Content
Plugin
claude-paper
Transform research papers into comprehensive learning environments A powerful Claude Code plugin that automates research paper study through intelligent material generation, code demonstrations, and an interactive web viewer.
Plugin Signal53/100Fair
maintained42
capable34
documented100
adopted52
Install on Claude Code
> /plugin marketplace add alaliqing/claude-paper> /plugin install claude-paper@claude-paper
What's inside
Skills
3/studyUse this skill when the user wants to read, study, analyze, or deeply understand a research paper (PDF)./summaryUse this for a quick summary of a research paper's core ideas and key points. Use when you want to quickly understand a paper without deep study materials. Triggers on PDF paths, arXiv URLs, or paper URLs./webuiStart the Claude Paper web viewer to browse and study papers
Commands
1README
1Claude Paper
Transform research papers into comprehensive learning environments
A powerful Claude Code plugin that automates research paper study through intelligent material generation, code demonstrations, and an interactive web viewer.
Features
- Automatic PDF parsing - Extract title, authors, abstract, and full content
- Smart content truncation - Handles large papers (50k char limit) intelligently
- Code repository detection - Automatically finds GitHub, arXiv, CodeOcean links
- Adaptive learning materials - Generates README, summary, insights, Q&A based on paper complexity
- Code demonstrations - Clean implementations with Jupyter notebooks and original code integration
- Interactive web viewer - Nuxt.js interface with math equation support (KaTeX)
- Intelligent assessment - Difficulty levels and paper type detection for adaptive content generation
Quick Start
Installation
Install from the Claude Code marketplace:
# Add the marketplace
/plugin marketplace add alaliqing/claude-paper
# Install the plugin
/plugin install claude-paper
# Restart Claude Code for the plugin to take effect
That's it! The plugin will automatically:
- Install all dependencies (pdf-parse for PDF processing)
- Create the papers directory at
~/claude-papers/ - Initialize the search index
- Install web viewer dependencies
System Requirements
- Node.js: 18.0.0 or higher
- npm: Comes with Node.js
- Claude Code: Latest version with plugin support
- poppler-utils: For PDF image extraction (install via system package manager)
- macOS:
brew install poppler - Ubuntu/Debian:
sudo apt-get install poppler-utils - Arch Linux:
sudo pacman -S poppler
- macOS:
Usage
Study a Research Paper
Simply talk to Claude Code to study a paper:
Help me study the paper at ~/Downloads/attention-is-all-you-need.pdf
You can also use URLs:
# Direct PDF URL
Help me study the paper at https://arxiv.org/pdf/1706.03762.pdf
# arXiv abstract URL (automatically converted to PDF)
Help me study the paper at https://arxiv.org/abs/1706.03762
Claude will automatically trigger the study workflow and:
- Parse the PDF and extract metadata
- Analyze paper complexity and type
- Generate adaptive learning materials
- Create code demonstrations (if applicable)
- Extract and include original code (if available)
- Extract key figures and images
- Update the global search index
- Launch the web viewer automatically
Launch Web Viewer
/claude-paper:webui
Opens the interactive web interface at http://localhost:5815 where you can:
- Browse all studied papers
- View generated materials with math rendering
- Access code demonstrations and notebooks
- Search through your paper library
Paper Storage Structure
Papers are organized in ~/claude-papers/papers/{paper-slug}/:
~/claude-papers/
βββ papers/
β βββ {paper-slug}/
β βββ paper.pdf # Original PDF file
β βββ meta.json # Paper metadata (title, authors, etc.)
β βββ README.md # Quick navigation and overview
β βββ summary.md # Detailed summary
β βββ insights.md # Key insights (most important!)
