Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From sagemaker-ai
Sets up project directories and organizes artifacts (specs/, scripts/, notebooks/) when starting or resuming work, and associates PLAN.md with a project folder.
npx claudepluginhub awslabs/agent-plugins --plugin sagemaker-aiHow this skill is triggered — by the user, by Claude, or both
Slash command
/sagemaker-ai:directory-managementThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Before any work begins, resolve the project name:
Creates a date-organized workspace folder with static project docs and an assets directory for code, enabling other skills to operate with project context and daily work tracking.
Organizes project folders with a standard research skeleton (data, src, models, results, figures, docs, paper, etc.) and enforces DAG-based data flow, immutable raw data, and DVC versioning. Use when scaffolding new projects or restructuring existing ones for reproducibility.
Creates a new project directory with AGENTS.md, initializes a Git repo, and auto-generates a GitHub repository based on an MVP domain input.
Share bugs, ideas, or general feedback.
Before any work begins, resolve the project name:
*/PLAN.md files in the current directory. If found, ask the user if they are resuming an existing project and load that PLAN.md into context.[a-z0-9-]), or ask directly if there isn't enough context. Present the recommended name and wait for user confirmation.Once project name is resolved:
<experiment-name>/ directory using the confirmed name for storing all the artifactsWhen working with the agent, all generated files are organized under an project directory.
<project-name>/
├── specs/
│ ├── PLAN.md # Your customization plan
├── scripts/ # Generated Python scripts
│ ├── <project-name>_transform_fn.py
└── notebooks/ # Generated Jupyter notebooks
├── <project-name>.ipynb