Loading...
Loading...
Found 552 Skills
External verl end-to-end validation workflow for Megatron-Bridge model/provider changes. Covers running a small verl Megatron backend job from a Bridge checkout, choosing LoRA/DDP plus optional save/resume and parallelism variants, setting PYTHONPATH so verl imports the local Bridge tree, and reporting pass/fail evidence.
This skill should be used when working with CSV files to create interactive data visualizations, generate statistical plots, analyze data distributions, create dashboards, or perform automatic data profiling. It provides comprehensive tools for exploratory data analysis using Plotly for interactive visualizations.
Guide for creating Observable Notebooks 2.0, the open-source notebook system for interactive data visualization and exploration. Use this skill when creating, editing, or building Observable notebooks.
Explore-first wave pipeline. Decomposes requirement into exploration angles, runs wave exploration via spawn_agents_on_csv, synthesizes findings into execution tasks with cross-phase context linking (E*→T*), then wave-executes via spawn_agents_on_csv.
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", or "test this app" on mobile. Produces a structured report with reproducible evidence: screenshots, optional repro videos, and detailed steps for every issue.
Bounded codebase exploration and architecture mapping. Use when discovery is needed before implementation. Do NOT use for broad refactoring — use do-plan instead.
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
LoRA, full fine-tuning, DPO preference tuning, VLM training, function-calling tuning, reasoning tuning, and BYOM uploads on Together AI. Reach for it whenever the user wants to adapt a model on custom data rather than only run inference, evaluate outputs, or host an existing model.
explore — Deep codebase exploration with parallel agents. Use when exploring a repo or discovering architecture.
Fast in-process analytical database for SQL queries on DataFrames, CSV, Parquet, JSON files, and more. Use when user wants to perform SQL analytics on data files or Python DataFrames (pandas, Polars), run complex aggregations, joins, or window functions, or query external data sources without loading into memory. Best for analytical workloads, OLAP queries, and data exploration.
Runs tilth CLI for structural code navigation — reads files with smart outlining, searches symbols/text/regex, finds files by glob, and maps codebases. Use instead of read/grep/find for all source code exploration.
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization