Qinyan Academic Skills packages reusable research skills for academic workflows, from paper search and citation work to scientific writing, review, figures, and statistics. The repository is split into skill categories under `skills/`, with an installer that can target a whole library, one category, or one named skill.
Builders who use agent tools to search papers, draft manuscripts, polish academic prose, and prepare submission materials.
You can add reusable academic workflows to your agent instead of rebuilding research prompts and steps from scratch.
Provides five composable skills for drafting, polishing, pre-submission review, figures, and statistics.
Lets you install the full library, one category, one skill, or a project-local copy.
Works with Claude Code, Cursor, Codex, Gemini CLI, OpenClaw, and OpenCode through one installer.
Supports listing, searching, status checks, update checks, and updates through `install.sh`.
Includes English, Chinese, Japanese, and Korean README files and multilingual skill organization.
curl -fsSL https://raw.githubusercontent.com/LeonChaoX/qinyan-academic-skills/main/install.sh | bash
git clone https://github.com/LeonChaoX/qinyan-academic-skills.git cd qinyan-academic-skills bash install.sh --help
187 installable AI agent skills for academic research, featuring a first-party Nature-style suite for scientific writing, manuscript polishing, peer review, publication figures, and statistics.
English · 简体中文 · 繁體中文 · 日本語 · 한국어
Qinyan Academic Skills equips Claude Code, Codex, Cursor, Gemini CLI, OpenClaw, and OpenCode with reusable research capabilities. The repository contains 187 skills across 18 domains, including a five-skill workflow for Nature-style scientific writing, academic editing, pre-submission review, scientific visualization, and statistical reporting.
Use the complete collection or install only the skill, category, tool, and scope that your workflow needs.
Move from a defensible scientific claim to a submission-ready manuscript with five focused, composable skills:
| Manuscript stage | Skill | Primary output |
|---|---|---|
| Argument and drafting | qinyan-nature-writing | Evidence-led narrative, section drafts, title, abstract, and submission package |
| Structural and language revision | qinyan-nature-polishing | Concise academic prose with meaning-preservation and anti-overclaim checks |
| Pre-submission assessment | qinyan-nature-review | Prioritized, traceable review findings with stable issue identifiers |
| Figures and visual evidence | qinyan-nature-figures | Reproducible multi-panel figures with export and preflight validation |
| Study design and statistics | qinyan-nature-statistics | Estimand-aware analysis plans, reporting audits, and figure-ready results |
Install one skill:
curl -fsSL https://raw.githubusercontent.com/LeonChaoX/qinyan-academic-skills/main/install.sh \
| bash -s -- --skill qinyan-nature-writing
Or explore the complete Nature skills workflow, including routing guidance, installation commands, quality gates, and example prompts.
[!NOTE] “Nature-style” describes editorial and scientific communication goals. This independent project is not affiliated with, endorsed by, or guaranteed acceptance by Nature Portfolio or Springer Nature.
| Capability | What you get |
|---|---|
| Research coverage | 187 skills spanning literature, writing, life sciences, AI, statistics, databases, and laboratory workflows |
| Agent portability | One installer for Claude Code, Cursor, Codex, Gemini CLI, OpenClaw, and OpenCode |
| Selective installation | Install the full library, one category, or one named skill |
| Project isolation | Choose global installation or keep skills inside a single project |
| Lifecycle management | Search, inspect status, check for updates, and update installed skills |
| Version-controlled source | Every skill is plain text, reviewable, portable, and easy to customize |
The default target is the global Claude Code skills directory.
curl -fsSL https://raw.githubusercontent.com/LeonChaoX/qinyan-academic-skills/main/install.sh | bash
[!NOTE] The installer requires Bash, Git, and
curl. On Windows, run it in WSL or Git Bash. Reviewinstall.shbefore piping it to Bash if your environment requires source inspection.
INSTALLER="https://raw.githubusercontent.com/LeonChaoX/qinyan-academic-skills/main/install.sh"
# Install one category
curl -fsSL "$INSTALLER" | bash -s -- --category 01
# Install one skill
curl -fsSL "$INSTALLER" | bash -s -- --skill scanpy
# Install into the current project instead of globally
curl -fsSL "$INSTALLER" | bash -s -- --project --skill scientific-writing
# Target another supported agent
curl -fsSL "$INSTALLER" | bash -s -- --tool codex
Short forms such as -c, -s, and -t are also supported. Run bash install.sh --help for the complete command reference.
