Design a new repeated statistical or computational analysis script from scratch using the five-layer modular architecture: constants → data loading → atomic functions → output functions → orchestrator (runone). Use this skill when a user wants to write a new analysis script that applies the same procedure across multiple combinations of inputs, asks how to structure code that loops over outcomes, predictors, conditions, timepoints, ROIs, cohorts, or other dimensions, or invokes /analysis-plan. This skill works in any scripting language (R, Python, Julia, MATLAB, shell, etc.) and for any kind of repeated analysis — statistical models, image processing pipelines, feature extraction loops, simulation sweeps, etc. If the user already has a working but disorganized script they want to clean up, suggest /analysis-refactor instead.
EnglishAuto-invoke when the user wants to transfer saved dataset state to a remote, publish a dataset, upload annexed content to a sibling, share changes with collaborators, or push to GitHub, OSF, or other storage. Trigger on "push to remote", "publish dataset", "upload to sibling", "share changes", "push to GitHub", "send to storage", or /datalad-push. Do NOT trigger for plain git push in repos without DataLad context.
EnglishUser describes a research question — what they're trying to predict or explain, what variables are involved, and what the study design looks like — and wants a recommended statistical model with a hierarchical test sequence from null to fully specified. Use this skill whenever the user asks which statistical test or model to use, wants to plan an analysis, needs help choosing between ANOVA/regression/mixed effects/CCA/factor analysis, or describes outcome and predictor variables and wants a structured modelling approach.
English
AGENT SKILLS ATLASIncludes Analysis Plan, Datalad Push, and Plan Analysis.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Analysis Plan
Design a new repeated statistical or computational analysis script from scratch using the five-layer modular architecture: constants → data loading → atomic functions → output functions → orchestrator (runone). Use this skill when a user wants to write a new analysis script that applies the same procedure across multiple combinations of inputs, asks how to structure code that loops over outcomes, predictors, conditions, timepoints, ROIs, cohorts, or other dimensions, or invokes /analysis-plan. This skill works in any scripting language (R, Python, Julia, MATLAB, shell, etc.) and for any kind of repeated analysis — statistical models, image processing pipelines, feature extraction loops, simulation sweeps, etc. If the user already has a working but disorganized script they want to clean up, suggest /analysis-refactor instead.
Datalad Push
Auto-invoke when the user wants to transfer saved dataset state to a remote, publish a dataset, upload annexed content to a sibling, share changes with collaborators, or push to GitHub, OSF, or other storage. Trigger on "push to remote", "publish dataset", "upload to sibling", "share changes", "push to GitHub", "send to storage", or /datalad-push. Do NOT trigger for plain git push in repos without DataLad context.
Plan Analysis
User describes a research question — what they're trying to predict or explain, what variables are involved, and what the study design looks like — and wants a recommended statistical model with a hierarchical test sequence from null to fully specified. Use this skill whenever the user asks which statistical test or model to use, wants to plan an analysis, needs help choosing between ANOVA/regression/mixed effects/CCA/factor analysis, or describes outcome and predictor variables and wants a structured modelling approach.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Analysis Plan skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.