evidence-crawl

Consolidate evidence from R2, Qdrant, and web crawling for narrative construction.

Updated Nov 3, 2025

Search Tags:#semantic search #web crawling #evidence consolidation #narrative construction #database retrieval

Ready to run

npx skills add https://github.com/ethicalcapital/skills --skill evidence-crawl

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: evidence-crawl
Source: https://github.com/ethicalcapital/skills/tree/main/evidence-crawl
Command: npx skills add https://github.com/ethicalcapital/skills --skill evidence-crawl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires monocloud_storage, qdrant_client, monocloud_search, httpx, os, monocloud_research, json, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the process of gathering and consolidating evidence for creating narrative details, ensuring a comprehensive and reliable source material collection.

Core Features & Use Cases

Local Evidence Consolidation: Integrates evidence from R2 and Qdrant for quick narrative construction.
Semantic Search: Utilizes Qdrant for semantic search over all crawled evidence.
Database Evidence: Leverages database records for context-rich narratives.
Flagging Gaps: Automatically flags missing evidence without speculation.
Crawling and Storing: Handles crawling new URLs or pages as requested.

Quick Start

Execute the evidence-crawl skill with the 'crawl-evidence' command to initiate the evidence consolidation process.

Frequently Asked Questions about evidence-crawl

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

FAQPage Schema

How do I consolidate evidence from multiple sources for narrative construction?▼

To consolidate evidence for narrative construction, this Skill integrates records from local R2 archives and Qdrant semantic search results into a unified collection. It automatically extracts available context and flags any missing information.

How does semantic search work over crawled web evidence?▼

Semantic search over crawled evidence is powered by Qdrant, allowing you to query stored web pages and database records by meaning rather than exact keywords. This retrieves contextually relevant material for reliable narratives.

Do I need R2 and Qdrant APIs to use evidence crawling and retrieval?▼

Yes, you need access to R2, Qdrant, and web crawling APIs to retrieve evidence. These dependencies are required to connect to storage layers, execute semantic search, and fetch new pages for consolidation.

What is the best way to flag missing information during evidence collection?▼

The best way to flag missing information during evidence collection is to let the process automatically identify gaps without speculating. This Skill checks R2 and Qdrant records, explicitly marking absent data for review.

Can I crawl new URLs and store them in an existing evidence archive?▼

Yes, you can crawl new URLs and store them in your existing evidence archive. The Skill handles web crawling requests via HTTPX and consolidates extracted page data directly into R2 storage for semantic search.