Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/
npx skills add https://github.com/github/awesome-copilot --skill create-llms
Create a new llms.txt file from scratch in the root of the repository following the official llms.txt specification at https://llmstxt.org/. This file provides high-level guidance to large language models (LLMs) on where to find relevant content for understanding the repository's purpose and specifications.
Create a comprehensive llms.txt file that serves as an entry point for LLMs to understand and navigate the repository effectively. The file must comply with the llms.txt specification and be optimized for LLM consumption while remaining human-readable.
Before creating the llms.txt file, you must complete a thorough analysis:
.md files in /docs/, /spec/, etc.)Based on your analysis, create a structured plan that includes:
The llms.txt file must follow this exact structure per the specification:
Each file link must follow: descriptive-name: optional description
Organize files into logical H2 sections such as:
Include files that:
Exclude files that:
llms.txt file in the repository root/llms.txt)# [Repository Name]
> [Concise description of the repository's purpose and scope]
[Optional additional context paragraphs without headings]
## Documentation
- [Main README](README.md): Primary project documentation and getting started guide
- [Contributing Guide](CONTRIBUTING.md): Guidelines for contributing to the project
- [Code of Conduct](CODE_OF_CONDUCT.md): Community guidelines and expectations
## Specifications
- [Technical Specification](spec/technical-spec.md): Detailed technical requirements and constraints
- [API Specification](spec/api-spec.md): Interface definitions and data contracts
## Examples
- [Basic Example](examples/basic-usage.md): Simple usage demonstration
- [Advanced Example](examples/advanced-usage.md): Complex implementation patterns
## Configuration
- [Setup Guide](docs/setup.md): Installation and configuration instructions
- [Deployment Guide](docs/deployment.md): Production deployment guidelines
## Optional
- [Architecture Documentation](docs/architecture.md): Detailed system architecture
- [Design Decisions](docs/decisions.md): Historical design decision records
The created llms.txt file should:
Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.
Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstrings in PyTorch code.
Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".
Use when working directly with the `esm` Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.
Use Therapeutics Data Commons through the PyTDC Python package for registry discovery, approved dataset access, task-aware splits, evaluator metrics, benchmark groups, and bounded molecular-oracle workflows.
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
Take github/create-llms from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.