Discover Tools skills, compare source repositories and read the instructions for each workflow.
Comprehensive org-mode file generation and editing with proper syntax, formatting, and structure. Use when Claude needs to work with org-mode files (.org) for: (1) Creating new org-mode documents, (2) Editing e...
提取PDF文件中的文本，并按标题/段落结构化输出。适用于文档总结、数据提取等场景。
Infrastructure as Code for AI workloads using Terraform across AWS, Azure, GCP, and OCI
Current best practices for Model Context Protocol server design, implementation, and integration. Updated patterns for 2025 MCP ecosystem including multi-server orchestration, security, and performance.
Deploy and operate AI workloads on Kubernetes with GPU scheduling, model serving, and MLOps patterns
Cost optimization for AI workloads - model selection, GPU sizing, commitment strategies, and multi-cloud cost management
Build autonomous AI agents using Claude Agent SDK with computer use, tool calling, MCP integration, and production best practices
Expert in Retrieval-Augmented Generation systems - knowledge bases, chunking strategies, embedding optimization, and production RAG architectures
Train and fine-tune LLMs using HuggingFace TRL, Transformers, and cloud GPU infrastructure with SFT, DPO, GRPO methods
Build AI applications on Azure using Azure OpenAI, Cognitive Services, and ML services with enterprise patterns
Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for building and managing agent systems.
Create professional architecture diagrams using D2, Draw.io, Mermaid, and OCI official icons for enterprise-grade visualizations
NVIDIA NIM inference microservices for deploying AI models with OpenAI-compatible APIs, self-hosted or cloud
Build AI applications on AWS using Bedrock, SageMaker, and AI/ML services with best practices for enterprise deployment
Enterprise AI security - OWASP LLM Top 10, prompt injection defense, guardrails, PII protection
Design and deploy AI workloads across AWS, Azure, GCP, and OCI with intelligent routing, cost optimization, and cross-cloud patterns
Production-grade AI architecture patterns for enterprise - security, governance, scalability, and operational excellence
Expert in OCI Generative AI Dedicated AI Clusters - deployment, fine-tuning, optimization, and production operations
Update work_index/index.json and index.json based on recent work folder activity and work_index.db. Use at the end of a task.
Workflow for using GitHub MCP + git to create private repos, sync main via git switch, branch safely, push without touching main, and open PRs. Use for any task that needs Git branching/publishing guidance.
Guidance for responding through Slack MCP: immediate acknowledgements, progress cadence, thread discipline, message templates, and failure handling. Use whenever Codex must reply to Slack mentions or share prog...
Record per-task work logs into each work folder's SQLite DB and update the global work_index.db summary after meaningful steps. Use whenever work starts or finishes.
This skill should be used when inspecting marimo notebook execution results. Triggers include: - Checking notebook output - Viewing execution results - Reading __marimo__ HTML snapshots - Debugging notebook er...
This skill should be used when working with marimo reactive notebooks for data science and analytics. Triggers include: - Creating new marimo notebooks - Converting Jupyter notebooks to marimo - Editing existi...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.