Open Science Skills
A library of Claude Code skills for experimental social science and computational text analsyis. Install as a plugin to get AI assistance, from hypothesis generation through final reporting. The skills are available both as auto-triggered context and as explicit /skill-name slash commands.
Skills were developed using a curated library of methodology texts. They are iteratively expanded as new sources, ideas, and skills are incorporated. This is a living and breathing kind of repo. Skill building and editing is author-driven with the help of Opus 4.6, Gemini 3.0, and Chat GPT 5.4.
Design follows Anthropic's skill authoring best practices: concise procedural guidance (no textbook definitions), trigger-rich YAML descriptions for auto-invocation, and progressive disclosure (instructions in skills, bibliography in SOURCES.md). Skills are periodically audited against both the Claude Code skills reference and the skill authoring guide to keep descriptions, frontmatter, and substantive content current.
These skills are meant to support, not supplant, the research and writing process. They adhere to APSA, JARS, and DA-RT reporting standards. All guidance is grounded in 90+ published sources — see SOURCES.md for the full bibliography.
How Skills Work
Each skill is available in two ways:
| Mode | How | When to use |
|---|---|---|
| Auto-trigger | Claude reads your prompt and loads the relevant skill silently | Working naturally — Claude detects context |
| Slash command | Type /skill-name (optionally with a task description) | When you want to invoke a skill explicitly |
Both modes are available when installed as a plugin. Individual skills can also be installed manually (auto-trigger only).
Installation
Option 1 — Plugin (recommended, installs all skills + slash commands)
Permanent install (user-wide, persists across all projects):
# Step 1: Register the marketplace (one-time)
claude plugin marketplace add scdenney/open-science-skills
# Step 2: Install the plugin
claude plugin install open-science-skills
# Project-only install
claude plugin install open-science-skills --scope project
Session-only (no install required, active for the current session):
git clone https://github.com/scdenney/open-science-skills.git
cd open-science-skills && claude --plugin-dir ./plugin
All 15 skills auto-trigger based on your prompts. All 15 slash commands (/conjoint-design, /list-experiment, etc.) are immediately available.
Option 2 — Selective install (choose specific skills, auto-trigger only)
Use the interactive install script to pick only the skills you want:
git clone https://github.com/scdenney/open-science-skills.git
cd open-science-skills
bash plugin/scripts/install.sh
The script lists available skills and lets you choose interactively. Skills are installed to ./.claude/skills/ by default (current project only). Options:
# Install to user-wide skills directory (all projects)
bash plugin/scripts/install.sh --target ~/.claude/skills
# Install specific skills non-interactively
bash plugin/scripts/install.sh --skill conjoint-design survey-design list-experiment
# Install all skills
bash plugin/scripts/install.sh --all --target ~/.claude/skills
Restart Claude Code after installing to load the new skills.
Option 3 — Manual copy (single skill, auto-trigger only)
git clone https://github.com/scdenney/open-science-skills.git
# Project-level (current project only)
mkdir -p your-project/.claude/skills/conjoint-design
cp open-science-skills/plugin/skills/conjoint-design/SKILL.md \
your-project/.claude/skills/conjoint-design/SKILL.md
# User-wide (all projects)
mkdir -p ~/.claude/skills/list-experiment
cp open-science-skills/plugin/skills/list-experiment/SKILL.md \
~/.claude/skills/list-experiment/SKILL.md
Note: Manual install gives you auto-trigger only. Slash commands (
/skill-name) require the plugin.