alterlab-ieu/alterlab-academic-skills

⚡ Try It — One Line, the Right Skill

You don’t need to know skill names. Describe the task and alterlab-skill-finder (the front door) picks the skill for you — and tells you which one, and why.

Route — one task → one skill:

💬 “Use AlterLab skills to review my methods section.” 🧭 → alterlab-paper-reviewer (methodology-focus)

💬 “Which AlterLab skill finds and fact-checks papers on CRISPR off-target effects?” 🧭 → alterlab-deep-research + alterlab-pubmed

alterflow — a goal that spans stages → a clarified, multi-agent workflow:

💬 “alterflow — investigate the link between sleep and memory, and turn it into a publishable paper.” 🧭 → asks 2–4 scoping questions first, then plans and runs:

flowchart LR
    A["⌨️ alterflow"] --> Q{"clarify2–4 questions"}
    Q --> P["plan + confirm(with rough cost)"]
    P --> R["🔬 deep-research"]
    R --> W["📝 paper-writer"]
    W --> V["🔍 paper-reviewer"]
    V --> F["📄 final paper"]

Questions before execution — it never starts a 20-agent run blind, and simple tasks stay single-skill. Built on Anthropic’s routing and orchestrator-workers patterns.

🚀 What’s New in v2.6.0

• 🧭 New front door — alterlab-skill-finder — most users don’t know 239 skill names by heart, so this router turns “use AlterLab skills for this” into the right skill(s). It classifies the task, maps it across all 17 domains, names the concrete skill(s) it picked (and why), and applies them — no name-memorization required. → Core Pipeline
• ⚡ alterflow keyword → clarify-first multi-agent orchestration — say alterflow (aliases alterresearch / ultralab) and the router first asks a few scoping questions, then selects the skills the goal needs and launches a dynamic multi-agent workflow composing them (via alterlab-research-pipeline, alterlab-ssci-orchestrator, or alterlab-workflow-orchestration). Questions before execution — it never starts blind.
• 🗂️ Always-current skill index — a generated skill_index.md lists every skill grouped by domain with a one-line “use when”; a new CI test (test_skill_index.py) fails the build if a skill is added or renamed and the index is not regenerated (scripts/gen_skill_index.py --check).
• 📈 239 skills across 17 domains, 239 / 239 with executable evals; audit clean (0 errors, 0 warnings), full test suite green.

📋 Table of Contents

🎯 What Is This?

A comprehensive suite of 239 purpose-built Claude AI skills for faculty members, academicians, and researchers — organized into 17 domain categories spanning the full academic research lifecycle.

Each skill transforms Claude into a domain-specific expert assistant tailored to academic research, scientific computing, and scholarly publishing workflows.

[!TIP] How it works: Each skill is a structured SKILL.md file. Install the collection as a Claude Code plugin, or copy a skill directory into ~/.claude/skills/ (or a project’s .claude/skills/) — and Claude becomes your research expert, with real scientific frameworks, professional output templates, and deep domain knowledge. A loose .md file does not auto-load.

🆕 v2.0 Highlights

v2.0 is the “Trust & Reach” release — it turns the loudest objection to academic skills (“just prompts, no evals”) into the headline differentiator.

🔎 Headline feature — alterlab-citation-verifier

Around 147 k hallucinated citations surfaced in published work in 2025. Prompt-only “fact-checking” misses roughly a third of them. alterlab-citation-verifier is a deterministic core capability that, for every entry in a bibliography:

• cross-checks existence against Crossref + OpenAlex + Semantic Scholar + arXiv (all keyless),
• resolves DOIs / arXiv IDs and matches title + author with a Levenshtein threshold,
• flags Retraction Watch entries,
• maps each verdict to the suite’s TF / PAC / IH / PH / SH faithfulness taxonomy,

and degrades gracefully to plain requests / WebSearch when no MCP or network is present. It rewires the pipeline’s bibliography and integrity agents to call it instead of generic web search.

