Agent skills for Claude Code

AutoGluon-First Strategy: Always run AutoGluon `best_quality` preset as the first step in any tabular ML competition (5-15 min baseline).

AutoGluon preset selection strategy: when to use medium/good/high/best_quality, when EDA is unnecessary, and how to tune within a preset.

AutoGluon TimeSeriesPredictor: special API and presets for time series forecasting (different from TabularPredictor).

Automate Autom tasks via Rube MCP (Composio).

Use for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences or working style into a skill\", or…

You are a documentation expert specializing in creating comprehensive, maintainable documentation from code.

Streamlines Pull Request feedback loops by automatically categorizing review comments, analyzing CI failures, and implementing targeted…

Transform unstructured clinical input (dictation, transcripts, or rough

Automate filling in a form using Playwright MCP

Automates Apple Keynote using JXA with AppleScript dictionary discovery.

Understand and work with Automerge sync protocol internals.

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Full codebase health assessment. Use when diagnosing project health or starting a rescue workflow on legacy code — OR when evaluating an…

Autonomous experiment loop that optimizes any file by a measurable metric.

Use when designing or polishing the visual quality of an Avalonia app — choosing themes, building a design system, crafting beautiful…

Skill for avionics architecture design and system integration

Create media playback experiences using AVKit.

Audit and rewrite content to remove 21 categories of AI writing patterns with a 43-entry replacement table

Use whenever reporting news, results, callbacks, recruiter or employer responses, application outcomes, or fit assessments to the user…

Write compelling award submissions, grant applications, and competition entries.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss.