io.github.Kastalien-Research/thoughtbox

Access 15 mental models for structured reasoning. Each model provides a complete prompt with process steps, examples, and pitfalls. Mental models are process scaffolds that tell you HOW to think about a problem, not WHAT to think. They're infrastructure for your reasoning. Operations: - get_model: Retrieve a specific mental model prompt - list_models: List available models (optionally filtered by tag) - list_tags: List all available tags with descriptions - get_capability_graph: Get structured data for knowledge graph initialization Available tags: debugging, planning, decision-making, risk-analysis, estimation, prioritization, communication, architecture, validation Use list_models with a tag filter to discover relevant models for your task. For example, use tag "debugging" when stuck on an issue, or "decision-making" when choosing between options.

Notebook toolhost for literate programming with JavaScript/TypeScript. Create, manage, and execute interactive notebooks with markdown documentation and executable code cells. Each notebook runs in an isolated environment with its own package.json and workspace. ✨ NEW: Pre-structured templates for guided workflows - Use template: "sequential-feynman" for deep learning with Feynman Technique - Templates provide scaffolded cells, metacognitive prompts, and progress tracking - Perfect for complex topics requiring validated understanding Available operations: - create: Create a new notebook (optionally from template) - list: List all active notebooks - load: Load notebook from .src.md file - add_cell: Add cell (title/markdown/code) - update_cell: Update cell content - run_cell: Execute code cell - install_deps: Install npm dependencies - list_cells: List all cells in notebook - get_cell: Get cell details - export: Export notebook to .src.md Common operation examples: Create a blank notebook: { operation: "create", args: { title: "My Analysis", language: "typescript" } } Create from Sequential Feynman template: { operation: "create", args: { title: "React Server Components", language: "typescript", template: "sequential-feynman" } } Add a code cell: { operation: "add_cell", args: { notebookId: "abc123", cellType: "code", content: "console.log('hello')", filename: "example.ts" } } Run a cell: { operation: "run_cell", args: { notebookId: "abc123", cellId: "cell_456" } } List notebooks: { operation: "list", args: {} } For detailed schemas of all operations, see the thoughtbox://notebook/operations resource. When to use: - Writing executable documentation - Building reproducible code examples - Creating step-by-step tutorials - Developing and testing code snippets - Prototyping with immediate feedback - Deep learning workflows (with templates)

Step-by-step thinking tool for complex problem-solving. Supports flexible reasoning: forward thinking (1→N), backward thinking (N→1), branching, and revision. Adjust your approach dynamically as understanding deepens. Use for: - Multi-step analysis and planning - Problems requiring course correction - Hypothesis generation and testing - System design and architecture decisions Patterns Cookbook: Automatically provided at thought 1 with 6 core reasoning patterns, examples, and best practices. Request anytime with includeGuide parameter.