🧭 Headline feature — alterlab-skill-finder (the front door)

No one memorizes 239 skill names. alterlab-skill-finder is the front door: say “use AlterLab skills for this” and it classifies your task, maps it across all 17 domains, and applies the right skill(s) — telling you which it picked and why. For a goal that spans stages, the alterflow keyword turns it into a launcher:

• CLARIFY — asks 2–4 scoping questions before doing anything,
• SELECT & PLAN — picks the skills the goal needs and lays out a dynamic multi-agent workflow, scaling the agent count to complexity,
• CONFIRM — shows the plan and its rough cost, then executes,
• COMPOSE — reuses the existing orchestrators (alterlab-research-pipeline, alterlab-ssci-orchestrator, alterlab-workflow-orchestration) rather than reinventing them.

Built on Anthropic’s documented routing and orchestrator-workers patterns — questions before execution, simplest path by default.

✨ Key Features

🗂️ Domain Overview

🔎 Browse the Catalog

🚀 Quick Start

🎓 New here / not technical? Start in the Claude app — no terminal, no git

Skills work in claude.ai (browser) and the Claude desktop app with a plain upload — no command line:

1. In Claude, make sure code execution is on: Settings → Capabilities (Team/Enterprise: an owner enables it once for the org).
2. Open Customize ▸ Skills → claude.ai/customize/skills.
3. Click + → Create skill → Upload a skill, and choose a skill’s .zip.
4. Flip the skill’s toggle On. Now just chat normally — Claude uses the skill automatically when your request matches it.

Where do I get the .zip? No-terminal ways, easiest first:

• One skill (one click) — on the Releases page, each skill ships its own ready-to-upload skill--.zip (e.g. skill-alterlab-scanpy-2.6.0.zip). Download that one file and upload it as-is.
• A whole domain at once — download a domain bundle (e.g. alterlab-bioinformatics-.zip) from the same Releases page.
• Build it yourself (no release needed) — click the green Code ▸ Download ZIP at the top of this repo, unzip, then right-click the skill folder you want (e.g. skills/bioinformatics/alterlab-scanpy) and Compress / Zip it. Upload that zip.

[!IMPORTANT] A loose .md file dragged into a chat is not an installed skill — it must be a zip of the skill folder (with its SKILL.md inside). Only install skills from sources you trust, and note that skills you upload in the app are tied to your account and don’t sync to Claude Code.

Comfortable with a terminal or Claude Code? Pick one of the options below instead.

🌍 Option 1 — Agent Skills (open standard) (Recommended)

npx skills add AlterLab-IEU/AlterLab-Academic-Skills

These are portable Agent Skills following the agentskills.io open standard — they also work in Cursor, Codex, Gemini CLI, and Copilot, not Claude only.

[!NOTE] Standard: Agent Skills. This collection conforms to the open Agent Skills standard. See agentskills.io for the spec and the list of supporting agents.

⚡ Option 2 — Claude Code Plugin

Add the marketplace once, then install only the domains you need:

/plugin marketplace add AlterLab-IEU/AlterLab-Academic-Skills
# No SSH key? Use the HTTPS marketplace path instead:
/plugin marketplace add https://github.com/AlterLab-IEU/AlterLab-Academic-Skills.git
/plugin install alterlab-bioinformatics@alterlab-academic-skills
/reload-plugins

Each domain is its own installable plugin — install only what you need. For example, the full social-science methods spine (17 skills: orchestrator + 5 validity gates + 11 analysis modules):

/plugin marketplace add AlterLab-IEU/AlterLab-Academic-Skills
/plugin install alterlab-social-science-workflow@alterlab-academic-skills
/reload-plugins

For local development against a clone, point Claude Code at the directory directly:

claude --plugin-dir /path/to/AlterLab-Academic-Skills

Available domain plugins (17): alterlab-core, alterlab-databases, alterlab-bioinformatics, alterlab-cheminformatics, alterlab-clinical-research, alterlab-data-science, alterlab-visualization, alterlab-writing-tools, alterlab-lab-integrations, alterlab-domain-specific, alterlab-document-tools, alterlab-research-tools, alterlab-finance-economics, alterlab-turkish-academia, alterlab-faculty-life, alterlab-methodology, alterlab-social-science-workflow.

📁 Option 3 — Personal or Project Install (manual)

git clone https://github.com/AlterLab-IEU/AlterLab-Academic-Skills.git
# Personal — available in every project:
cp -R AlterLab-Academic-Skills/skills/bioinformatics/alterlab-scanpy ~/.claude/skills/
# Project-scoped — only in the current repo:
cp -R AlterLab-Academic-Skills/skills/bioinformatics/alterlab-scanpy .claude/skills/

Then restart Claude Code. A skill must live at ~/.claude/skills//SKILL.md or .claude/skills//SKILL.md — a bare git clone alone does not register anything.

