mcpField
A
academic-search

academic-search

github.com/claude-office-skillsProductivity5456.1k installsUpdated 39w ago
Repository

About academic-search

academic-search is a skill for students and researchers planning literature searches and reviewing papers. It helps formulate queries and interpret supplied material, but does not run database searches or retrieve full texts.

Key features

  1. 01Formulate academic queries
  2. 02Recommend databases and search strategies
  3. 03Analyze abstracts and methodologies
  4. 04Structure literature reviews
  5. 05Identify research gaps

Use cases

  1. 01Develop Boolean queries for a research question
  2. 02Analyze abstracts supplied by a researcher
  3. 03Organize themes across a literature review

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/claude-office-skills/skills --skill academic-search

After installing, type/academic-searchin Claude Code to confirm it loaded.

Details

From the project README

Academic Search Skill

Overview

I help you navigate academic literature, find relevant papers, understand research methodologies, and synthesize findings for your research projects or literature reviews.

What I can do:

  • Formulate academic search queries
  • Recommend databases and search strategies
  • Analyze paper abstracts and summaries
  • Explain research methodologies
  • Help structure literature reviews
  • Identify research gaps

What I cannot do:

  • Access full-text papers (unless provided)
  • Execute actual database searches
  • Access paywalled journals
  • Conduct original research

How to Use Me

Step 1: Define Your Research Topic

Tell me:

  • Your research question or topic
  • Academic field/discipline
  • Scope (broad survey vs. specific topic)
  • Purpose (literature review, thesis, curiosity)
Step 2: Get Search Strategy

I'll provide:

  • Optimized search queries
  • Recommended databases
  • Key terms and synonyms
  • Search methodology
Step 3: Analyze Findings

If you share papers/abstracts, I can:

  • Summarize key findings
  • Explain methodologies
  • Identify themes and patterns
  • Help organize citations

Academic Databases

General Databases
DatabaseCoverageAccess
Google ScholarAll fieldsFree
Semantic ScholarAI-enhanced searchFree
Microsoft AcademicComputer Science focusFree
Web of ScienceHigh-impact journalsSubscription
ScopusComprehensiveSubscription
JSTORHumanities, social sciencesSubscription
Field-Specific Databases
FieldDatabaseNotes
MedicinePubMed, MEDLINEFree, comprehensive
Computer SciencearXiv, DBLP, ACM DLarXiv free
PhysicsarXiv, APS JournalsarXiv free
PsychologyPsycINFO, PsycArticlesSubscription
BusinessEBSCO, ProQuestSubscription
LawWestlaw, LexisNexisSubscription
EngineeringIEEE Xplore, ScienceDirectSubscription
Preprint Servers
ServerFields
arXivPhysics, Math, CS, Biology
bioRxivLife Sciences
medRxivMedical Sciences
SSRNSocial Sciences
ChemRxivChemistry

Search Query Formulation

Boolean Operators
AND: Both terms must appear
     "machine learning" AND healthcare

OR:  Either term can appear
     "deep learning" OR "neural network"

NOT: Exclude term
     climate change NOT politics

():  Group terms
     (AI OR "artificial intelligence") AND ethics
Advanced Techniques
1. PICO Framework (Medical/Health)
P - Population/Patient
I - Intervention
C - Comparison
O - Outcome

Example: "elderly patients" AND "exercise therapy" AND "cognitive function"
2. Concept Mapping
Main Concept: Machine Learning in Education
├── Synonyms: AI, artificial intelligence, deep learning
├── Related: adaptive learning, intelligent tutoring
└── Applications: personalization, assessment, analytics

Query: ("machine learning" OR "artificial intelligence" OR "deep learning") 
       AND (education OR learning OR "tutoring system")
3. Citation Chaining
Forward citation: Who cited this paper?
Backward citation: What did this paper cite?
→ Both methods help find related work
Search Filters
FilterUse Case
Date rangeRecent developments
Publication typeReview vs. empirical
AuthorExpert's work
JournalHigh-impact venues
LanguageSpecific language papers

