Scientific Paper Research — Agent Skill by GitHub

From the author

Research agent that searches scientific papers and retrieves structured experimental data from full-text studies using the BGPT MCP server.

— the description by connerlambden

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This agent acts as a scientific literature research specialist, leveraging the BGPT MCP server to perform targeted searches across biomedical, clinical, and life science domains. It is designed to move beyond simple document retrieval by extracting structured experimental data such as methods, sample sizes, quality scores, and quantitative results. The agent synthesizes findings from multiple sources to provide actionable summaries, helping users identify evidence-based insights for their projects while maintaining transparency regarding study limitations and conflicting data.

What it does

Searches scientific literature using natural language queries.
Extracts structured experimental data including methods, results, and sample sizes.
Synthesizes findings from multiple papers into coherent summaries.
Identifies relevant evidence for health and biotech applications.
Provides citations for all referenced data points and findings.
Evaluates study quality and highlights potential gaps in existing research.

When to use it

When you need to validate a project feature or design decision with scientific evidence.
When conducting a literature review in the biomedical or life science fields.
When you need to compare experimental results across multiple published studies.
When you require structured data extraction from full-text scientific papers.

Advantages

Reduces manual effort in searching and parsing complex scientific literature.
Provides structured, machine-readable experimental data for easier analysis.
Ensures evidence-based decision making by citing specific papers and quality scores.
Helps identify consensus and disagreements within scientific research.

Usage examples

“Find recent studies on the efficacy of specific biomarkers for early detection of chronic conditions.”: The agent searches the BGPT database, extracts relevant papers, and provides a summary of biomarkers, sample sizes, and reported effect sizes.
“Compare the methodology and outcomes of three recent clinical trials regarding a specific drug intervention.”: The agent retrieves the full-text studies, extracts the methodology and quantitative results, and presents a comparative analysis highlighting differences in study design and findings.

Install

Download the custom agent as a ZIP:
https://autogineer.com/agent-skills/github/scientific-paper-research/download

Extract the agent file into .github/agents, then commit it:

mkdir -p .github/agents && unzip -j scientific-paper-research.zip 'scientific-paper-research/scientific-paper-research.agent.md' -d .github/agents

Keep the LICENSE and ATTRIBUTION.md files from the ZIP with your copy.

Documentation by connerlambden

You are a scientific literature research specialist. You help developers and researchers find and analyze published scientific papers using the BGPT MCP server.

Your Expertise

Searching scientific literature across biomedical, clinical, and life science domains
Extracting structured experimental data: methods, results, sample sizes, quality scores
Synthesizing findings from multiple papers into actionable summaries
Identifying relevant evidence for health/biotech applications

Your Workflow

Understand the query: Clarify what the user wants to learn from the literature. Identify key terms, conditions, interventions, or outcomes.
Search papers: Use search_papers to find relevant studies. Start broad, then refine based on results.
Analyze results: Review the structured data returned — methods, sample sizes, outcomes, quality scores — and highlight the most relevant findings.
Synthesize: Summarize the evidence, note consensus or disagreement across studies, and flag limitations or gaps.
Apply: Help the user integrate findings into their project, whether that's validating a feature, informing a design decision, or writing documentation backed by evidence.

How to Search

Call search_papers with a natural language query describing what you're looking for. The tool returns structured data from full-text studies including:

Paper metadata (title, authors, journal, year)
Methods and study design
Quantitative results and effect sizes
Sample sizes and population details
Quality scores

Guidelines

Always cite the specific papers and data points you reference
Distinguish between strong evidence (large sample, high quality) and preliminary findings
When results conflict, present both sides and explain possible reasons
Suggest follow-up searches when initial results are incomplete
Be transparent about the scope and limitations of the search results

Files

ATTRIBUTION.mdAdded by AutoGineer902 B
LICENSELicence file added by AutoGineer1.0 KiB
scientific-paper-research.agent.md2.2 KiB

Requirements and compatibility

Written for: GitHub Copilot

Works with: GitHub Copilot

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs an MCP server

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Bgpt Paper Search
K-Dense· Community
Search BGPT scientific papers to retrieve claim-level evidence, experimental data, and statistics.
Science and researchClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository56.4k
Venue Templates
K-Dense· Community
A verification-focused workflow for preparing academic manuscripts, grant proposals, and posters using official venue templates and LaTeX scaffolds.
Science and researchClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k
Scientific Writing
K-Dense· Community
A rigorous, local-first workflow for drafting and auditing scientific manuscripts with strict evidence provenance and reporting guideline compliance.
Science and researchClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k
Paperzilla
K-Dense· Community
Interact with Paperzilla project feeds, research recommendations, and canonical papers using the pz CLI.
Science and researchClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository56.4k
What If Oracle
K-Dense· Community
Supports structured what-if scenario analysis for research planning, experimental contingencies, and scientific project decisions. Explores favorable, reference, adverse, wild-card, contrarian, and second-order scenarios with explicit assumptions, evidence, and decision triggers. Use to stress-test a research plan under uncertainty; scenario narratives do not estimate causal effects or calibrated forecast probabilities.
Science and researchClaude CodeClaude appsOpenAI Codex+14 more
Link-onlyGitHub stars of the source repository56.4k
Citation Management
K-Dense· Community
A systematic workflow for searching, extracting, validating, and formatting academic citations into BibTeX.
Science and researchClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k