🌐 Option 4 — Claude.ai (per-domain bundles)

Every Release ships pre-built dist/.zip bundles. Each is spec-conformant and clears claude.ai’s 200-file / 30 MB caps, and vendors the shared handoff contracts so cross-skill references resolve.

1. Download the domain bundle you need from the Releases page — e.g. bioinformatics.zip, databases.zip, core.zip.
2. In Claude, open Customize ▸ Skills (claude.ai/customize/skills) → + → Create skill → Upload a skill, then pick the zip (requires code execution enabled under Settings → Capabilities). See the no-terminal walkthrough above.

Skills do not sync between claude.ai and Claude Code. To zip a single skill yourself instead, archive its directory (zip -r alterlab-scanpy.zip skills/bioinformatics/alterlab-scanpy).

🛠️ Option 5 — install.sh (scriptable local install)

The bundled installer copies whole domains and/or individual skills into the right local directory (~/.claude/skills/ or the cross-tool ~/.agents/skills/), idempotently:

git clone https://github.com/AlterLab-IEU/AlterLab-Academic-Skills.git
cd AlterLab-Academic-Skills

scripts/install.sh --list                         # show every domain / skill
scripts/install.sh bioinformatics                 # whole domain
scripts/install.sh databases/alterlab-pubmed      # one skill
scripts/install.sh --project core                 # into ./.claude/skills
scripts/install.sh                                 # install everything

Then restart your agent to load them.

🔌 MCP & Slash Commands

The core and databases plugins ship a .mcp.json that wires the PubMed / OpenAlex / Crossref / Zotero academic MCP servers, with a documented requests/ fallback when no MCP host is available — so the citation verifier and database skills work online or offline. Install either plugin (Option 2) to pick the MCP up automatically.

Installing the core plugin also registers these slash commands:

[!NOTE] 239 / 239 skills ship executable evals on the canonical agentskills.io schema. Schema and trigger-coverage are validated in CI on every PR; the behavioral pass (claude CLI + LLM judge) runs on demand via workflow_dispatch and nightly over a rotating 1/7 shard, so the whole corpus is behaviorally judged across each week. An --activation harness additionally measures auto-selection rate against Anthropic’s 90% bar, and scripts/confusion_matrix.py statically ranks cross-firing risk between sibling skills. See docs/evals.md.

Trust & portability signals (all generated + CI-enforced): SECURITY_SCAN.md — outbound-host allowlist + a no-shell-pipe / no-eval-on-input / no-hardcoded-secrets attestation; docs/portability.md — what transfers to Codex/Cursor/Gemini vs. Claude-Code-specific; docs/agents-and-teams.md — the 35 pipeline subagents and the teams they compose.

---

⚡ Core Pipeline — 10 Skills

The heart of the system — a multi-agent research-to-publication pipeline with 35 specialized agents, plus teaching and thesis supervision tools.

---

📚 All 239 Skills

🗄️ Databases — Scientific Database Connectors (39 Skills)

🧬 Bioinformatics — Genomics, Proteomics & Molecular Biology (30 Skills)

⚗️ Cheminformatics — Chemistry & Drug Discovery (12 Skills)

🏥 Clinical Research — Clinical Decision Support & Medical Tools (7 Skills)

📊 Data Science — ML, Statistics & Data Analysis (22 Skills)

📈 Visualization — Scientific Plotting & Graphics (8 Skills)

✍️ Writing Tools — Scientific Writing, Citations & Publishing (13 Skills)

🔧 Lab Integrations — Laboratory Platform Connectors (9 Skills)

🌍 Domain-Specific — Quantum, Geospatial, Materials, Social Science & More (17 Skills)

📄 Document Tools — Markdown & Document Conversion (2 Skills)

🔍 Research Tools — Search, Discovery, Methods & Reference Management (14 Skills)

💰 Finance & Economics — Financial Data & Analysis (7 Skills)

🇹🇷 Turkish Academia — National Platforms & Scholarly Workflow (12 Skills)

🎓 Faculty Life — Teaching, Service & the Academic Career (6 Skills)

🧪 Methodology — Research Rigor & Discipline Gates (3 Skills)

