AlterLab-Academic-Skills CLAUDE.md

A set of project instructions for a collection of 239 AI skills aimed at university faculty and academic researchers. It describes the project structure, naming rules, categories, audience, and how requests should be routed through the skills.

In plain words
What is it for?
Maintaining the academic-skills project, classifying skills across its research areas, following naming conventions, and directing requests to the appropriate category.
Why use it?
It gives contributors and users a shared understanding of what the collection contains and who it serves. This reduces confusion when choosing or organising skills for academic work.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/alterlab-ieu/alterlab-academic-skills/claude-md
Clone the repo
git clone --depth 1 https://github.com/AlterLab-IEU/AlterLab-Academic-Skills
Per session 1,908 This file is loaded in full into every session.
When invoked 1,908 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01908 $0.01908
Opus 5 $0.00954 $0.00954
Sonnet 5 $0.00382 $0.00382
Haiku 4.5 $0.00191 $0.00191

Measured yesterday against content hash c648cff9d50d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AlterLab-Academic-Skills CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AlterLab Academic Skills — by AlterLab Creative Technologies Laboratory

Project: AlterLab Academic Skills — 239 Claude AI skills for faculty and researchers Owner: AlterLab Creative Technologies Laboratory


Project Overview

This project provides 239 professional Claude AI skills organized into 17 domain categories for faculty members, academicians, and researchers. Each skill transforms Claude into a domain-specific expert assistant tailored to academic research, scientific computing, and scholarly publishing workflows.

The repo is installable as a Claude Code plugin marketplace named alterlab-academic-skills, with 17 domain plugins (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).

Audience

  • Faculty members and academic researchers
  • NOT students (see AlterLab FC for student skills)

Naming Convention

  • Folder: alterlab-{name} (lowercase, hyphenated)
  • Frontmatter name: "alterlab-{name}"
  • Suite label: Part of the AlterLab Academic Skills suite.

Skill Categories

Category Path Count Description
Core Pipeline skills/core/ 10 Research -> Write -> Review -> Publish pipeline + citation-verifier + link-health + workflow-orchestration + skill-finder router
Databases skills/databases/ 39 Scientific database connectors
Bioinformatics skills/bioinformatics/ 38 Genomics, proteomics, molecular biology
Cheminformatics skills/cheminformatics/ 12 Chemistry, drug discovery
Clinical Research skills/clinical-research/ 7 Clinical decision support, medical tools
Data Science skills/data-science/ 22 ML, statistics, data analysis
Visualization skills/visualization/ 9 Scientific plotting and graphics
Writing Tools skills/writing-tools/ 13 Scientific writing, citations, posters
Lab Integrations skills/lab-integrations/ 9 Laboratory platform connectors
Domain-Specific skills/domain-specific/ 18 Quantum, geospatial, materials science
Document Tools skills/document-tools/ 3 Markdown conversion, notebook handling
Research Tools skills/research-tools/ 14 Search, discovery, reference management
Finance & Economics skills/finance-economics/ 7 Financial data and analysis
Turkish Academia skills/turkish-academia/ 12 Turkish academic system workflows (YÖK, ÜAK, DergiPark, TÜBİTAK)
Faculty Life skills/faculty-life/ 6 Faculty research-lifecycle and academic administration
Methodology skills/methodology/ 3 Research methodology and rigor scaffolds
Social-Science Workflow skills/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)

Read the full file on GitHub · 137 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 137 lines · 1,908 tokens per session scan A c648cff9d50d

Subscribe to this mod's changes

AlterLab-Academic-Skills CLAUDE.md is an instructions file published in the GitHub repository AlterLab-IEU/AlterLab-Academic-Skills (62 stars, last pushed 2mo ago), licensed MIT. It adds 1,908 tokens to every session, about $0.0095 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.