0010 views
Shareable instruction files for Cursor, Claude Code, Copilot, Windsurf, and more — installed alongside your existing agent rules.
1. Ensure the `uv` tool is available on your system. If not, run: 2. From the project root execute: The script will create a local virtual environment using **uv** and install the package in editable mode with development extras.
1. **Long-running Commands**: When executing commands that typically take a significant amount of time (such as `npm run build`, `npm run lint`, or test suites), you MUST wait for user input or confirmation before proceeding to the next step. Do not auto-run subsequent steps assuming the command has finished immediately.
1. **System 2 Thinking**: Approach the problem with analytical rigor. Break down the requirements into smaller, manageable parts and thoroughly consider each step before implementation. 2. **Tree of Thoughts**: Evaluate multiple possible solutions and their consequences. Use a structured approach to explore different paths and select the optimal one.
const handleApiCall = async () => { const response = await api('/endpoint', { method: 'POST', body: data }); if (response.status !== STATUS.OK) throw new Error(response.message); showToast('Success message', 'success');
`multi-agent-reference-architecture` is the NVIDIA SA capstone reference implementation demonstrating production-ready multi-agent LLM orchestration using LangGraph with fully YAML-driven graph assembly. It is 100% feature-complete and serves as the primary ISV customization surface in the NVIDIA SA portfolio. This repo is what an NVIDIA Solutions Architect shows a customer or ISV partner as the "how to build on NIM" reference. `core/graph_builder.py` reads agent YAML configs and dynamically ass
Anda adalah SENIOR FULL-STACK WEB DEVELOPER (10+ tahun pengalaman), spesialis: middleware via bootstrap/app.php, validasi/form request, migration & seeder, artisan CLI, build aset Vite charset utf8mb4, autentikasi caching_sha2_password
Eres el copiloto de desarrollo principal de EcoTrack, una app que estima la huella de carbono diaria a partir de una descripción en lenguaje natural (ej. "Hoy comí carne y viajé 20km en bus"). Actúas como ejecutor: yo doy la
Use `memory.*` MCP tools as a persistent memory loop when available. **Namespace for all operations in this repo:** { "repo_url": "https://github.com/matt-antone/ai-memory" } Do not pass `agent` or `repo_name` — set automatically. Global items (no `repo_url`) are always included in repo-scoped searches.