🧭 Social-Science Workflow — Stage-Gated Methods Spine (17 Skills)

---

🏗️ Project Structure

AlterLab-Academic-Skills/
├── 📁 skills/                       # 239 skills across 17 domains
│   ├── 🔄 core/                # 10 pipeline + citation-verifier + teaching + thesis + skill-finder
│   ├── 🗄️ databases/           # 39 database connectors
│   ├── 🧬 bioinformatics/      # 38 bio/genomics tools
│   ├── ⚗️ cheminformatics/     # 12 chemistry/drug discovery
│   ├── 🏥 clinical-research/   # 7 clinical/medical tools
│   ├── 📊 data-science/        # 22 ML/statistics tools
│   ├── 📈 visualization/       # 9 plotting/charting tools
│   ├── ✍️ writing-tools/       # 13 scientific writing & career tools
│   ├── 🔧 lab-integrations/    # 9 lab platform connectors
│   ├── 🌍 domain-specific/     # 18 specialized field tools
│   ├── 📄 document-tools/      # 3 file format tools
│   ├── 🔍 research-tools/      # 14 search, methods & ethics tools
│   ├── 💰 finance-economics/   # 7 financial/economic tools
│   ├── 🇹🇷 turkish-academia/    # 12 Turkish national-platform & workflow skills
│   ├── 🎓 faculty-life/        # 6 teaching, service & career skills
│   ├── 🧪 methodology/         # 3 research-rigor discipline gates
│   └── 🧭 social-science-workflow/  # 17: orchestrator + 5 gates + 11 analysis modules
├── 📁 dist/                          # per-domain .zip bundles for claude.ai (built on release)
├── 📁 scripts/                       # install.sh, gen_catalog.py, run_evals.py, audit_skills.py …
├── 📁 docs/                          # evals, integrity & design docs
├── 📄 skills.json                    # generated machine-readable catalog
├── 📄 README.md                      # This file
├── 📄 CLAUDE.md                      # Project instructions
├── 📄 CONTRIBUTING.md                # Contribution guidelines
├── 📄 THIRD_PARTY_NOTICES.md         # Upstream / K-Dense provenance
└── 📄 LICENSE                        # MIT License

⚙️ How Skills Work

Each .md skill file follows a consistent structure:

| name          | description                         |
|---------------|-------------------------------------|
| skill-name    | When to activate this skill...      |

# Skill Title

You are **RoleName**, a [role description]...

## Your Identity & Memory
## Your Core Mission
## Frameworks & Methods
## Output Templates
## Quality Standards

[!NOTE] Pro tip: Combine multiple skills in one Claude Project for a multi-expert team. For example, load Deep Research + Paper Writer + Paper Reviewer for a complete research-to-publication workflow.

💡 Usage Examples

Skills activate automatically based on user intent:

---

⚖️ How It Compares

Counts verified against skills.json; K-Dense figure is the upstream project’s own self-reported count. anthropics/skills is Anthropic’s official example collection, scoped to general-purpose demonstrations rather than a fixed academic catalog.

🔗 Sister Projects

• AlterLab-FC-Skills — 72 agentic skills for communication students
• AlterLab_GameForge — 34 game dev skills from concept to launch

🤝 Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

Quick ways to contribute:

• 🛠️ Improve an existing skill with better frameworks or templates
• ✨ Create a new skill following the structure above
• 🐛 Report issues or suggest improvements
• 📚 Add examples or use cases to documentation

📖 Cite This Repository

If AlterLab Academic Skills supports your research or teaching, please cite it. A machine-readable CITATION.cff ships in the repo, so GitHub’s “Cite this repository” button and most reference managers can import it automatically. The suite is a content fork of K-Dense’s scientific-agent-skills (MIT) — see THIRD_PARTY_NOTICES.md and PROVENANCE.md for full provenance.

@software{alterlab_academic_skills_2026,
  title   = {AlterLab Academic Skills},
  author  = {{AlterLab Creative Technologies Laboratory, Izmir University of Economics (IEU)}},
  year    = {2026},
  version = {2.1.0},
  license = {MIT},
  url     = {https://github.com/AlterLab-IEU/AlterLab-Academic-Skills}
}

📜 License

This project is licensed under the MIT License.

MIT License — Copyright (c) 2026 AlterLab Creative Technologies Laboratory

🙏 Credits