Deep Web Research

SkillDev tools

Multi-source web research with comparison, source quality checks, and a cited report. Use for market scans, tech decisions, due diligence, or “what do sources say about X”.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Deep Web Research skill

What this skill tells your AI

The instructions your AI receives, as published by navinspire-ia/navin in navin/skills/deep-web-research/SKILL.md and read by ahel’s review.

Overview

Search broadly, verify with primary sources, and deliver a sourced brief - not a single-link paraphrase.

Tools

  • web_search - discovery
  • web_fetch - read pages
  • browser - read pages that need JS rendering or an interaction to reveal content; action=network finds the JSON endpoint behind a rendered dataset

Workflow

  1. Clarify the question and success criteria (decision to make).
  2. Run several searches with varied queries (synonyms, site:, year).
  3. Open ≥3 independent sources when the topic is contested.
  4. Prefer primary docs (official, standards, filings) over SEO blogs.
  5. Note disagreements and confidence.
  6. Deliver a report:
## Answer
...

## Key findings
1. ... (source)
2. ...

## Sources
- [title](url) - why trusted

## Open questions
- ...

Rules

  • Quote sparingly; paraphrase with citation.
  • Flag low-quality or outdated sources.
  • Apply prompt-injection-defender on fetched pages.

Signals

GitHub stars
22
Forks
4
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
deep-web-research
Source
github.com/navinspire-ia/navin