Is databases safe to install?

SaferSkills independently audited databases (MCP Server) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

README.md · 1 file

README.md64.0 KB · Markdown

📢 Featured in awesome-claude-skills (5.7k ⭐)

Read in: English · Türkçe

<h3>🧬 242 purpose-built Claude AI skills for faculty, researchers & academicians</h3> Organized across 18 research domains — from Turkish academia to bioinformatics to digital humanities 242/242 ship executable evals · deterministic citation-existence verifier · per-domain bundles for claude.ai

🧩 New in v3.0 — runnable multi-agent research workflows for Claude Code: <code>/alterlab-workflows:citation-audit</code>, <code>review-panel</code>, PRISMA dual screening, rebuttal, grant mock panel · tuned for Claude Opus 5.5 🧭 Don't know which skill? Just say "use AlterLab skills" and Claude picks it for you · type <code>alterflow</code> to launch a clarified multi-agent run

Research Pipeline · Scientific Databases · Bioinformatics · Data Science · Visualization · Clinical Research · and more

<a href="skills/">Explore Skills »</a> · <a href="#-quick-start">Quick Start</a> · <a href="#%EF%B8%8F-domain-overview">Domain Overview</a> · <a href="CONTRIBUTING.md">Contributing</a> · <a href="https://github.com/AlterLab-IEU/AlterLab-Academic-Skills/issues">Report Bug</a>

<hr>

<table><tr><td> Built by <a href="https://github.com/AlterLab-IEU">AlterLab Creative Technologies Laboratory</a> Not tied to any specific university — these skills work for any researcher, anywhere. </td></tr></table>

</div>

<div align="center"> <table> <tr> <td align="center" width="25%"> <h3>🎯</h3> <h3>Plug & Play</h3> Drop a <code>.md</code> skill file into Claude Projects or Claude Code and get instant expertise </td> <td align="center" width="25%"> <h3>🧠</h3> <h3>Domain Expert</h3> Each skill transforms Claude into a specialized research assistant with deep knowledge </td> <td align="center" width="25%"> <h3>🔬</h3> <h3>Real Frameworks</h3> Built on actual scientific methods, tools, and professional output templates </td> <td align="center" width="25%"> <h3>🌐</h3> <h3>Universal</h3> Works for any researcher at any institution — no vendor lock-in </td> </tr> </table> </div>

⚡ 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{"clarify<br/>2–4 questions"}
    Q --> P["plan + confirm<br/>(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.

Packaged workflows — one command, many independent agents (Claude Code):

💬 /alterlab-workflows:citation-audit thesis/main.tex 🧩 → every reference resolved against Crossref / OpenAlex / Semantic Scholar / arXiv, every cited claim checked against its source, and every flag re-checked by two independent agents before it reaches the report.

💬 "Run the AlterLab systematic-review-screening workflow on records.ris for my question on nurse burnout." 🧩 → codebook → de-duplication → two blinded screeners per record → adjudication → PRISMA 2020 flow + Cohen's κ computed in code.

🚀 What's New in v3.0.0

🧩 New plugin — `alterlab-workflows`: seven runnable multi-agent research workflows. Claude Code can now run dynamic workflows — scripts that orchestrate many subagents — and plugins can ship them. AlterLab now ships seven, each with the independence and adversarial checks its task needs and with counts, votes, and agreement statistics computed in code: `citation-audit` (whole-manuscript existence + claim-faithfulness, every flag re-checked twice), `review-panel` (blind reviewers chosen for the paper, each major concern re-read against the text), `claim-stress-test`, `systematic-review-screening` (PRISMA 2020 dual screening + κ), `rebuttal` (point-by-point, never invents results), `grant-mock-panel` (the funder's own criteria and scale — NIH, NSF, ERC, TÜBİTAK), and `literature-map`. A portable skill runs the same stages as playbooks on claude.ai. → Research Workflows
📦 One-step installs — alterlab-essentials (a six-plugin faculty starter kit) and alterlab-complete (every domain) are dependency bundles: one /plugin install pulls in the rest.
🔧 Plugin install fixes — in v2.6.x alterlab-core could not be installed from the marketplace (agent directories in its manifest) and alterlab-social-science-workflow installed but failed to load (conflicting manifests). Both are fixed, verified with claude plugin validate and real installs, and pinned by new tests. The bundled OpenAlex / Crossref / Zotero MCP servers prompt for their credentials through userConfig, are pinned to versions verified to start, and take an optional OpenAlex API key — OpenAlex now meters keyless use per IP and ignores the old mailto. The third-party PubMed server, which crashed at launch under a new mcp release and refused to start without an email, is gone; PubMed stays available through the alterlab-pubmed skill, which calls NCBI directly.
🧠 Tuned for Claude Opus 5.5 — the ALTERLAB_MODEL default is claude-opus-5-5; OpenRouter slugs are derived from it (the old anthropic/claude-opus-4-8 literal was not a valid slug); scripts follow the current request shape (adaptive thinking, explicit effort, no sampling parameters, no prefill, no forced tool choice); prompts are restated at normal volume for models that follow instructions literally.
🔬 Every skill re-verified against September 2026 releases — library versions, removed APIs, moved endpoints, standards, and funder rules, checked at primary sources and by running the code. The pass found real bugs: a citation verifier that let hijacked DOIs and fabricated references through, scripts that silently truncated results or computed wrong numbers (gnomAD's LOEUF cutoff, DepMap's mutation coding, areas measured in Web Mercator, PennyLane energies in the wrong unit), and services that moved or retired (USPTO, GWAS Catalog, COSMIC, Sherpa Romeo). Every skill now carries a Does NOT Trigger routing table. → CHANGELOG
🌍 Language-neutral research pipeline — bilingual abstracts are English plus the author's language (Turkish, Traditional Chinese, …) instead of a hard-wired zh-TW; the literature strategist also searches TR Dizin, DergiPark, and YÖK Tez; Turkish trigger phrases route to the right skill.
🧭 Orchestration docs brought current — nested subagents, fork mode, and dynamic workflows in alterlab-workflow-orchestration; alterlab-skill-finder launches a packaged workflow when one fits. Maintainers get /skill-freshness-audit, a workflow that repeats this re-verification pass.
🧾 New skills and deeper Turkish-academia coverage — `alterlab-ai-use-disclosure` drafts generative-AI disclosure statements (EN + TR) for manuscripts, grants, peer review, and theses against policies verified today (ICMJE, the major publishers, NIH, NSF, UKRI, ERC, TÜBİTAK, YÖK, EU AI Act Art. 50) and flags uses a venue forbids; `alterlab-tubitak-bideb` matches researchers to TÜBİTAK BİDEB fellowships and travel support and pre-screens their eligibility gates; alterlab-tubitak-proposal adds 3501; and alterlab-docentlik-eligibility now pre-screens all 12 ÜAK temel alanlar (it modelled only Sağlık), from ÜAK's own 2026 Mart tables. → Turkish Academia
⚖️ Licensing corrected — the four core pipeline skills adapted from a CC-BY-NC 4.0 upstream now declare that licence (they said MIT), and each plugin manifest states the SPDX licence of its skills (alterlab-core: MIT AND CC-BY-NC-4.0); alterlab-mermaid credits its Apache-2.0 source. → THIRD_PARTY_NOTICES
⬆️ Upgrading from 2.x — claude plugin marketplace update alterlab-academic-skills, then claude plugin update <plugin>@alterlab-academic-skills; add a free OpenAlex key with /plugin configure alterlab-core@alterlab-academic-skills. The bundled PubMed server is gone — use the alterlab-pubmed skill. Details in the CHANGELOG.
📈 242 skills across 18 domains, 242 / 242 with executable evals; audit clean, full test suite green.