β βββ method.md # Methodology (if complex)
β βββ mental-model.md # Paper categorization (if needed)
β βββ reflection.md # Future directions (if needed)
β βββ qa.md # Learning questions
β βββ index.html # Interactive HTML explorer
β βββ images/ # Extracted figures and tables
β β βββ fig1.png
β β βββ fig2.png
β βββ code/ # Code demonstrations
β βββ core-demo.py # Clean reference implementation
β βββ concept-demo.ipynb # Interactive Jupyter notebook
β
βββ index.json # Global search index
Architecture
Plugin Structure
claude-paper/
βββ .claude-plugin/
β βββ marketplace.json # Marketplace catalog entry
βββ plugin/
β βββ .claude-plugin/
β β βββ plugin.json # Plugin manifest
β βββ skills/
β β βββ study/
β β βββ SKILL.md # Study workflow definition
β β βββ scripts/
β β βββ parse-pdf.js # PDF parsing utility
β β βββ extract-images.py # Image extraction
β βββ commands/
β β βββ webui.md # /webui command
β βββ hooks/
β β βββ hooks.json # Session lifecycle hooks
β β βββ check-install.sh # Installation verification
β βββ src/
β β βββ web/ # Nuxt.js web viewer
β β βββ components/ # Vue components
β β βββ composables/ # Vue composables
β β βββ server/ # API endpoints
β β βββ package.json
β βββ package.json
βββ README.md
Key Components
- Study Skill - Main workflow agent that orchestrates paper processing
- PDF Parser - Extracts text, metadata, and code links using pdf-parse
- Image Extractor - Python script for PDF figure extraction
- Web Viewer - Nuxt.js application with Nitro API server
- Hooks System - Automatic dependency installation and setup
Development
Running Tests
# Test PDF parsing
node plugin/skills/study/scripts/parse-pdf.js /path/to/paper.pdf
# Test web viewer
cd plugin/src/web
npm run dev
# Test full workflow
cd /path/to/claude-paper
claude --plugin-dir ./plugin
/claude-paper:study /path/to/paper.pdf
Building for Production
# Build web viewer
cd plugin/src/web
npm run build
# The built viewer will be in .output/
Configuration
Environment Variables
No configuration required! The plugin uses sensible defaults:
- Papers directory:
~/claude-papers/ - Web viewer port:
5815 - Content limit:
50,000characters (with intelligent truncation)
Advanced Customization
You can modify behavior by editing the skill file at:
plugin/skills/study/SKILL.md
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Make your changes
- Add tests if applicable
- Commit your changes (
git commit -m 'add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Built with Claude Code
- PDF parsing powered by pdf-parse
- Web viewer built with Nuxt.js
- Math rendering by KaTeX
File tree
1799alaliqing/claude-paperView on GitHub
.claude-plugin/
marketplace.json
assets/
screenshot1.png
screenshot2.png
LICENSE
plugin/
.claude-plugin/
plugin.json
commands/
webui.md
hooks/
check-install.sh
hooks.json
package.json
skills/
study/
scripts/
download-pdf.cjs
extract-images.py
parse-pdf.js
SKILL.md
summary/
SKILL.md
webui/
SKILL.md
src/
web/
.gitignore
components/
FileTreeNode.vue
PaperCard.vue
PaperContent.vue
SearchFilterBar.vue
TagBadge.vue
TagEditor.vue
VSCodeButton.vue
composables/
usePapers.ts
node_modules/
.bin/
esbuild
nanoid
parser
rollup
vite
.package-lock.json
@babel/
helper-string-parser/
lib/
index.js
index.js.map
LICENSE
package.json
README.md
helper-validator-identifier/
lib/
identifier.js
identifier.js.map
index.js
index.js.map
keyword.js
keyword.js.map
LICENSE
package.json
README.md
parser/
bin/
babel-parser.js
CHANGELOG.md
lib/
index.js
index.js.map
LICENSE
package.json
README.md
typings/
babel-parser.d.ts
types/
lib/
asserts/
assertNode.js
assertNode.js.map
generated/
index.js
index.js.map
ast-types/
generated/
index.js
index.js.map
builders/
flow/
createFlowUnionType.js
createFlowUnionType.js.map
createTypeAnnotationBasedOnTypeof.js
createTypeAnnotationBasedOnTypeof.js.map
generated/
index.js
index.js.map
lowercase.js
lowercase.js.map
uppercase.js
uppercase.js.map
productions.js
productions.js.map
react/
buildChildren.js
buildChildren.js.map
typescript/
createTSUnionType.js
createTSUnionType.js.map
validateNode.js
validateNode.js.map
clone/
clone.js
clone.js.map
cloneDeep.js
cloneDeep.js.map
cloneDeepWithoutLoc.js
cloneDeepWithoutLoc.js.map
cloneNode.js
cloneNode.js.map
cloneWithoutLoc.js
cloneWithoutLoc.js.map
comments/
addComment.js
addComment.js.map
addComments.js
addComments.js.map
inheritInnerComments.js
inheritInnerComments.js.map
inheritLeadingComments.js
inheritLeadingComments.js.map
inheritsComments.js
inheritsComments.js.map
inheritTrailingComments.js
inheritTrailingComments.js.map
removeComments.js
removeComments.js.map
constants/
generated/
index.js
index.js.map
index.js
index.js.map
converters/
ensureBlock.js
ensureBlock.js.map
gatherSequenceExpressions.js
gatherSequenceExpressions.js.map
toBindingIdentifierName.js
toBindingIdentifierName.js.map
toBlock.js
toBlock.js.map
toComputedKey.js
toComputedKey.js.map
