A comprehensive research integration for searching academic databases, parsing PDFs, and generating structured markdown analyses of scientific papers.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install swiftscholar-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install swiftscholar-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is SwiftScholar Skill?
The SwiftScholar skill is a sophisticated integration designed to bridge the gap between AI agents and the vast world of academic literature. By utilizing the SwiftScholar HTTP API, this skill allows users to perform high-level research tasks programmatically. It is a core component for researchers using Openclaw Skills who need to move beyond simple web searches and into structured, semantic discovery of peer-reviewed content.
This skill excels at transforming unstructured academic data into actionable insights. It provides tools for keyword and vector-based searching, handles complex PDF parsing, and returns structured markdown that is easy for AI agents to process. Whether you are building a literature review bot or a personal knowledge management system, this skill provides the necessary endpoints to manage papers, folders, and analysis models efficiently.
SwiftScholar Skill Use Cases
- Conduct semantic vector searches to find papers related to complex research concepts rather than just keywords.
- Automatically submit and parse paper URLs or PDF files to extract structured markdown summaries.
- Organize discovered research into a hierarchical system of favorite folders with custom notes.
- Generate dual-language (English and Chinese) summaries of technical papers for better accessibility.
- Track research quotas and parse history to manage API usage across large-scale data extraction projects.
How SwiftScholar Skill Works
- The skill authenticates with the SwiftScholar backend using a Bearer token provided in the HTTP headers.
- Users initiate a request for either a literal keyword search or a fuzzy semantic vector search.
- The agent identifies relevant papers and can trigger a submission process for new URLs or local PDFs.
- SwiftScholar processes the document, applying chosen analysis models to generate structured markdown output.
- The agent retrieves the analyzed data, allowing for further synthesis, summarization, or storage in the user's favorites library.
SwiftScholar Skill Setup
To integrate this skill, you must obtain an API key from the SwiftScholar platform. This key should be handled securely and never exposed in natural language responses.
# Example of setting the required environment variable
export SWIFTSCHOLAR_API_KEY="your_secure_api_token"
All calls should be directed to the base URL https://www.swiftscholar.net using the /api/tools/* path prefix. Ensure your Openclaw Skills configuration includes the proper Authorization header for all POST requests.
SwiftScholar Skill Data Schema & Taxonomy
The skill organizes data around paper entities and user libraries. Below is the primary data structure for paper interactions:
| Object | Key Fields | Purpose |
|---|---|---|
| Paper Metadata | paperId, title, publishedAt, tags |
Basic identification and filtering |
| Search Result | data, total, page |
Paginated lists of discovered literature |
| Analysis | markdown, language, scope |
Structured content extraction |
| Account | parseQuota, points, consumeUnits |
Resource management and usage tracking |
| Favorites | folderId, favoriteNote, includeDescendants |
Library organization and personal taxonomy |
SwiftScholar Skill Advanced Features
- Vector Search Capability: Move beyond exact matches to find papers based on conceptual similarity using modern embedding techniques.
- Multipart PDF Uploads: Support for direct binary file uploads for parsing local research papers without public URLs.
- Multi-Model Analysis: Select from different PDF analysis models based on the required depth of extraction and point cost.
- Batch Processing: Submit multiple URLs simultaneously to build research datasets rapidly within Openclaw Skills.
- Tag-Based Filtering: Refine search results using complex tag logic (AND/OR) to narrow down specific academic domains.
SKILL.md
Loading
Related Openclaw Skills
OPC (One-Person Company) Framework
A comprehensive 14-skill AI agent framework designed to help solo entrepreneurs manage the entire business lifecycle from ideation to operations.
World Model for AGI
A production-grade environment understanding and causal reasoning engine designed for high-performance AGI simulations and decision support.
Unified Reasoning Engine
A high-performance reasoning engine that automatically selects the best logic strategy for AI agents with parallel execution and intelligent caching.
Tree of Thoughts Reasoning
An advanced reasoning skill for Openclaw Skills that explores multiple solution branches, evaluates them based on custom criteria, and selects the most optimal path.
Exa MCP Web Search
A powerful research skill that integrates Exa MCP for targeted web discovery and person-centric data retrieval.
Google Video URL Analysis
Analyze public video URLs directly with Google Gemini models for instant summarization and data extraction.
Featured*
