Directory Management
SkillAI & modelsThis skill gives your AI a tidy home for every project it works on. It sets up a clear folder structure with places for specs, scripts, notebooks, manifests, and agent memory, and keeps planning files like PLAN.md tied to the right project directory.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then ask your AI to set up folders for a new project or to pick up an existing one. It will create the structure and give any PLAN.md a home in the matching directory.
Then ask your AI: use the Directory Management skill
What your AI can do with it
- Create a ready-to-use project folder with specs, scripts, notebooks, manifests, and agent memory folders
- Organize files and artifacts into the right folders as work continues
- Reconnect to an existing project so work can resume in the same structure
- Link a PLAN.md file to the project directory it belongs to
What this skill tells your AI
The instructions your AI receives, as published by awslabs/agent-plugins in plugins/sagemaker-ai/skills/directory-management/SKILL.md and read by ahel’s review.
Project Setup
Before any work begins, resolve the project name:
- If the project name is already known from conversation context, use it.
- Otherwise, scan for existing
*/PLAN.mdfiles in the current directory. If found, ask the user if they are resuming an existing project and load thatPLAN.mdinto context. - If no existing projects are found, recommend a ≤64-char lowercase slug based on what you know from the conversation (only
[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:
- Create and/or use the
<experiment-name>/directory using the confirmed name for storing all the artifacts
Directory Structure
When 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
├── manifests/ # Machine-readable outputs (JSON)
└── agent_memory/ # Session persistence (git-ignored)
└── session-notes.md # Progress, artifacts, next steps
Signals
- GitHub stars
- 893
- Forks
- 153
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
directory-management- Source
- github.com/awslabs/agent-plugins