Full-page web reading for non-academic perspectives — blogs, tech reports, product pages, industry analysis. Spawns a subagent to read pages in isolated context. Hard constraint: at least 30 web pages read in full.
Scanned 6/1/2026
Install to Claude Code
Skills Directorynpx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill deep-web-search --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Deep Web Search?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/yogsoth-ai-deep-web-search)More formats (shields.io, HTML) on the badges page.
---
name: deep-web-search
description: Full-page web reading for non-academic perspectives — blogs, tech reports, product pages, industry analysis. Spawns a subagent to read pages in isolated context. Hard constraint: at least 30 web pages read in full.
execution: subagent
prompt: ./prompt.md
input: search_queries (string), field_context (string)
---
# Deep Web Search
Deep web reading for non-academic perspectives (blogs, tech reports, products, industry analysis).
## Execution
Subagent — spawned via `subagent-spawning/spawn-agent` skill. The subagent reads pages in its own context window, protecting the main session from context overflow.
## Hard Constraint
At least 30 web pages read in full before completing this SOP.
## Why Subagent (Not Import)
Reading 30+ full web pages consumes significant context. Running this as a subagent isolates the heavy reading from the main dialogue session. The subagent returns a structured summary, not raw page content.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
