AMiner Research Skills plugin
Official AMiner skills: search over 29 APIs, review paper collection, PDF parsing, SOTA tables and cited reports
- 78 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Skills send requests to AMiner servers with your token and spend paid quotas
- The PDF to Markdown skill sends the paper file to an external service
Install
- Works in
Manual install
/plugin marketplace add AMinerOrg/aminer-research-skillsThen `/plugin install aminer-free-academic@aminer-research-skills`. The token goes into `AMINER_API_KEY`.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Skills send requests to AMiner servers with your token and spend paid quotas
- The PDF to Markdown skill sends the paper file to an external service
This is third-party code. Review the repository files before installing.
What it does
The AMiner repository gathers skills for research on AMiner platform data: real publications, a traceable evidence chain and ready artifacts. Seven workflows open on the AMiner site with no install: paper writing and revision, deep reading, experiment analysis, grant applications, topic and advisor selection, thesis and patent and technology intelligence. The other 15 skills install into Claude Code, Codex or OpenClaw. The local set includes free search of papers, scholars, institutions, journals and patents (`aminer-free-academic`), full data access through 29 APIs (`aminer-academic-search`), paper recommendations by topic or scholar profile, collection of hundreds of papers for a review (`aminer-deep-search`), SOTA result search with a table and sources, PDF to Markdown conversion, experiment extraction to JSON, a classification tree, tracing claims to their sources and `deep-research` for a report with citations. Installation is `npx skills add AMinerOrg/aminer-research-skills --agent claude-code --skill aminer-free-academic --yes`, and Claude Code has a plugin variant with commands. A token is issued in the AMiner console and placed in the `AMINER_API_KEY` variable.
Who it is for. Researchers, graduate students and review authors who want papers, authors and results from an academic database inside a conversation with an agent.
Good fit when
- A review needs a few hundred candidate papers on a topic collected and filtered
- You need the best results (SOTA) for a task as a table with source links
- A paper PDF must become Markdown with experiments extracted to JSON
- A claim in the text needs tracing to its source and a citation graph built
Not a fit when
- You need search with no platform registration: most skills require an AMiner token
- You need data from outside AMiner: the skills are built on its API and database
- You need an English-only install flow: the main docs are in Chinese and the English ones live in separate files
Example request
Collect about 300 papers on agentic RAG for a review, pick the best and show a SOTA table with sourcesLimitations
Most skills need an AMiner token from the open platform console in the `AMINER_API_KEY` variable, and billing rules are described in the install guide. Node.js 18 or newer is required, some skills need Python dependencies and OpenClaw needs separate setup. Seven workflows exist only on the AMiner site, while the other 15 install locally. The main README is in Chinese with an English version in `README.en.md` and `INSTALL.en.md`. Data comes from AMiner servers, so search quality depends on the coverage of that database.
How to disable. For Claude Code run `/plugin uninstall aminer-free-academic@aminer-research-skills`. Skills installed through `npx skills` are removed from the agent skill folder, and the token should be removed from the environment variable.
FAQ
How many skills are in the set?
22 in total: seven workflows open on the AMiner site with no install and 15 install into Claude Code, Codex or OpenClaw.
Which skill should I start with?
`aminer-free-academic`: it searches papers, scholars, institutions, journals and patents for free. The full data set comes with `aminer-academic-search` and its 29 APIs.
Is a token required?
Yes, for most skills: create it in the AMiner console and put it in `AMINER_API_KEY`. Billing is described in `INSTALL.md`.
How do I install it as a plugin in Claude Code?
With `/plugin marketplace add AMinerOrg/aminer-research-skills` and `/plugin install aminer-free-academic@aminer-research-skills`. The plugin also registers the skill slash commands.
Can the set parse PDFs?
Yes, the `aminer-pdf-ocr` skill converts a paper PDF to Markdown and `aminer-exp-extraction` pulls experiment information from it into JSON.
Discussion
No questions or reviews yet.
Related
PluginsA library of 280+ research skills: literature search, experiment design, analysis, reference checks and paper preparation
A skill for master and PhD students that runs research through novelty and reality gates, from review to claim checks
A marketplace of five Claude Code plugins for researchers: literature search, research design, project memory and manuscript work
A zero-key, zero-dependency skill and CLI that turns PDF, Office and image files into Markdown via MinerU's cloud.
AlterLab Academic Skills bundles 241 research skills: literature review, manuscripts, citation checks, statistics, databases
A Claude Code skill for scientific literature reviews: an interview, Scopus and OpenAlex search, DOI checks and a final docx file
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| AMiner Research Skills (this card) | yes | 78 | |
| Scientific Agent Skills | no | 56,977 | 166 skills for science on open databases |
| PaperPRISM | no | 109 | Codex skills for a scientific paper with a LaTeX draft |
README in short
The main README, in Chinese, presents the set as skills for the whole research cycle on AMiner data. A table of seven online workflows, a list of 15 local skills by category, quick installation with token setup and a link to the guide follow.