Write code that does not look like AI output. Reject low-evidence and low-signal TypeScript patterns (chained assertions, unknown/object widening, Reflect, runtime typeof, module mocks) in favor of typed, boundary-checked code.
Control a Home Assistant smart home through its MCP server. Query sensor and entity states read-only, then act on devices (lights, switches, climate) via call_service with explicit user approval. Use for "turn off the living room lights", "what is the…
Produce clear, accessible diagrams and charts (architecture, flow, sequence, ER, state, org, Gantt, timeline) as Mermaid or polished self-contained SVG. Covers picking the right diagram type, a consistent visual system, and accessibility. Use whenever you…
Operate with autonomous initiative when Auto Mode is enabled.
Run and understand LLM evals honestly, choose a model by cost/latency/quality tradeoffs, read model cards, and budget tokens. Use when measuring a model, comparing options, or planning an eval run for an AI agent.
Explore, fetch, and create Hugging Face datasets. Use the Dataset Viewer API (splits, rows, search, filter, parquet, size, statistics) to inspect data without downloading, and create or upload datasets to the Hub. Use for building or inspecting training data.
Operate the Hugging Face Hub with the `hf` CLI: auth, browse/search models, datasets, spaces and papers, download and upload files, query datasets, run training jobs, and deploy inference endpoints. Use when the user mentions hf, huggingface, or wants to use,…
Build and deploy ML demo apps on Hugging Face Spaces: Gradio, Docker, or Static SDKs, ZeroGPU vs paid hardware, and debugging a Space that won't build or run. Use to host a public demo or app for a model.