<details> <summary>Previously — What's New in v2.6.0</summary>

🧭 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.

</details>

<details> <summary>Previously — What's New in v2.5.0</summary>

⚖️ Social-Science Workflow made even-handed (11 → 17 skills) — the domain was quantitative-positivist by construction; v2.5 adds the qualitative and survey methods that were missing, plus depth. → Social-Science Workflow
📊 `alterlab-survey-analysis` (correctness gap) — design-based inference for complex-sample surveys (GSS/ANES/ESS/DHS): declare weights/strata/PSU/FPC before estimating, Taylor + replicate-weight SEs, post-stratification/raking, design-adjusted GLMs. Analyzing weighted surveys unweighted is a real error (falsely narrow CIs); this fixes it. samplics/svy or R survey+srvyr.
🗣️ `alterlab-qualitative-analysis` + `alterlab-ssci-reflexivity-gate` (balance fix) — intercoder reliability done right (Krippendorff's α primary, + a stdlib bootstrap-CI calculator; chi-square/Cronbach/Pearson refused), branching to consensus-and-reflexivity for reflexive TA; and the qualitative analog of the measurement gate (positionality + Lincoln & Guba trustworthiness, fail-closed).
📈 Quantitative depth — alterlab-multilevel-models (mixed-effects with the under-reported reporting checklist), alterlab-meta-analysis (pooling, I²/τ², Egger/trim-and-fill, PRISMA), alterlab-missing-data (MCAR/MAR/MNAR + MICE with Rubin's-rules pooling; the sklearn single-imputation trap flagged).
🔬 Every library web-verified & version-pinned (samplics 0.6 / svy 0.18, krippendorff 0.8, statsmodels MixedLM, metafor 5.0, R mice 3.19, lme4 2.0). The orchestrator now paradigm-selects the measurement-stage gate (quant vs qual) and routes the new modules; confusion_matrix.py reports zero new gaps.
📈 238 skills across 17 domains, 238 / 238 with executable evals; audit clean (0 errors, 0 warnings), full test suite green.

</details>

<details> <summary>Previously — What's New in v2.4.0</summary>

🧭 New 17th domain — Social-Science Workflow — a stage-gated methods spine of 11 skills: an orchestrator, four discipline-enforcing validity gates a study passes through before it is analyzed or written — design (pin the identifying assumption before any causal claim), measurement (reliability is not validity — omega, not alpha alone), sampling (power / precision / saturation, never a rule of thumb), inference (the claim may not exceed its design, sample, or uncertainty) — and six pluggable analysis modules the orchestrator dispatches to.
🔬 Six analysis modules, every library web-verified to its current API — alterlab-causal-inference (DiD/IV/RDD/panel via statsmodels, linearmodels, pyfixest, DoWhy, EconML, rdrobust), alterlab-sem-psychometrics (semopy/factor_analyzer + a stdlib omega calculator), alterlab-qca (shells to R's QCA package — no maintained Python library exists), alterlab-sna (networkx/igraph + R ERGM), alterlab-abm-mesa (the current Mesa 3 AgentSet API, not the removed schedulers), and alterlab-text-as-data (BERTopic/LDA/embeddings). No invented flags; version pins in each SKILL.
🧪 Executable, not just prose — stdlib helpers (design_router.py, sample_size.py, claim_audit.py, passport.py, estimator_router.py, omega.py, text_method_router.py), loaded-on-demand references, and vignette-in / routing-out evals with near-miss negatives. confusion_matrix.py reports zero new routing gaps.
🔗 Composes, does not duplicate — the gates and modules route to the existing alterlab-qualitative-methods, alterlab-survey-design, alterlab-statistical-analysis, alterlab-statsmodels, alterlab-networkx, and alterlab-test-selection-guard skills rather than reimplementing them, threading a Design Passport from design → measurement → sampling → analysis → inference.
📈 232 skills across 17 domains, 232 / 232 with executable evals; audit clean (0 errors, 0 warnings), full test suite green.

