semanticscholar-skill
Health Gecti
- License — License: MIT
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Community trust — 34 GitHub stars
Code Gecti
- Code scan — Scanned 2 files during light audit, no dangerous patterns found
Permissions Gecti
- Permissions — No dangerous permissions requested
Bu listing icin henuz AI raporu yok.
Semantic Scholar API wrapper for agents — search 200M+ papers, traverse citations, find authors. Python, rate-limited, multi-agent.
semanticscholar-skill — the easiest way to search the scientific literature 📚
English · 中文
External references: Semantic Scholar API Tutorial · API Docs · Request API Key
A skill that turns the Semantic Scholar academic graph (200M+ papers across arXiv + bioRxiv + PubMed + journals + conferences) into a single-script, rate-limited, agent-friendly toolkit.
- Search by keyword, boolean expression, full-text snippet, exact title, or author
- Traverse forward / backward citations and find similar or recommended papers
- Filter by year, venue, fields of study, min citations, open access, pub types
- Export to BibTeX, Markdown, or JSON
- Built-in correctness — automatic rate limiting, exponential backoff, single-script execution
Works with Claude Code, Codex, Hermes, OpenClaw, ClawHub, and SkillsMP — any agent that supports the Agent Skills format.
🔄 How it works
The skill picks the right endpoint for the user's intent (keyword search, citation traversal, recommendations, author lookup), runs the call through the rate-limited s2.py helper with exponential backoff, applies filters (year / venue / fields of study / min citations / open access), and returns results ready to export to BibTeX, Markdown, or JSON.
Documentation
| Doc | What's inside |
|---|---|
| docs/features.md | Why Semantic Scholar, full feature list, comparison vs. arXiv / bioRxiv / asta-skill / native agents |
| docs/api-reference.md | s2.py helper module API, usage examples |
| docs/limitations.md | Prerequisites, API key setup, known limitations |
| docs/tutorial.md | End-to-end tutorial |
| skills/semanticscholar-skill/SKILL.md | Workflow guide loaded by the agent |
Quick Start
# Recommended — set an API key for a dedicated quota
export S2_API_KEY=xxxxxxxxxxxxxxxx
# Install dependencies
pip install requests
Install the skill:
# Any agent (Claude Code, Cursor, Copilot, etc.)
npx skills add Agents365-ai/365-skills -g
# Claude Code only
> /plugin marketplace add Agents365-ai/365-skills
> /plugin install semanticscholar
Also published on SkillsMP and ClawHub — each handles updates through its own marketplace.
Usage
Just describe what you want:
> Use semanticscholar-skill to search for recent mixture-of-experts papers at NeurIPS since 2023
> Find papers citing "Attention Is All You Need" and rank by citation count
> Recommend papers similar to DOI:10.1038/nature14539, excluding NLP
> Export the top 10 results to BibTeX
See docs/api-reference.md for more examples and the helper module reference.
🔗 Related Skills
Part of the Agents365-ai research-skill family — pick the right tool for the job:
| Skill | Niche | When to use |
|---|---|---|
| asta-skill | Same corpus via Ai2 Asta MCP | When your host supports MCP and you have an Asta API key |
| paper-fetch | DOI → PDF, 7-source fallback | When you already have IDs and need the actual full text |
| scholar-deep-research | 8-phase literature review pipeline | When the user wants a structured cited report, not just search results |
| zotero-research-assistant | Zotero library workflows | When the user manages references in Zotero |
💬 Community
- Discord: https://discord.gg/79JF5Atuk
- WeChat: scan the QR code below
❤️ Support
If this skill helps you, consider supporting the author:
WeChat Pay |
Alipay |
Buy Me a Coffee |
Give a Reward |
👤 Author
Agents365-ai
- GitHub: https://github.com/Agents365-ai
- Bilibili: https://space.bilibili.com/441831884
📄 License
Yorumlar (0)
Yorum birakmak icin giris yap.
Yorum birakSonuc bulunamadi