Claude Skills for a Data Scientist / ML — Page 40
Azure OpenAI Optimal Region Deployment
Automatically checks Azure capacity and deploys an Azure OpenAI model in a suitable available region.
M365 Agents Toolkit Installer
Install or update the M365 Agents Toolkit CLI and VS Code extension with intent-aware commands.
Contracts Engine Verifier
Verify contracts-engine changes end to end through its stdio MCP server.
NeMo MBridge Training Guide
Run Megatron-LM and Megatron Bridge training and verify whether their loss curves match.
cuTile Python Kernel Assistant
Guides developers in writing, debugging, validating, and optimizing high-performance cuTile GPU kernels.
TileGym cuTile Kernel Optimizer
Systematically reduce cuTile GPU kernel latency through profiling, bottleneck diagnosis, and controlled tuning.
Hugging Face Model Memory Estimator
Estimate inference memory without downloading model weights.
Hugging Face Local Model Runner
Choose compatible GGUF quantizations from Hugging Face and run them locally with llama.cpp.
Agent Platform Model Tuning
A guided end-to-end workflow for fine-tuning open or Gemini models on Google Agent Platform.
Google Agents CLI Agent Development Guide
Guides agents from specification through development, deployment, and monitoring.
Context Engineering for Production Agents
A structured guide to designing, optimizing, and evaluating production agent systems with reliable context management.
Context Efficiency Optimizer
Reduce context cost with caching, masking, compaction, and partitioning while preserving answer quality.
i4H Dataset Annotation Workflow
Use a vision-language model to verify task success and filter episodes for fine-tuning.
Jetpack Compose Styles Integration Skill
Integrate the Jetpack Compose Styles API into an Android project for unified theming and layout migration.
PDF Toolkit
A comprehensive PDF manipulation skill for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms.
SkillOpt-Sleep OpenClaw Reference Adaptation
A reference-only port of the SkillOpt-Sleep nightly self-evolution cycle to OpenClaw — for study and porting, not a ready-to-run integration.
PinchBench
Benchmarks LLMs as OpenClaw coding agents on real-world tasks, with a public leaderboard for side-by-side model comparison.
Graphify — Folder-to-Knowledge-Graph
Turns any folder of code, docs, papers, images, or video into a queryable knowledge graph so AI can answer real questions about your project.
Code Review and Testing Guidance
Helps coding agents choose and structure tests for logic changes.
Client Performance Report
Turn portfolio performance, allocation, holdings, and market context into a polished client-ready report.
Anthropic SDK Upgrade Assistant
Upgrade Anthropic SDK packages methodically while checking API changes, compilation, and Claude-focused tests.
Search View Results Reader
Reads the existing results in Visual Studio Code’s Search view.
VS Code Project Bootstrapper
Builds complete project scaffolds in VS Code from the requested project type.
Session Pull Request Assistant
Checks session changes and creates a GitHub pull request through GitHub MCP.