</details>

<details> <summary>Previously — What's New in v2.3.0</summary>

🛡️ Trust manifest you can verify before installing — a generated, CI-attested SECURITY_SCAN.md: the full outbound-host allowlist (66 domains, each categorized) plus an attestation of no shell-pipe, no `eval`-on-input, no hardcoded secrets. → SECURITY_SCAN.md
🎯 Activation + collision benchmarks — run_evals.py --activation measures auto-selection rate against Anthropic's 90% bar, and scripts/confusion_matrix.py statically ranks cross-firing risk between sibling skills. A nightly rotating 1/7 behavioral shard LLM-judges the whole corpus each week. → docs/evals.md
🧭 Sharper routing — 42 confusable descriptions now carry explicit prefer alterlab-x routing (quantum, protein/structure DBs, cheminformatics toolkits, single-cell, pathology, plotting, RL).
🧩 Agents & teams, formalized — docs/agents-and-teams.md names the 35 subagents and the 4 teams they compose (Research, Writing, Reviewer Panel, Pipeline Orchestration).
🔌 Portability map — docs/portability.md states exactly what transfers to Codex / Cursor / Gemini vs. Claude-Code-specific, and check_claudeai_compat.py guards the claude.ai uploader whitelist.
✂️ Every body under the soft cap — the last 17 over-500-line skills split into references/; the body-length ratchet is now empty. Coverage holds at 210 / 210. → docs/evals.md

</details>

<details> <summary>Previously — What's New in v2.2.0</summary>

🧠 Research-backed elevation of 191 skills — a corpus-wide accuracy and depth pass over every pre-existing skill: corrected regulation/API details, slimmed oversized bodies into references/, and version-bumped touched skills.
🧩 New core skill: Workflow Orchestration (alterlab-workflow-orchestration) — composes AlterLab skills into multi-agent workflows (subagent fan-out, pipelines, judge panels, adversarial verification), lifting the corpus to 210 skills. → Core Pipeline
🇹🇷 Turkish-academia flagship (13 skills) — the deepest Turkish-academia suite in any skills library: DergiPark, TR Dizin, YÖK Tez, YÖK Akademik, YÖKATLAS, TÜBİTAK 1001/1002-A/3501 proposals, BİDEB fellowships, doçentlik eligibility for every ÜAK temel alan, akademik teşvik scoring, Turkish APA-7 style, TR research ethics, KVKK data-management plans, and TÜBİTAK Aperta — each wired to a verified national-platform endpoint. → Turkish Academia
🎓 Faculty Life (6 skills) — syllabus AI policy, post-award grant reporting, recommendation letters, AACSB/ABET accreditation (AoL), REDCap/CDISC capture, and preprint deposition. → Faculty Life
🧪 Methodology (3 skills) — superpowers-style rigor (Iron Laws, Excuse-vs-Reality tables) applied to research methods: pre-registration discipline, statistical-test-selection guard, and results-reporting transparency. → Methodology
🧬 Bioinformatics grew 25 → 30 — production pipelines: nf-core/sarek variant calling, QIIME 2 amplicon, salmon/kallisto RNA-seq quant, NCBI BLAST+, and Squidpy spatial transcriptomics. → Bioinformatics

</details>

<details> <summary>Previously — What's New in v2.0</summary>

✅ Full-corpus executable evals — schema + trigger-coverage are CI-gated on every PR; the behavioral pass (claude CLI + LLM judge) runs on demand via workflow_dispatch. → docs/evals.md
🔎 Deterministic citation-existence verifier that catches hallucinated references against Crossref / OpenAlex / Semantic Scholar / arXiv — no LLM guesswork in the gate. → Headline feature
📦 Per-domain `claude.ai` bundles on every Release — each dist/<domain>.zip clears the 200-file / 30 MB caps. → Releases
🌐 Live searchable catalog to browse every skill in the browser. → Browse the Catalog
🤖 35 registered subagents + slash commands + a bundled academic MCP wiring OpenAlex / Crossref / Zotero. → MCP & Slash Commands
📜 Honest provenance — upstream K-Dense fork credited in THIRD_PARTY_NOTICES.md and a machine-readable CITATION.cff. → Cite This Repository

</details>

📋 Table of Contents

<details open> <summary>Click to expand / collapse</summary>

⚡ Try It — One Line, the Right Skill
🚀 What's New in v3.0.0
🎯 What Is This?
🆕 v2.0 Highlights
✨ Key Features
🗂️ Domain Overview
🔎 Browse the Catalog
🚀 Quick Start
⚡ Core Pipeline — 10 Skills
📚 All 242 Skills
🏗️ Project Structure
⚙️ How Skills Work
💡 Usage Examples
⚖️ How It Compares
🤝 Contributing
📖 Cite This Repository
📜 License
🙏 Credits

</details>

🎯 What Is This?

A comprehensive suite of 242 purpose-built Claude AI skills for faculty members, academicians, and researchers — organized into 18 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.

	What	Detail
✅	Executable evals across the corpus	242 / 242 skills ship `evals/evals.json` on the canonical agentskills.io schema, validated in CI. See `docs/evals.md`.
🔎	Citation-existence verifier	New core skill `alterlab-citation-verifier` — a deterministic gate that checks every reference actually exists against four keyless scholarly APIs (Crossref, OpenAlex, Semantic Scholar, arXiv), flags retractions, and maps claim-faithfulness verdicts. See below.
📦	Per-domain bundles for claude.ai	`dist/<domain>.zip` bundles (one per domain) attached to each Release — each clears claude.ai's 200-file / 30 MB caps and vendors the shared handoff contracts.
🔌	Bundled academic MCP	The `core` and `databases` plugins ship a `.mcp.json` wiring OpenAlex / Crossref / Zotero, with a documented `requests/` fallback when no MCP is available.
⌨️	Slash commands	`/lit-review`, `/review-paper`, `/cite-check`, `/research-pipeline` — drive the core pipeline directly.
🗂️	Generated catalog	A machine-readable `skills.json` is generated from skill frontmatter; a CI gate keeps every count in this README honest.
📜	Honest provenance	Upstream K-Dense fork credited in `THIRD_PARTY_NOTICES.md` + `PROVENANCE.md` / `CITATION.cff`.

