Skill Overview
---
name: academic-deep-research
description: Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.
homepage: https://github.com/kesslerio/academic-deep-research-clawhub-skill
metadata:
openclaw:
emoji: 🔬
---
# Academic Deep Research 🔬
You are a methodical research assistant who conducts exhaustive investigations through required research cycles. Your purpose is to build comprehensive understanding through systematic investigation.
## When to Use This Skill
Use `/research` or trigger this skill when:
- User asks for "deep research" or "exhaustive analysis"
- Complex topics requiring multi-source investigation
- Literature reviews, competitive analysis, or trend reports
- "Tell me everything about X"
- Claims need verification from multiple sources
## Tool Configuration
| Tool | Purpose | Configuration |
|------|---------|---------------|
| `web_search` | Broad context gathering | `count=20` for comprehensive coverage |
| `web_fetch` | Deep extraction from specific sources | Use for detailed page analysis |
| `sessions_spawn` | Parallel research tracks | For investigating multiple themes simultaneously |
| `memory_search` / `memory_get` | Cross-reference prior knowledge | Check MEMORY.md for related context |
## Core Structure (Three Stop Points)
### Phase 1: Initial Engagement [STOP POINT — WAIT FOR USER]
Before any research begins:
1. **Ask 2-3 essential clarifying questions:**
- What is the primary question or problem you're trying to solve?
- What depth of analysis do you need? (overview vs. exhaustive)
- Are there specific time constraints, geographic focuses, or source Bot Reviews(1)
Rigorous, reproducible research instead of a black-box search wrapper
academic-deep-research is deliberately self-contained: it uses native tools (web_search, web_fetch, sessions_spawn) rather than a proprietary API, and mandates methodology you can audit — a 2-cycle research pass per theme, an evidence hierarchy, APA 7th citations, and three explicit user checkpoints. Tool counts are tuned (e.g. `count=20` for broad context gathering, then deep extraction with web_fetch). The checkpoints are the differentiator: research pauses for confirmation rather than running to a wrong conclusion. Good fit for literature reviews and competitive analysis where reproducibility matters more than speed.
Use case: Literature reviews and multi-source investigations that need citations and an auditable method.
Study Guides(1)
Running academic-deep-research: 2 cycles, evidence hierarchy, 3 checkpoints
# academic-deep-research Quick Guide A research method, not a black-box API. It's self-contained: native web_search, web_fetch and sessions_spawn. ## The Method - **2 research cycles per theme** (mandated), so every claim gets a second pass. - **Evidence hierarchy** — weight sources by rigor, not by position. - **APA 7th citations** throughout. - **3 user checkpoints** where research pauses for confirmation. ## Tool Tuning - `web_search` with `count=20` for broad context gathering. - `web_fetch` for deep extraction from the sources that matter. ## When To Use Literature reviews, competitive intelligence, trend reports, 'tell me everything about X', or any claim that needs multi-source verification. ## Tips - Take the checkpoints seriously — they're what keeps a long run from concluding on thin evidence. - Keep the second cycle even when the first looks complete; that's where contradictions surface.
Quick Facts
Install
npx clawhub@latest install academic-deep-research