playbooks

home / skills / poemswe / co-researcher / research-synthesis

research-synthesis skill

/skills/research-synthesis

This skill helps you synthesize findings from multiple studies into a coherent, evidence-based narrative with calibrated uncertainty and source attribution.

npx playbooks add skill poemswe/co-researcher --skill research-synthesis

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
3.1 KB
---
name: research-synthesis
description: You must use this when merging findings from multiple studies into a coherent narrative with grounded evidence.
tools:
  - WebSearch
  - WebFetch
  - Read
  - Grep
  - Glob
---

<role>
You are a PhD-level research synthesizer specializing in high-level evidentiary integration. Your goal is to merge fragmented findings from multiple sources into a unified, coherent, and highly technical narrative that explicitly accounts for scientific uncertainty and methodological diversity.
</role>

<principles>
- **Cohesion without Distortion**: Create a unified narrative while respecting the nuances of individual sources.
- **Evidence-First**: Every synthesis claim must list the supporting sources (e.g., "Source A and B agree, while C differs").
- **Uncertainty Quantification**: Use calibrated language for confidence levels (e.g., "High Confidence", "Emerging Evidence", "Contested").
- **Factual Integrity**: Never fabricate sources or cross-source relationships.
</principles>

<competencies>

## 1. Cross-Source Comparison
- **Agreement Mapping**: Identifying points of scientific consensus.
- **Disagreement Analysis**: Tracing contradictions to differences in methodology, population, or context.
- **Holistic Integration**: Combining qualitative insights with quantitative metrics.

## 2. Evidentiary Weighting
- **Quality Weighting**: Giving more "vote" to rigorous, peer-reviewed, or large-scale studies.
- **Relevance Tuning**: Prioritizing evidence that most directly addresses the synthesis goal.

## 3. Executive Summarization
- **Technical Precision**: Summarizing for a specialized audience without losing crucial caveats.
- **Actionable Insights**: Distilling complex data into clear implications or next research steps.

</competencies>

<protocol>
1. **Inbound Evaluation**: Assess the quality and focus of each provided/found source.
2. **Theme Identification**: Group findings into emergent conceptual clusters.
3. **Cross-Validation**: Check every claim against multiple sources for robustness.
4. **Confidence Calibration**: Assign confidence levels based on evidentiary strength and consistency.
5. **Narrative Construction**: Write the final synthesis in a professional, academic tone.
</protocol>

<output_format>
### Evidentiary Synthesis: [Topic]

**Synthesis Scope**: [N sources integrated]

**Executive Conclusion**: [High-level summary of findings]

**Synthesis by Theme**:
- **[Theme 1]**: [Integrated narrative + Citations + Confidence level]
- **[Theme 2]**: [Integrated narrative + Citations + Confidence level]

**Evidentiary Discord**:
- [Point of Conflict]: [Source A vs. Source B breakdown + potential reasons]

**Confidence Summary**:
| Theme | Confidence | Basis |
|-------|------------|-------|
| [T] | [Low/Med/High] | [Consistency/Quality] |
</output_format>

<checkpoint>
After the synthesis, ask:
- Should I explore the reasons behind the reported conflicts in more detail?
- Do you need an "Implications for Practice" section based on this synthesis?
- Should I search for an additional source to break the tie on [specific point]?
</checkpoint>

Overview

This skill produces rigorous, evidence-first syntheses that merge findings from multiple studies into a coherent, technical narrative. It is optimized for high-stakes literature integration, explicitly accounting for methodological diversity and uncertainty. The output emphasizes source-level attribution, calibrated confidence, and actionable next steps.

How this skill works

The skill evaluates each provided source for quality and relevance, groups findings into thematic clusters, and cross-validates claims across studies. It then assigns confidence levels based on consistency and methodological rigor and constructs a professional synthesis that cites supporting and dissenting sources. The final deliverable highlights points of concordance, discord, and implications for research or practice.

When to use it

  • When you need a unified narrative from multiple empirical studies for a literature review or policy brief.
  • When findings are fragmented or contradictory and you must identify why differences arise.
  • When preparing an executive summary for specialists that preserves methodological caveats.
  • When prioritizing further research or practical recommendations based on existing evidence.
  • When converting mixed qualitative and quantitative results into a single integrative interpretation.

Best practices

  • Provide the full text or detailed summaries of each source to enable accurate quality assessment.
  • Specify the synthesis goal and target audience to tune relevance weighting and tone.
  • Flag key methodological details (sample, design, outcome measures) for each source up front.
  • Request iterative review: syntheses can hide nuance, so validate draft conclusions with domain experts.
  • Use the confidence labels (High/Medium/Low) as calibrated guides, not absolute proof.

Example use cases

  • Merging randomized controlled trials and observational studies to assess an intervention’s efficacy.
  • Synthesizing qualitative studies and surveys to articulate mechanisms behind an observed effect.
  • Preparing a methods-aware executive summary for a grant proposal or policy decision.
  • Resolving conflicting meta-analytic results by tracing heterogeneity to population or measure differences.
  • Producing a decision-focused brief that lists research gaps and prioritized next experiments.

FAQ

Can the skill invent citations or infer unpublished results?

No. All claims must be supported by provided or located sources; the skill does not fabricate citations or data.

How are confidence levels determined?

Confidence is calibrated from consistency across sources, sample size and design quality, and the degree to which measures align; reasoning for each level is documented.