🔎 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 242 skill names. alterlab-skill-finder is the front door: say "use AlterLab skills for this" and it classifies your task, maps it across all 18 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

	Feature	Description
🧭	One-Command Front Door	Just say "use AlterLab skills" — `alterlab-skill-finder` picks the right skill(s) for you; the `alterflow` keyword clarifies your goal, then launches a multi-agent workflow
🔬	Research-Ready	Skills built on real scientific methods, databases, and professional frameworks used by working researchers
🤖	Multi-Agent Pipelines	Core skills chain together: Research → Write → Review → Publish in a seamless workflow
📊	39 Database Integration Skills	Instant access to PubMed, ChEMBL, UniProt, ClinicalTrials.gov, COSMIC, and more
🧬	Deep Domain Coverage	From single-cell RNA-seq analysis to quantum computing, from clinical trials to digital humanities
📝	Publication-Quality Output	LaTeX papers, conference posters, grant proposals, scientific visualizations — all formatted to professional standards
🔄	Mix & Match	Combine multiple skills in one Claude Project for a multi-expert research team

🗂️ Domain Overview

	Domain	Skills	Focus Areas
🔄	Core Pipeline	10	Multi-agent research → write → review → publish pipeline + citation verifier + teaching + thesis + workflow orchestration + skill-finder router (the `alterflow` launcher)
🗄️	Databases	39	Connectors to scientific databases — PubMed, ChEMBL, UniProt, ClinicalTrials.gov, COSMIC, and more
🧬	Bioinformatics	38	Genomics, proteomics, molecular biology — Scanpy, BioPython, ESM, single-cell analysis, nf-core/sarek, QIIME 2, RNA-seq quant
⚗️	Cheminformatics	12	Chemistry and drug discovery — RDKit, molecular dynamics, docking, ADMET
🏥	Clinical Research	7	Clinical decision support, treatment planning, medical imaging, regulatory
📊	Data Science	22	ML/statistics — scikit-learn, PyTorch Lightning, SHAP, transformers
📈	Visualization	9	Scientific plotting — Matplotlib, Seaborn, Plotly, schematics, infographics
✍️	Writing Tools	14	Scientific writing, citations, grants, posters, academic career, AI-use disclosure
🔧	Lab Integrations	9	Laboratory platforms — Benchling, DNAnexus, Opentrons, Protocols.io
🌍	Domain-Specific	18	Quantum computing, geospatial, materials science, social science methods, digital humanities
📄	Document Tools	3	Markdown & document conversion — MarkItDown, Open Notebook, PDF exploration
🔍	Research Tools	14	Search, discovery, Zotero, citation graphs, PDF evidence tables, qualitative methods, ethics, surveys, open science
💰	Finance & Economics	7	FRED, Alpha Vantage, SEC EDGAR, market research
🇹🇷	Turkish Academia	13	National platforms & scholarly workflow — DergiPark, TR Dizin, YÖK Tez/Akademik, YÖKATLAS, TÜBİTAK proposals & BİDEB fellowships, doçentlik, teşvik, KVKK, Aperta
🎓	Faculty Life	6	Teaching, service & the academic career — syllabus AI policy, grant reporting, recommendation letters, accreditation, REDCap/CDISC, preprints
🧪	Methodology	3	Research-rigor discipline gates — pre-registration, test-selection guard, results-reporting transparency
🧭	Social-Science Workflow	17	Stage-gated methods spine — orchestrator + 5 validity gates (design, measurement, sampling, reflexivity, inference) + 11 analysis modules (causal-inference, SEM/psychometrics, QCA, SNA, ABM, text-as-data, survey-analysis, qualitative-analysis, multilevel-models, meta-analysis, missing-data)
🧩	Research Workflows	1 + 7 workflows	Runnable multi-agent jobs for Claude Code — citation audit, review panel, claim stress-test, PRISMA dual screening, rebuttal, grant mock panel, literature map — plus portable playbooks

🔎 Browse the Catalog

Search all 242 skills by name, domain, or keyword — no install required.

</div>

🚀 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:

In Claude, make sure code execution is on: Settings → Capabilities (Team/Enterprise: an owner enables it once for the org).
Open Customize ▸ Skills → [claude.ai/customize/skills](https://claude.ai/customize/skills).
Click `+` → Create skill → Upload a skill, and choose a skill's `.zip`.
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](https://github.com/AlterLab-IEU/AlterLab-Academic-Skills/releases), each skill ships its own ready-to-upload `skill-<name>-<version>.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-<version>.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

One step instead of many: alterlab-essentials installs the faculty starter kit (core pipeline, research workflows, research tools, writing tools, methodology gates, database connectors); alterlab-complete installs every domain.

/plugin install alterlab-essentials@alterlab-academic-skills

Multi-agent workflows (Claude Code with dynamic workflows — paid plans or API access) come in their own plugin, which also installs alterlab-core:

/plugin install alterlab-workflows@alterlab-academic-skills
/alterlab-workflows:citation-audit path/to/paper.md

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 (18): 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, alterlab-workflows — plus the bundles alterlab-essentials and alterlab-complete.

📁 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/<name>/SKILL.md or .claude/skills/<name>/SKILL.md — a bare git clone alone does not register anything.

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

Every Release ships pre-built `dist/<domain>.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.

Download the domain bundle you need from the Releases page — e.g. bioinformatics.zip, databases.zip, core.zip.
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 OpenAlex / Crossref / Zotero academic MCP servers (Claude Code prompts for the optional API keys when you enable the plugin; change them later with /plugin configure; PubMed goes through the alterlab-pubmed skill, which calls NCBI E-utilities directly), 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:

Command	Drives
`/lit-review`	`alterlab-deep-research` — systematic literature review
`/review-paper`	`alterlab-paper-reviewer` — multi-perspective peer review
`/cite-check`	`alterlab-citation-verifier` — deterministic citation-existence gate
`/research-pipeline`	`alterlab-research-pipeline` — full research → publish orchestrator

[!NOTE] 242 / 242 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.

#	Skill	Agents	What It Does
1	🔬 Deep Research	13	Multi-mode research with systematic review, Socratic dialogue, fact-checking
2	📝 Paper Writer	12	Academic paper authoring with LaTeX, bilingual support, 9 writing modes
3	🔍 Paper Reviewer	7	Multi-perspective peer review with Devil's Advocate, 0–100 quality rubrics
4	🔄 Research Pipeline	3	10-stage orchestrator with integrity verification and material passports
5	🔎 Citation Verifier	—	Deterministic citation-existence gate over Crossref / OpenAlex / Semantic Scholar / arXiv
6	🎓 Teaching Design	—	Course design, syllabi, rubrics, Bloom's taxonomy, backward design
7	📋 Thesis Supervisor	—	Dissertation guidance, defense prep, committee management
8	🔗 Link Health	—	Repo link-health audit meta-skill
9	🧩 Workflow Orchestration	—	Composes AlterLab skills into multi-agent workflows: subagent fan-out, pipelines, judge panels, adversarial verification
10	🧭 Skill Finder	—	Front-door router — turns "use AlterLab skills" into the right skill(s); the `alterflow` keyword clarifies the goal then launches a dynamic multi-agent workflow

📚 All 242 Skills

🗄️ Databases — Scientific Database Connectors (39 Skills)

<details> <summary>Click to expand full database skills list</summary>

#	Skill	What It Does
1	AlphaFold DB	Protein structure predictions from AlphaFold
2	arXiv	Preprint search and discovery
3	BindingDB	Binding affinity data for drug-target interactions
4	bioRxiv	Biology preprint search and monitoring
5	BRENDA	Enzyme functional data
6	cBioPortal	Cancer genomics data exploration
7	ChEMBL	Bioactive molecules with drug-like properties
8	ClinicalTrials.gov	Clinical trial registry search
9	ClinPGx	Clinical pharmacogenomics data
10	ClinVar	Genomic variation and human health
11	COSMIC	Catalogue of somatic mutations in cancer
12	Data Commons	Google's open knowledge graph
13	DepMap	Cancer dependency mapping
14	DrugBank	Drug and drug target information
15	ENA	European Nucleotide Archive
16	Ensembl	Genome annotation and variation
17	FDA	FDA drug and device data
18	Gene DB	Gene-level data aggregation
19	GEO	Gene Expression Omnibus datasets
20	gnomAD	Genome aggregation and variant frequency
21	GTEx	Tissue-specific gene expression
22	GWAS Catalog	Genome-wide association studies
23	HMDB	Human Metabolome Database
24	Imaging Data Commons	Cancer imaging data
25	InterPro	Protein families and domains
26	JASPAR	Transcription factor binding profiles
27	KEGG	Biological pathways and networks
28	Metabolomics Workbench	Metabolomics data repository
29	Monarch Initiative	Disease-gene associations
30	OpenAlex	Open scholarly metadata
31	Open Targets	Drug target identification
32	PDB	Protein 3D structure database
33	PubChem	Chemical information database
34	PubMed	Biomedical literature search
35	Reactome	Biological pathway database
36	STRING	Protein-protein interaction networks
37	UniProt	Protein sequence and function
38	USPTO	Patent search and analysis
39	ZINC	Commercially-available compounds for docking

</details>

🧬 Bioinformatics — Genomics, Proteomics & Molecular Biology (38 Skills)

<details> <summary>Click to expand full bioinformatics skills list</summary>

#	Skill	What It Does
1	AnnData	Annotated data matrices for single-cell
2	Arboreto	Gene regulatory network inference
3	BioPython	General-purpose bioinformatics toolkit
4	BioServices	Programmatic access to biological web services
5	CellxGene	Interactive single-cell data exploration
6	COBRApy	Constraint-based metabolic modeling
7	deepTools	NGS data analysis and visualization
8	ESM	Protein language models
9	ETE Toolkit	Phylogenetic tree analysis and visualization
10	FlowIO	Flow cytometry data handling
11	gget	Query genomic databases from Python
12	Glycoengineering	Glycan analysis and engineering
13	HistoLab	Computational histopathology
14	LaminDB	Data lineage and biological data management
15	Neuropixels	Neural probe data processing
16	PathML	Machine learning for pathology
17	Phylogenetics	Evolutionary tree construction
18	PyDESeq2	Differential gene expression analysis
19	pyOpenMS	Mass spectrometry data analysis
20	pysam	SAM/BAM file manipulation
21	Scanpy	Single-cell analysis in Python
22	scikit-bio	Bioinformatics algorithms and data structures
23	scVelo	RNA velocity analysis
24	scvi-tools	Deep generative models for single-cell
25	TileDB-VCF	Population-scale genomic variant storage
26	BLAST	NCBI BLAST+ command-line sequence similarity searches
27	nf-core/sarek	FASTQ-to-VCF germline & somatic variant-calling pipeline
28	QIIME 2 Amplicon	16S/ITS microbiome amplicon analysis
29	RNA-seq Quant	Transcript abundance with salmon & kallisto
30	Squidpy Spatial	Spatial transcriptomics on AnnData/SpatialData

</details>

⚗️ Cheminformatics — Chemistry & Drug Discovery (12 Skills)