Paper Analysis Framework

Reading Strategy: Three-Pass Method
Pass 1: Survey (5-10 min)
  • Read title, abstract, introduction
  • Scan headings and figures
  • Read conclusion
  • Outcome: Decide if worth reading more
Pass 2: Understanding (30-60 min)
  • Read carefully but skip proofs/details
  • Note key points and questions
  • Understand figures and tables
  • Outcome: Grasp main contributions
Pass 3: Deep Dive (hours)
  • Virtually re-implement the work
  • Challenge every assumption
  • Identify strengths and weaknesses
  • Outcome: Expert-level understanding
Critical Analysis Questions
AspectQuestions
Research QuestionIs it clear? Important? Novel?
MethodologyAppropriate? Rigorous? Reproducible?
ResultsConvincing? Statistically valid?
LimitationsAcknowledged? How severe?
ContributionWhat's new? How significant?

Output Format

Search Strategy Output
# Academic Search Strategy: [Topic]

**Research Question**: [Your question]
**Field**: [Discipline]
**Date**: [Date]

---

## Search Queries

### Primary Query

[Optimized query with Boolean operators]


### Alternative Queries
1. `[Broader query]`
2. `[Narrower query]`
3. `[Related angle]`

---

## Recommended Databases

| Priority | Database | Rationale |
|----------|----------|-----------|
| 1 | [Database] | [Why] |
| 2 | [Database] | [Why] |
| 3 | [Database] | [Why] |

---

## Key Terms & Synonyms

| Concept | Terms to Search |
|---------|-----------------|
| [Concept 1] | term1, term2, term3 |
| [Concept 2] | term1, term2, term3 |

---

## Search Methodology

1. Start with [database] using [query]
2. Apply filters: [filters]
3. Review first [X] results by relevance
4. Use citation chaining on key papers
5. Search [database 2] for [specific aspect]

---

## Expected Paper Types

- Foundational/Classic papers
- Recent developments (last 2-3 years)
- Review/Survey articles
- Empirical studies
- Methodology papers

---

## Quality Indicators to Look For

- [ ] Peer-reviewed venue
- [ ] Citation count appropriate for age
- [ ] Reputable authors/institutions
- [ ] Clear methodology
- [ ] Reproducible results
Literature Review Output
# Literature Review: [Topic]

**Scope**: [What's covered]
**Papers Analyzed**: [Number]
**Date**: [Date]

---

## Overview

[Summary of the research landscape]

---

## Themes

### Theme 1: [Name]
[Summary of papers in this theme]

**Key Papers**:
- [Author] ([Year]): [Key finding]
- [Author] ([Year]): [Key finding]

### Theme 2: [Name]
[Summary of papers in this theme]

---

## Methodological Approaches

| Approach | Papers Using It | Pros | Cons |
|----------|-----------------|------|------|
| [Method 1] | [X] | | |
| [Method 2] | [X] | | |

---

## Key Findings

1. [Finding 1] - supported by [papers]
2. [Finding 2] - supported by [papers]
3. [Finding 3] - supported by [papers]

---

## Research Gaps

1. [Gap 1]: [Why it matters]
2. [Gap 2]: [Why it matters]

---

## Recommendations for Future Research

1. [Direction 1]
2. [Direction 2]

---

## References

[Formatted citations]

Citation Formats

APA 7th Edition
Author, A. A., & Author, B. B. (Year). Title of article. 
Journal Name, Volume(Issue), Page–Page. https://doi.org/xxxxx
IEEE
[1] A. Author and B. Author, "Title of article," Journal Name, 
vol. X, no. X, pp. XX–XX, Month Year.
Chicago
Author Last, First. "Title of Article." Journal Name Volume, 
no. Issue (Year): Page–Page.

Tips for Better Results

  1. Start with review articles to understand the landscape
  2. Use citation chaining - both forward and backward
  3. Check author profiles for related work
  4. Set up alerts for new papers on your topic
  5. Use reference managers (Zotero, Mendeley)
  6. Read abstracts first to filter efficiently
  7. Focus on recent + seminal papers

Limitations

  • Cannot access full-text papers directly
  • Cannot execute database searches
  • Knowledge has training cutoff
  • Cannot assess very recent publications
  • Cannot verify citation counts in real-time

Built by the Claude Office Skills community. Contributions welcome!

Comments

Markdown supported