domains / research / scholarly-evidence-lookup / research-lookup

research-lookup

Skill card

combined

The three copies share the name and the broad goal of gathering current research, but they implement different procedures. The K-Dense copy is a Parallel-first manuscript pipeline with a 60-reference target, context file, academic search passes, and Extract verification. The Vibe-Skills and OpenClaw copies are nearly identical Perplexity/OpenRouter lookup skills that add automatic model selection and a scientific-schematics visualization step. Because the K-Dense copy lacks the Perplexity model-selection and schematic steps, and the Perplexity copies lack the Parallel academic pipeline and verification workflow, crowning one would hide a real alternative.

Repositories

Other copies

Combined skill

---
name: research-lookup
description: "Compiles current scholarly evidence for a scientific manuscript or research brief. Supports a Parallel-first academic pipeline for manuscript packets and a Perplexity/OpenRouter lookup path for fast or deep research queries, with optional scientific schematics for visual communication."
---

# Research Lookup

Compile external evidence for a scientific manuscript or research brief. Choose the backend based on the user's request and available credentials.

## Scope and boundaries

Use this skill when the user explicitly wants:
- literature and background research for a manuscript
- many high-quality academic references
- evidence supporting or contradicting a scientific claim
- a structured evidence matrix or claim-to-source map
- current studies, methods precedent, mechanisms, limitations, or research gaps
- fast bounded web lookup or technical documentation
- statistical data, recent developments, or expert opinions

Do not activate it for casual factual questions that do not need research, private or unpublished material, or a claim that can be answered from user-provided files.

This skill compiles external evidence. It cannot supply the user's unpublished study data, decide what their Results show, or guarantee systematic-review completeness.

## Backend selection

| Need | Backend | Selection |
|---|---|---|
| Manuscript literature and references | Parallel Search + Extract | Default; use `--academic` |
| Fast bounded web lookup | Parallel Search | Use `--no-academic` |
| Deep/exhaustive multi-source report | Parallel Research | Explicit `--force-backend research` |
| OpenAI-compatible synthesis with research basis | Parallel Chat | Explicit `--force-backend chat` |
| Optional alternative academic search | Perplexity via OpenRouter | Explicit or enabled failure fallback |
| Fast Perplexity lookup | Perplexity Sonar Pro Search | Automatic for straightforward queries |
| Deep Perplexity reasoning | Perplexity Sonar Reasoning Pro | Automatic for complex analytical queries |

## Parallel-first manuscript workflow

### 1. Capture manuscript context

Use the user's available context to constrain retrieval:
- research question or hypothesis
- study type
- population or biological/technical system
- intervention or exposure
- comparator
- outcomes
- field and date range
- target journal, if known

The script accepts a JSON object through `--context-file`. Do not invent missing study details. A bare topic is supported, but the packet will flag its section briefs as broad.

### 2. Run the academic evidence pipeline

From the repository root:

```bash
python skills/research-lookup/scripts/research_lookup.py \
  "Evidence relevant to the manuscript's research question" \
  --academic \
  --target-references 60 \
  --context-file manuscript-context.json \
  --packet-dir sources/manuscript-research \
  --json
```

The academic pipeline runs bounded `advanced` Search passes for:
1. recent peer-reviewed primary studies
2. systematic reviews, meta-analyses, and consensus evidence
3. seminal and foundational publications
4. methods, protocols, validation, benchmarks, and mechanisms
5. contradictory, null, negative, replication, and limitation evidence
6. an unrestricted companion search when filtered passes do not reach the target

It prioritizes PubMed/PMC, Europe PMC, Crossref, OpenAlex, Semantic Scholar, arXiv/bioRxiv/medRxiv, major journals, and authoritative institutional sources.

### 3. Verify promising sources with Parallel Extract

Search candidates are deduplicated and ranked before batched extraction. Extraction requests source-supported:
- authors, year, venue, DOI, and PMID
- publication and study design
- population/system and sample size
- methods, intervention/exposure, comparator, and outcomes

## Perplexity/OpenRouter lookup workflow

Use Perplexity's Sonar models through OpenRouter for fast or deep research queries.

### Automatic model selection

- **Sonar Pro Search** (`perplexity/sonar-pro-search`): Use for straightforward information lookup, simple fact-finding, recent publication searches, basic protocol lookups, and statistical data retrieval.
- **Sonar Reasoning Pro** (`perplexity/sonar-reasoning-pro`): Use for deep analytical reasoning, complex multi-step queries, and synthesis of conflicting evidence.

### Core capabilities

1. **Academic Research Queries**: Query for recent papers, studies, and reviews. Expected response includes a summary of key findings, citation of 3-5 most relevant papers, key statistics, research gaps, and links to full papers.
2. **Technical and Methodological Information**: Find detailed procedures, specifications, and methodologies. Expected response includes step-by-step procedures, required materials, critical parameters, troubleshooting, and references.
3. **Statistical and Data Information**: Look up current statistics, survey results, and research data. Expected response includes current statistics with dates and sources, methodology, confidence intervals, comparisons, and citations.
4. **Citation and Reference Assistance**: Locate relevant papers and studies for citation. Expected response includes 5-10 most influential papers, complete citation information, brief descriptions, citation impact metrics, and journal rankings.

## Visual enhancement with scientific schematics

When creating documents with this skill, consider adding scientific diagrams and schematics to enhance visual communication.

If your document does not already contain schematics or diagrams:
- Use the scientific-schematics skill to generate AI-powered publication-quality diagrams
- Describe your desired diagram in natural language
- The AI will generate, review, and refine the schematic

For new documents, scientific schematics should be generated by default to visually represent key concepts, workflows, architectures, or relationships described in the text.

How to generate schematics:
```bash
python scripts/generate_schematic.py "your diagram description" -o figures/output.png
```

When to add schematics:
- Research information flow diagrams
- Query processing workflow illustrations
- Model selection decision trees
- System integration architecture diagrams
- Information retrieval pipeline visualizations
- Knowledge synthesis frameworks
- Any complex concept that benefits from visualization

## Conflicts

- K-Dense-AI/scientific-agent-skills uses Parallel as the default backend and treats Perplexity as optional; foryourhealth111-pixel/Vibe-Skills and FreedomIntelligence/OpenClaw-Medical-Skills use Perplexity as the primary backend.
- K-Dense-AI/scientific-agent-skills targets a 60-verified-reference manuscript packet with a context file and multi-pass academic search; the other two copies do not specify a reference target or context file.
- foryourhealth111-pixel/Vibe-Skills and FreedomIntelligence/OpenClaw-Medical-Skills include a scientific-schematics visualization step; K-Dense-AI/scientific-agent-skills does not.