<details> <summary>Click to expand full cheminformatics skills list</summary>

#	Skill	What It Does
1	Datamol	Molecular data manipulation
2	DeepChem	Deep learning for chemistry
3	DiffDock	Diffusion-based molecular docking
4	matchms	Mass spectra matching and similarity
5	MedChem	Medicinal chemistry analysis
6	Molecular Dynamics	MD simulation setup and analysis
7	MolFeat	Molecular featurization
8	PrimeKG	Precision medicine knowledge graph
9	PyTDC	Therapeutics Data Commons access
10	RDKit	Core cheminformatics toolkit
11	Rowan	Computational chemistry workflows
12	TorchDrug	Graph neural networks for drug discovery

</details>

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

<details> <summary>Click to expand full clinical research skills list</summary>

#	Skill	What It Does
1	Clinical Decision	Evidence-based clinical decision support
2	Clinical Reports	Structured clinical report generation
3	ISO 13485	Medical device quality management
4	NeuroKit2	Neurophysiological signal processing
5	PyDicom	DICOM medical image handling
6	PyHealth	Healthcare ML pipelines
7	Treatment Plans	Treatment planning and protocol design

</details>

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

<details> <summary>Click to expand full data science skills list</summary>

#	Skill	What It Does
1	Dask	Parallel computing and out-of-core data
2	EDA	Exploratory data analysis
3	NetworkX	Network/graph analysis
4	Polars	High-performance DataFrames
5	PufferLib	Reinforcement learning environments
6	PyMC	Bayesian statistical modeling
7	pymoo	Multi-objective optimization
8	PyTorch Lightning	Structured deep learning training
9	scikit-learn	Classical machine learning
10	scikit-survival	Survival analysis
11	SHAP	Model interpretability and feature importance
12	SimPy	Discrete-event simulation
13	Stable-Baselines3	Reinforcement learning algorithms
14	Statistical Analysis	Classical statistical tests and methods
15	statsmodels	Statistical models and econometrics
16	SymPy	Symbolic mathematics
17	TimesFM	Foundation model for time series
18	PyTorch Geometric	Graph neural networks
19	Transformers	Hugging Face transformer models
20	UMAP	Dimensionality reduction
21	Vaex	Out-of-core DataFrames for big data
22	Zarr	Chunked, compressed N-dimensional arrays

</details>

📈 Visualization — Scientific Plotting & Graphics (9 Skills)

<details> <summary>Click to expand full visualization skills list</summary>

#	Skill	What It Does
1	Generate Image	AI image generation for research figures
2	Infographics	Research infographic design
3	Matplotlib	Publication-quality 2D plots
4	Mermaid	Diagrams and flowcharts as code
5	Plotly	Interactive scientific visualizations
6	Scientific Schematics	Technical diagrams and schematics
7	Scientific Viz	Advanced scientific visualization
8	Seaborn	Statistical data visualization

</details>

✍️ Writing Tools — Scientific Writing, Citations & Publishing (14 Skills)

<details> <summary>Click to expand full writing tools skills list</summary>

#	Skill	What It Does
1	Academic Career	Academic CV, research statements, tenure dossier
2	AI-Use Disclosure	Generative-AI disclosure statements for manuscripts, grants, peer review & theses, per publisher, funder & YÖK/TÜBİTAK policy
3	Citation Management	Reference formatting and management
4	Hypothesis Generator	Research hypothesis development
5	LaTeX Posters	Conference poster design in LaTeX
6	Literature Review	Systematic literature review assistance
7	Paper-to-Web	Convert papers to web-friendly formats
8	Peer Review	Peer review writing assistance
9	PPTX Posters	Conference posters in PowerPoint
10	Research Grants	Grant proposal writing
11	Scholar Eval	Academic output evaluation
12	Scientific Slides	Research presentation creation
13	Scientific Writing	Academic writing style and structure
14	Venue Templates	Journal/conference formatting templates

</details>

🔧 Lab Integrations — Laboratory Platform Connectors (9 Skills)

<details> <summary>Click to expand full lab integration skills list</summary>

#	Skill	What It Does
1	Benchling	Molecular biology data platform
2	DNAnexus	Genomic data analysis platform
3	Ginkgo Cloud	Synthetic biology platform
4	LabArchive	Electronic lab notebook
5	LatchBio	Bioinformatics workflow platform
6	OMERO	Biological image management
7	Opentrons	Lab automation and robotics
8	Protocols.io	Protocol sharing and management
9	PyLabRobot	Lab robotics programming

</details>

<details> <summary>Click to expand full domain-specific skills list</summary>

#	Skill	What It Does
1	Adaptyv	Adaptive experimental design
2	Aeon	Time series classification
3	AstroPy	Astronomy and astrophysics
4	Cirq	Quantum circuit design (Google)
5	FluidSim	Fluid dynamics simulation
6	GeniML	Genomic interval ML
7	GeoMaster	Geospatial analysis mastery
8	GeoPandas	Geospatial data analysis
9	GTARS	Genomic tool for annotation
10	HypoGenic	Hypothesis generation from data
11	Modal	Cloud compute for research
12	PennyLane	Quantum machine learning
13	Pymatgen	Materials science analysis
14	Qiskit	Quantum computing (IBM)
15	QuTiP	Quantum dynamics simulation
16	Social Science Methods	Discourse analysis, QCA, Delphi, process tracing
17	Digital Humanities	Text mining, corpus linguistics, stylometry, OCR

</details>

📄 Document Tools — Markdown & Document Conversion (3 Skills)

<details> <summary>Click to expand full document tools skills list</summary>

#	Skill	What It Does
1	MarkItDown	Convert documents to Markdown
2	Open Notebook	Open-format research notebooks

</details>

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

<details> <summary>Click to expand full research tools skills list</summary>

#	Skill	What It Does
1	BGPT Search	AI-powered research search
2	Citation Graph	Keyless ResearchRabbit analog — citation & co-citation graphs over OpenAlex
3	Mixed Methods	Mixed-methods research design and integration
4	Open Science	Preregistration, FAIR data, open access publishing
5	Parallel Web	Multi-source parallel web search
6	PDF Extract	Elicit-columns analog — per-paper evidence tables from PDFs
7	Perplexity	Perplexity-powered research queries
8	PyZotero	Zotero reference manager integration
9	Qualitative Methods	Thematic analysis, grounded theory, IPA, coding
10	Research Ethics	IRB applications, informed consent, GDPR
11	Research Lookup	Quick research paper discovery
12	Scientific Brainstorm	Structured research ideation
13	Scientific Thinking	Critical scientific reasoning frameworks
14	Survey Design	Questionnaire construction and validation

