crawl-round

Execute a single crawl round by loading its TypeScript definition and writing the output delta.

1|1|Updated Mar 27, 2026
One-click install
npx skills add https://github.com/jadecli/researchers --skill crawl-round
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: crawl-round
Source: https://github.com/jadecli/researchers/tree/main/claude-multi-agent-dispatch/.claude/skills/crawl-round
Command: npx skills add https://github.com/jadecli/researchers --skill crawl-round

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Executes a single crawl round by loading the round-{N}.ts definition and validating prerequisites. Inject accumulated context deltas, execute extraction tasks, score quality against a threshold, and write the resulting delta to rounds/{N}/.

Core Features & Use Cases

  • Deterministic per-round execution by loading src/rounds/round-{N}.ts and applying context deltas.
  • Quality scoring and delta generation to produce an output written to rounds/{N}/.
  • Supports integration within large crawl workflows to isolate and verify individual rounds before proceeding.

Quick Start

Specify the round number to execute that crawl round and generate its output delta.

Frequently Asked Questions about crawl-round

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute a single round in a multi-round web scraping workflow?

To execute a single crawl round, you specify the round number to load the round-{N}.ts definition, validate prerequisites, and run extraction tasks to generate the output delta.

How does context delta injection work during automated data extraction?

Context delta injection works by accumulating data from previous cycles and applying it to the current crawl round, ensuring that subsequent extraction tasks build upon prior context for accurate data extraction.

What is deterministic per-round processing for web crawling?

Deterministic per-round processing isolates individual crawl cycles by loading specific round definitions and scoring quality against a threshold, ensuring verifiable and isolated extraction before proceeding to the next round.

Can I validate crawl quality before moving to the next scraping round?

Yes, you can validate crawl quality because the execution process includes scoring the extraction results against a predefined quality threshold before writing the resulting delta to the rounds directory.

Do I need a specific round definition file to run a crawl round?

Yes, you need a round-{N}.ts definition file present in the src/rounds/ directory, as the execution process requires loading this file to validate prerequisites and apply context deltas for that specific round.