No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add skill-blisspixel-primr-scrape-strategy

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Scrape Strategy? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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")

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Web & Browser