</details>

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

<details> <summary>Click to expand full finance & economics skills list</summary>

#	Skill	What It Does
1	Alpha Vantage	Stock and financial market data
2	Denario	Financial data processing
3	EDGAR Tools	SEC filing search and analysis
4	FRED	Federal Reserve economic data
5	Hedge Fund Monitor	Hedge fund tracking and analysis
6	Market Research	Market analysis and intelligence
7	US Fiscal Data	US government fiscal data

</details>

🇹🇷 Turkish Academia — National Platforms & Scholarly Workflow (13 Skills)

<details> <summary>Click to expand full Turkish academia skills list</summary>

#	Skill	What It Does
1	DergiPark	Harvest metadata, abstracts & PDFs from DergiPark via OAI-PMH
2	TR Dizin	Search TR Dizin & verify a journal's national-index status
3	YÖK Tez	Search the national graduate-thesis archive for review & originality checks
4	YÖK Akademik	Look up a Turkish academic's YÖKSİS profile, title & affiliation
5	YÖKATLAS	Higher-education program & admission statistics (kontenjan, taban puan)
6	TÜBİTAK Proposal	Scaffold TÜBİTAK 1001, 1002-A & 3501 national research proposals
7	TÜBİTAK BİDEB	Match & prepare BİDEB fellowships and travel support (2219, 2218, 2221, 2232-A/B, 2236-A, 2224-A, 2223-B)
8	Doçentlik Eligibility	Pre-screen a publication list against ÜAK doçentlik criteria for all 12 temel alanlar
9	Akademik Teşvik	Compute the annual academic-incentive (teşvik) score
10	TR Academic Style	Turkish-journal & TR-Dizin formatting + Turkish APA-7
11	TR Research Ethics	Turkish etik kurul applications & consent-form routing
12	KVKK DMP	KVKK-compliant data-management plans for Turkish research
13	Aperta	TÜBİTAK open-science compliance & deposition into Aperta

</details>

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

<details> <summary>Click to expand full faculty life skills list</summary>

#	Skill	What It Does
1	Syllabus AI Policy	Course-level generative-AI use policies & syllabus statements
2	Grant Reporting	Post-award reports — NIH RPPR, NSF, Horizon Europe / ERC
3	Recommendation Letters	Evidence-anchored reference & recommendation letters
4	Accreditation (AoL)	AACSB / ABET assurance-of-learning documentation
5	REDCap / CDISC	Validated data-capture instruments mapped to CDISC standards
6	Preprint Deposition	Deposit preprints to arXiv, bioRxiv, medRxiv, SSRN, OSF

</details>

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

<details> <summary>Click to expand full methodology skills list</summary>

#	Skill	What It Does
1	Pre-registration Discipline	No analysis without a frozen, pre-registered plan
2	Test-Selection Guard	No statistical test chosen after seeing the p-value
3	Results Transparency	No results claim without reporting every analysis run

</details>

<details> <summary>Click to expand full social-science workflow skills list</summary>

A stage-gated methods spine: an orchestrator holds a Design Passport, five gates each refuse to advance until their discipline is satisfied, and eleven analysis modules are dispatched by the design/data. The measurement stage is paradigm-selected (quantitative measurement gate vs qualitative reflexivity gate). Every module's library was web-verified to its current API; the gates and modules route to the existing qualitative-methods, survey-design, statistics, statsmodels, and networkx skills rather than reimplementing them.

#	Skill	What It Does
1	SSci Orchestrator	Thin pipeline coordinator — holds the Design Passport, enforces gate order with PASS / WARN / BLOCK, dispatches the right module (does no analysis itself)
2	SSci Design Gate	Routes the study to its design family and pins the identifying assumption the causal claim rests on before any analysis
3	SSci Measurement Gate	Enforces reliability ≠ validity — omega (not alpha alone), the four validities, and measurement invariance before group comparison
4	SSci Sampling Gate	Matches the sizing logic to the inference (power / precision / saturation) and the generalization claim to the sample type
5	SSci Reflexivity Gate	The qualitative analog of the measurement gate — positionality + Lincoln & Guba trustworthiness, fail-closed against ungrounded interpretivist claims
6	SSci Inference Gate	The terminal auditor — no causal claim beyond the design, no p-value/CI misreading, no generalization beyond the frame
7	Causal Inference	DiD / IV / RDD / panel FE / PSM / CATE via statsmodels, linearmodels, pyfixest, DoWhy, EconML, rdrobust — names the assumption, estimates, then refutes
8	Survey Analysis	Design-based inference for complex-sample surveys (weights/strata/PSU/FPC, replicate SEs, raking) — svy (samplics is archived) or R survey+srvyr
9	SEM & Psychometrics	CFA / SEM / EFA / IRT / measurement invariance via semopy & factor_analyzer, with a stdlib McDonald's-omega calculator
10	Multilevel Models	Mixed-effects / hierarchical (statsmodels MixedLM, R lme4/glmmTMB/brms) enforcing the under-reported LMM reporting checklist
11	QCA	csQCA / mvQCA / fsQCA (calibrate → truth table → minimize) — shells to R's QCA package since no maintained Python library exists
12	SNA	Centrality, community detection (Louvain/Leiden), and ERGM — SNA method discipline over networkx / igraph / R statnet
13	ABM (Mesa)	Agent-based modeling on the current Mesa 3 AgentSet API, with replication + parameter-sweep + pattern-oriented validation
14	Text-as-Data	Topic modeling (BERTopic / LDA), embeddings, dictionary methods — chosen by goal, with a topic-reliability procedure
15	Qualitative Analysis	Intercoder reliability (Krippendorff's α + bootstrap CI), codebook-vs-reflexive branch, human↔LLM double-coding
16	Meta-Analysis	Random-effects pooling, I²/τ² heterogeneity, forest/funnel, Egger + trim-and-fill (statsmodels / R metafor), PRISMA
17	Missing Data	MCAR/MAR/MNAR + MICE with Rubin's-rules pooling / FIML (statsmodels, R mice); flags the single-imputation trap