toExpression.js
toExpression.js.map
toIdentifier.js
toIdentifier.js.map
toKeyAlias.js
toKeyAlias.js.map
toSequenceExpression.js
toSequenceExpression.js.map
toStatement.js
toStatement.js.map
valueToNode.js
valueToNode.js.map
definitions/
core.js
core.js.map
deprecated-aliases.js
deprecated-aliases.js.map
experimental.js
experimental.js.map
flow.js
flow.js.map
index.js
index.js.map
jsx.js
jsx.js.map
misc.js
misc.js.map
placeholders.js
placeholders.js.map
typescript.js
typescript.js.map
utils.js
utils.js.map
index-legacy.d.ts
index.d.ts
index.js
index.js.flow
index.js.map
modifications/
appendToMemberExpression.js
appendToMemberExpression.js.map
flow/
removeTypeDuplicates.js
removeTypeDuplicates.js.map
inherits.js
inherits.js.map
prependToMemberExpression.js
prependToMemberExpression.js.map
removeProperties.js
removeProperties.js.map
removePropertiesDeep.js
removePropertiesDeep.js.map
typescript/
removeTypeDuplicates.js
removeTypeDuplicates.js.map
retrievers/
getAssignmentIdentifiers.js
getAssignmentIdentifiers.js.map
getBindingIdentifiers.js
getBindingIdentifiers.js.map
getFunctionName.js
getFunctionName.js.map
getOuterBindingIdentifiers.js
getOuterBindingIdentifiers.js.map
traverse/
traverse.js
traverse.js.map
traverseFast.js
traverseFast.js.map
utils/
deprecationWarning.js
deprecationWarning.js.map
inherit.js
inherit.js.map
react/
cleanJSXElementLiteralChild.js
cleanJSXElementLiteralChild.js.map
shallowEqual.js
shallowEqual.js.map
validators/
buildMatchMemberExpression.js
buildMatchMemberExpression.js.map
generated/
index.js
index.js.map
is.js
is.js.map
isBinding.js
isBinding.js.map
isBlockScoped.js
isBlockScoped.js.map
isImmutable.js
isImmutable.js.map
isLet.js
isLet.js.map
isNode.js
isNode.js.map
isNodesEquivalent.js
isNodesEquivalent.js.map
isPlaceholderType.js
isPlaceholderType.js.map
isReferenced.js
isReferenced.js.map
isScope.js
isScope.js.map
isSpecifierDefault.js
isSpecifierDefault.js.map
isType.js
isType.js.map
isValidES3Identifier.js
isValidES3Identifier.js.map
isValidIdentifier.js
isValidIdentifier.js.map
isVar.js
isVar.js.map
matchesPattern.js
matchesPattern.js.map
react/
isCompatTag.js
isCompatTag.js.map
isReactComponent.js
isReactComponent.js.map
validate.js
validate.js.map
LICENSE
package.json
README.md
@esbuild/
darwin-arm64/
bin/
esbuild
package.json
README.md
@jridgewell/
sourcemap-codec/
dist/
sourcemap-codec.mjs
sourcemap-codec.mjs.map
sourcemap-codec.umd.js
sourcemap-codec.umd.js.map
LICENSE
package.json
README.md
src/
scopes.ts
sourcemap-codec.ts
strings.ts
vlq.ts
types/
scopes.d.cts
scopes.d.cts.map
scopes.d.mts
scopes.d.mts.map
sourcemap-codec.d.cts
sourcemap-codec.d.cts.map
sourcemap-codec.d.mts
sourcemap-codec.d.mts.map
strings.d.cts
strings.d.cts.map
strings.d.mts
strings.d.mts.map
vlq.d.cts
vlq.d.cts.map
vlq.d.mts
vlq.d.mts.map
@rollup/
rollup-darwin-arm64/
package.json
README.md
rollup.darwin-arm64.node
@shikijs/
core/
dist/
index.d.mts
index.d.ts
index.mjs
textmate.d.mts
textmate.d.ts
textmate.mjs
types.d.mts
types.d.ts
types.mjs
wasm-inlined.d.mts
wasm-inlined.d.ts
wasm-inlined.mjs
LICENSE
package.json
README.md
engine-javascript/
dist/
engine-compile.d.mts
engine-compile.d.ts
engine-compile.mjs
engine-raw.d.mts
engine-raw.d.ts
engine-raw.mjs
index.d.mts
index.d.ts
index.mjs
shared/
engine-javascript.hzpS1_41.mjs
LICENSE
package.json
README.md
engine-oniguruma/
dist/
chunk-index.d.d.mts
index.d.mts
index.mjs
onig.d.mts
wasm-inlined.d.mts
wasm-inlined.mjs
LICENSE
package.json
README.md
langs/
dist/
1c-query.d.mts
1c-query.mjs
1c.d.mts
1c.mjs
abap.d.mts
abap.mjs
actionscript-3.d.mts
actionscript-3.mjs
ada.d.mts
ada.mjs
adoc.d.mts
adoc.mjs
angular-expression.d.mts
angular-expression.mjs
angular-html.d.mts
angular-html.mjs
angular-inline-style.d.mts
angular-inline-style.mjs
angular-inline-template.d.mts
angular-inline-template.mjs
angular-let-declaration.d.mts
angular-let-declaration.mjs
angular-template-blocks.d.mts
angular-template-blocks.mjs
angular-template.d.mts
angular-template.mjs
angular-ts.d.mts
... 1600 moreShowing a partial view of a very large repo.
FAQ
claude-paper is a Claude Code plugin with 3 hand-picked skills for content work, indexed on Flowy. Install it with the command on its page. It includes study, summary, webui. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is claude-paper?
- Transform research papers into comprehensive learning environments A powerful Claude Code plugin that automates research paper study through intelligent material generation, code demonstrations, and an interactive web viewer.
- How do I install claude-paper?
- Run these in Claude Code: /plugin marketplace add alaliqing/claude-paper then /plugin install claude-paper@claude-paper. Then prompt normally.
- Does claude-paper auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is claude-paper free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.