Claude Awesome Stack

claude-awesome-stack

Installable stack packs for Claude Code -- production-ready configurations of skills, hooks, and project instructions for domain-specific development.

Unlike link-collection "awesome lists", this repo gives you working setups you copy into your project for an immediate, opinionated Claude Code experience.

How It Works

graph LR
    A[claude-awesome-stack] -->|copy| B[Your Project]
    subgraph "Stack Pack"
        C[CLAUDE.md]
        D[skills/]
        E[hooks/]
        F[settings.json]
    end
    subgraph "Your Project"
        G[CLAUDE.md]
        H[.claude/skills/]
        I[.claude/hooks/]
        J[.claude/settings.json]
    end
    C --> G
    D --> H
    E --> I
    F --> J

Quick Start

# 1. Clone
git clone https://github.com/giacomogaglione/claude-awesome-stack.git

# 2. Copy a stack into your project
cp -r claude-awesome-stack/stacks/python-ml/CLAUDE.md ./CLAUDE.md
mkdir -p .claude/skills .claude/hooks
cp -r claude-awesome-stack/stacks/python-ml/skills/* .claude/skills/
cp -r claude-awesome-stack/stacks/python-ml/hooks/* .claude/hooks/
cp claude-awesome-stack/stacks/python-ml/settings.json .claude/settings.json

# 3. Start Claude Code
claude

Available Stacks

| Stack | Status | Description | |-------|--------|-------------| | [Python/ML](stacks/python-ml/) | Ready | ML conventions, debugging skills, auto-formatting hooks | | [Frontend](stacks/frontend/) | Coming soon | React/Next.js development |

Python/ML Stack

| Component | What It Does | |-----------|--------------| | CLAUDE.md | ML conventions: tensor shapes, dtype checks, anti-patterns, testing patterns | | ml-debug skill | Systematic debugging: shapes, NaN propagation, gradients, devices, dtypes | | data-explore skill | Dataset profiling: schema, distributions, missing values, outliers, correlations | | notebook-refactor skill | Extract Jupyter notebooks into tested Python modules | | python-lint.sh hook | Auto-format with ruff + black on every file edit | | type-check.sh hook | pyright/mypy type checking after edits | | test-guard.sh hook | Run relevant pytest tests when source files change | | pyproject.toml template | Dev/ML/torch dependency groups with ruff, black, pyright config | | .env.example template | Common ML environment variables |

Hook Execution Flow

sequenceDiagram
    participant C as Claude Code
    participant H as Hooks
    participant T as Tools

    C->>C: Edit Python file
    C->>H: PostToolUse event (JSON)
    H->>T: ruff check --fix
    H->>T: black format
    H->>T: pyright type-check
    H->>T: pytest (matching tests)
    H-->>C: Results fed back to conversation

Curated Resources

Hand-picked tools and patterns for Claude Code:

| Resource | Description | |----------|-------------| | [MCP Servers](curated/mcp-servers.md) | Categorized MCP servers for data, cloud, monitoring, and more | | [Skills](curated/skills.md) | Community skills reviewed for quality and compatibility | | [Hook Recipes](curated/hooks.md) | Ready-to-use hook patterns for linting, testing, security, and productivity |

Documentation

• [Installation Guide](docs/install.md) -- step-by-step setup
• [Architecture](docs/architecture.md) -- how stacks work and why
• [Creating Stacks](docs/creating-stacks.md) -- contributor guide for new stacks

Contributing

See [CONTRIBUTING.md](CONTRIBUTING.md) for how to submit stacks, skills, hook recipes, or curated list entries.

License

[MIT](LICENSE)

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: giacomogaglione
• Source: giacomogaglione/claude-awesome-stack
• License: MIT

Install and usage instructions live in the source repository linked above.