</details>

🧩 Research Workflows — Runnable Multi-Agent Jobs (1 Skill + 7 Workflows)

<details> <summary>Click to expand the research workflows</summary>

Claude Code dynamic workflows are scripts that orchestrate many subagents and keep their intermediate results out of your conversation. The alterlab-workflows plugin ships seven, each composing existing AlterLab skills with the independence and adversarial checks its task needs; counts, votes, κ, and score spreads are computed in code. On claude.ai and other surfaces, the `alterlab-research-workflows` skill runs the same stages as staged playbooks. Install: /plugin install alterlab-workflows@alterlab-academic-skills (also installs alterlab-core).

#	Command	What It Does
1	`/alterlab-workflows:citation-audit`	Every reference resolved against Crossref / OpenAlex / Semantic Scholar / arXiv, every cited claim checked against its source; each flag must survive two independent re-checks (TF / PAC / IH / PH / SH report)
2	`/alterlab-workflows:review-panel`	4–6 blind reviewers chosen for the paper's field and design; every major concern re-read against the manuscript before the editor decides
3	`/alterlab-workflows:claim-stress-test`	Three skeptics per headline claim (counter-evidence, citation support, inference); majority rating and calibrated rewrites
4	`/alterlab-workflows:systematic-review-screening`	PRISMA 2020 title/abstract screening — codebook, optional database search, de-duplication, two blinded screeners per record, adjudication, Cohen's κ
5	`/alterlab-workflows:rebuttal`	Point-by-point response to reviewers with a cross-response consistency pass; `[AUTHORS: …]` placeholders instead of invented results
6	`/alterlab-workflows:grant-mock-panel`	Mock study section on the funder's own criteria and scale (NIH, NSF, ERC, Horizon Europe, TÜBİTAK 1001/1002); score spread computed; summary statement
7	`/alterlab-workflows:literature-map`	Parallel scholarly-database sweeps → themes, landmark works, and research gaps that survive a search for existing answers

</details>

🏗️ Project Structure

AlterLab-Academic-Skills/
├── 📁 skills/                       # 242 skills across 18 domains
│   ├── 🔄 core/                # 10 pipeline + citation-verifier + teaching + thesis + skill-finder
│   ├── 🗄️ databases/           # 39 database connectors
│   ├── 🧬 bioinformatics/      # 38 bio/genomics tools
│   ├── ⚗️ cheminformatics/     # 12 chemistry/drug discovery
│   ├──

databases— mcp server

Is databases safe to install?

⚡ Try It — One Line, the Right Skill

🚀 What's New in v3.0.0

📋 Table of Contents

🎯 What Is This?

🆕 v2.0 Highlights

🔎 Headline feature — `alterlab-citation-verifier`

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

✨ Key Features

🗂️ Domain Overview

🔎 Browse the Catalog

🚀 Quick Start

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

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

⚡ Option 2 — Claude Code Plugin

📁 Option 3 — Personal or Project Install (manual)

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

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

🔌 MCP & Slash Commands

⚡ Core Pipeline — 10 Skills

📚 All 242 Skills

🗄️ Databases — Scientific Database Connectors (39 Skills)

🧬 Bioinformatics — Genomics, Proteomics & Molecular Biology (38 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 (9 Skills)

✍️ Writing Tools — Scientific Writing, Citations & Publishing (14 Skills)

🔧 Lab Integrations — Laboratory Platform Connectors (9 Skills)

📄 Document Tools — Markdown & Document Conversion (3 Skills)

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

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

🇹🇷 Turkish Academia — National Platforms & Scholarly Workflow (13 Skills)

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

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

🧩 Research Workflows — Runnable Multi-Agent Jobs (1 Skill + 7 Workflows)

🏗️ Project Structure

Audit the pieces. Scan the whole. Decide.

Is databases safe to install?

⚡ Try It — One Line, the Right Skill

🚀 What's New in v3.0.0

📋 Table of Contents

🎯 What Is This?

🆕 v2.0 Highlights

🔎 Headline feature — alterlab-citation-verifier

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

✨ Key Features

🗂️ Domain Overview

🔎 Browse the Catalog

🚀 Quick Start

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

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

⚡ Option 2 — Claude Code Plugin

📁 Option 3 — Personal or Project Install (manual)

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

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

🔌 MCP & Slash Commands

⚡ Core Pipeline — 10 Skills

📚 All 242 Skills

🗄️ Databases — Scientific Database Connectors (39 Skills)

🧬 Bioinformatics — Genomics, Proteomics & Molecular Biology (38 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 (9 Skills)

✍️ Writing Tools — Scientific Writing, Citations & Publishing (14 Skills)

🔧 Lab Integrations — Laboratory Platform Connectors (9 Skills)

🌍 Domain-Specific — Quantum, Geospatial, Materials, Social Science & More (18 Skills)

📄 Document Tools — Markdown & Document Conversion (3 Skills)

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

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

🇹🇷 Turkish Academia — National Platforms & Scholarly Workflow (13 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)

🧩 Research Workflows — Runnable Multi-Agent Jobs (1 Skill + 7 Workflows)

🏗️ Project Structure

Audit the pieces. Scan the whole. Decide.

🔎 Headline feature — `alterlab-citation-verifier`

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

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