This guide covers the full lifecycle of building, running, and serving a custom OpenBB Workspace application from an extension project scaffolded by openbb-cookiecutter. It assumes the project shell already exists (see the developextension skill for scaffolding instructions).
This is a complete guide for creating a new OpenBB Platform extension from scratch. Follow every phase in order. When the user says "build me an application that does X", use this guide to scaffold, implement, install, and verify the extension.
Address all valid review comments on a PR for the current branch in the streamlit/streamlit repo. Covers both inline review comments and general PR (issue) comments. Use when a PR has reviewer feedback to address, including code changes, style fixes, and documentation updates.
Generates polished website release notes between two git tags for docs.streamlit.io. Use when preparing a new Streamlit release or reviewing changes between versions.
Explains Streamlit's internal architecture including backend runtime, frontend rendering, and WebSocket communication. Use when debugging cross-layer issues, understanding how features work end-to-end, planning architectural changes, or onboarding to the codebase. Covers ForwardMsg/BackMsg protocol, script rerun…
Write comprehensive, behaviour-driven unit tests for Gradio frontend Svelte components using Vitest browser mode, Playwright, and the @self/tootils test utilities.
Build and customise Gradio themes. Use when creating, editing, or publishing Python-based Gradio themes that control colours, typography, spacing, shadows, and dark mode.
Build Gradio web UIs and demos in Python. Use when creating, modifying, debugging, or answering questions about Gradio and its capabilties, components, event listeners, or layouts.
Estimate a public equity's intrinsic value with a discounted-cash-flow model — pull fundamentals, set a discount rate via CAPM/WACC, project free cash flow, and discount it.
A thorough single-equity deep dive — read the recent qualitative picture from the web, then ground it in fundamentals and health ratios, an intrinsic DCF with a sensitivity range, a comparable-company cross-check, and the analyst-consensus view.
Value an equity against its peers — peer-median trading multiples applied to the company's metrics for an implied range, cross-read against its own valuation ratios.
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
Upload one or more local images or videos to GitHub and get back a user-attachments URL for each, to embed in a PR body, issue, or comment. Use when asked to attach screenshots or screen recordings.
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
Fill empty description: "" fields in packages/llm-info/data/models.yml by querying OpenRouter and provider documentation. Use when the user asks to populate model descriptions, enrich the model catalog, or backfill descriptions after running pnpm sync-models.
Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training…
Use when launching cloud VMs, Kubernetes pods, or Slurm jobs for GPU/TPU/CPU workloads, training or fine-tuning models on cloud GPUs, deploying inference servers (vllm, TGI, etc.) with autoscaling, writing or debugging SkyPilot task YAML files, using spot/preemptible instances for cost savings, comparing GPU prices…
Anomaly detection expert backed by PyOD's ADEngine. Drives autonomous detection workflows on tabular, time series, graph, text, and image data: profiling, planning, multi-detector comparison, quality assessment, iteration, and reporting. Encodes deep OD knowledge so non-expert users can run the full workflow without…
Add a new self-contained example agent under examples/. Use when asked to "create an example for ", "add a tutorial agent", "demo integration with ", or when showcasing a new pattern users should copy.