Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

academic-search

skill · claude-office-skills/skillsMIT licenceAudited 20 Oct 2026 · source 79d91524ef4c

★ 529pushed 261 days agoversion 1.0.0
✓SAFEGrade B · 89/100 · 20 Oct 2026 · 79d9152
529repo stars · whole claude-office-skills/skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 79d91524ef4c and found no filesystem, network or shell access and no hard-coded secrets. What it does: Search and analyze academic literature. Find papers, understand research methodologies, and synthesize academic findings for research projects.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “academic-search (claude-office-skills/skills)”. Retrieved 20 Oct 2026. https://modelsatlas.com/skills/claude-office-skills/academic-search

Trust audit

Audit 0.4.1 · source read 20 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 79d91524ef4c · 20 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherclaude-office-skills GitHub organizationOwner of the repository this skill is read from
  • Source folderclaude-office-skills/skills/academic-searchThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict79d91524ef4cA new audit runs when the source changes
  • Repository statusNot archivedLast push 261 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Search and analyze academic literature. Find papers, understand research methodologies, and synthesize academic findings for research projects.

---
# ═══════════════════════════════════════════════════════════════════════════════
# CLAUDE OFFICE SKILL - Academic Search
# ═══════════════════════════════════════════════════════════════════════════════

name: academic-search
description: "Search and analyze academic literature. Find papers, understand research methodologies, and synthesize academic findings for research projects."
version: "1.0.0"
author: claude-office-skills
license: MIT

category: research
tags:
  - academic
  - papers
  - research
  - literature-review
  - citations
department: Research/Academia

models:
  recommended:
    - claude-sonnet-4
    - claude-opus-4
  compatible:
    - claude-3-5-sonnet
    - gpt-4
    - gpt-4o

mcp:
  server: office-mcp
  tools:
    - create_docx
    - extract_text_from_pdf

capabilities:
  - literature_search
  - paper_analysis
  - methodology_assessment
  - citation_management
  - research_synthesis

languages:
  - en
  - zh

related_skills:
  - deep-research
  - web-search
  - content-writer
---

# 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

| Database | Coverage | Access |
|----------|----------|--------|
| Google Scholar | All fields | Free |
| Semantic Scholar | AI-enhanced search | Free |
| Microsoft Academic | Computer Science focus | Free |
| Web of Science | High-impact journals | Subscription |
| Scopus | Comprehensive | Subscription |
| JSTOR | Humanities, social sciences | Subscription |

### Field-Specific Databases

| Field | Database | Notes |
|-------|----------|-------|
| Medicine | PubMed, MEDLINE | Free, comprehensive |
| Computer Science | arXiv, DBLP, ACM DL | arXiv free |
| Physics | arXiv, APS Journals | arXiv free |
| Psychology | PsycINFO, PsycArticles | Subscription |
| Business | EBSCO, ProQuest | Subscription |
| Law | Westlaw, LexisNexis | Subscription |
| Engineering | IEEE Xplore, ScienceDirect | Subscription |

### Preprint Servers

| Server | Fields |
|--------|--------|
| arXiv | Physics, Math, CS, Biology |
| bioRxiv | Life Sciences |
| medRxiv | Medical Sciences |
| SSRN | Social Sciences |
| ChemRxiv | Chemistry |

---

## 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

| Filter | Use Case |
|--------|----------|
| Date range | Recent developments |
| Publication type | Review vs. empirical |
| Author | Expert's work |
| Journal | High-impact venues |
| Language | Specific 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

| Aspect | Questions |
|--------|-----------|
| Research Question | Is it clear? Important? Novel? |
| Methodology | Appropriate? Rigorous? Reproducible? |
| Results | Convincing? Statistically valid? |
| Limitations | Acknowledged? How severe? |
| Contribution | What's new? How significant? |

---

## Output Format

### Search Strategy Output

```markdown
# 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] 

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 79d9152

Download folder ↗
git clone https://github.com/claude-office-skills/skills
git -C skills checkout 79d91524ef4c

The author documents no install command, so this uses the repository directly. Our verdict covers commit 79d91524ef4c only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 79d91524ef4c

Questions about academic-search

What does the academic-search skill do?
A curated collection of practical Claude Skills for real-world office tasks
Is academic-search safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can academic-search access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (79d91524ef4c), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.