# Browse and search
bash install.sh --list
bash install.sh --list-skills
bash install.sh --search "protein"
# Inspect and update
bash install.sh --status
bash install.sh --check-update
bash install.sh --update
bash install.sh --update --skill scanpy
git clone https://github.com/LeonChaoX/qinyan-academic-skills.git
cd qinyan-academic-skills
bash install.sh --help
| Agent | --tool value | Global directory | Project directory |
|---|---|---|---|
| Claude Code | claude (default) | ~/.claude/skills/ | .claude/skills/ |
| Cursor | cursor | ~/.cursor/skills/ | .cursor/skills/ |
| Codex | codex | ~/.codex/skills/ | .codex/skills/ |
| Gemini CLI | gemini | ~/.gemini/skills/ | .gemini/skills/ |
| OpenClaw | openclaw | ~/.openclaw/skills/ | .openclaw/skills/ |
| OpenCode | opencode | ~/.config/opencode/skills/ | .opencode/skills/ |
Each category links directly to its source directory. Use --list-skills for the complete list or --search <term> to discover skills by name and description.
| ID | Category | Skills | Focus |
|---|---|---|---|
| — | Qinyan Academic skills | 10 | Paper search, analysis, citations, and Nature-focused writing, review, figures, and statistics |
| 01 | Literature discovery and reference management | 10 | Scholarly search, reviews, citation workflows, and literature databases |
| 02 | Scientific writing and communication | 6 | Manuscripts, peer review, research proposals, and venue templates |
| 03 | Academic presentation and visualization | 9 | Slides, posters, schematics, infographics, and scientific figures |
| 04 | Research methods and scientific reasoning | 10 | Hypotheses, critical thinking, brainstorming, evaluation, and grants |
| 05 | Bioinformatics and genomics | 21 | Sequences, single-cell analysis, regulatory networks, and variants |
| 06 | Cheminformatics and drug discovery | 12 | Molecular processing, docking, medicinal chemistry, and simulation |
| 07 | Clinical medicine and precision health | 18 | Trials, clinical reports, imaging, variants, and decision support |
| 08 | Protein engineering and structural biology | 7 | Protein language models, structures, domains, and sequence resources |
| 09 | Machine learning and artificial intelligence | 14 | Deep learning, classical ML, forecasting, optimization, and explainability |
| 10 | Materials science and computational physics | 10 | Materials, quantum computing, astronomy, fluids, and simulation |
| 11 | Data analysis and statistical modeling | 11 | Dataframes, statistics, visualization, graphs, and symbolic mathematics |
| 12 | Scientific databases | 22 | Chemistry, genes, proteins, pathways, populations, and patents |
| 13 | Laboratory automation and integrations | 9 | ELNs, cloud labs, robotics, imaging, and workflow platforms |
| 14 | Documents and data tools | 7 | PDF, Word, PowerPoint, spreadsheets, notebooks, and conversion |
| 15 | Finance and economic data | 6 | Markets, filings, fiscal data, economic series, and research reports |
| 16 | Geospatial analysis and remote sensing | 2 | GIS, satellite imagery, spatial analysis, and remote sensing |
| 17 | Platforms and infrastructure | 3 | Resource discovery, cloud compute, and ISO 13485 readiness |
| Skill | Purpose |
|---|---|
qinyan-paper-search | Search Google Scholar, PubMed, arXiv, and Wanfang through the Qinyan Academic OpenAPI |
qinyan-paper-analysis | Produce structured, in-depth analysis of individual academic papers |
qinyan-paper-polish | Improve Chinese and English academic prose while preserving meaning |
qinyan-citation | Discover sources and format citations in common academic styles |
qinyan-topic-analysis | Evaluate research topics, evidence landscapes, and promising directions |
qinyan-nature-writing | Build evidence-led manuscript arguments, sections, and initial-submission materials |
qinyan-nature-polishing | Restructure, translate, and polish academic prose without changing scientific meaning |
qinyan-nature-review | Run traceable pre-submission review through conceptual, technical, and evidence lenses |
qinyan-nature-figures | Design, export, and preflight reproducible publication figures |
qinyan-nature-statistics | Plan, analyse, audit, and report design-aware manuscript statistics |
| Goal | Recommended starting points |
|---|---|
| Literature search and evidence mapping | qinyan-paper-search, openalex-database, pubmed-database, literature-review |
| Manuscript drafting and revision | qinyan-nature-writing, qinyan-nature-polishing, qinyan-nature-review, venue-templates |
| Grant and proposal development | nsfc-proposal, nssfc-proposal, research-grants, research-proposal |
| Academic slides and posters | paper-slide-deck, scientific-slides, latex-posters, pptx-posters |
| Bioinformatics and omics | biopython, scanpy, pydeseq2, scvi-tools, gget |
| Drug discovery and molecular modeling | rdkit, deepchem, diffdock, molecular-dynamics, rowan |
| Statistical analysis and visualization | statistical-analysis, statsmodels, polars, plotly, seaborn |
| Clinical and precision medicine | clinical-decision-support, clinicaltrials-database, clinvar-database, pydicom |
[!TIP] Start with one focused skill, inspect its
SKILL.md, and combine skills only when the research workflow genuinely needs multiple capabilities.
install.sh --help — complete CLI options and examplesskills/ — canonical source for every skillThis collection combines first-party Qinyan Academic skills with carefully organized skills derived from the following open-source projects:
Attribution and license metadata for an individual skill remain in that skill's SKILL.md.
Contributions that improve skills, translations, documentation, and installer compatibility are welcome.
mainSKILL.md as its entry pointWhen changing shared facts such as counts, supported tools, or CLI flags, update all five README files in the same pull request.
The repository is distributed under the MIT License. Individual skills may declare additional or different terms in their SKILL.md; review those terms before redistribution or commercial use.
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
Public repository for Agent Skills
Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
A skill to stop your coding agent from burying the answer. ADHD-friendly output.