LLM & Agents

Guides development with SAP AI Core and SAP AI Launchpad for enterprise AI/ML workloads on SAP BTP. Use when: deploying generative AI models (GPT, Claude, Gemini, Llama), building orchestration workflows with templating/filtering/grounding, implementing RAG with vector databases, managing ML training pipelines with Argo Workflows, configuring content filtering and data masking for PII protection, using the Generative AI Hub for prompt experimentation, or integrating AI capabilities into SAP applications. Covers service plans (Free/Standard/Extended), model providers (Azure OpenAI, AWS Bedrock, GCP Vertex AI, Mistral, IBM), orchestration modules, embeddings, tool calling, and structured outputs.

Implements stateful agent graphs using LangGraph. Use when building graphs, adding nodes/edges, defining state schemas, implementing checkpointing, handling interrupts, or creating multi-agent systems with LangGraph.

Record quality metrics baseline before refactoring or major changes, capturing audit scores, test coverage, and complexity for comparison

World-class security content writer for VibeShip Knowledge Base. Creates authoritative, SEO-optimized, LLM-extractable content about cybersecurity vulnerabilities in AI-generated code.Use this skill when:- Writing vulnerability articles (SQL injection, XSS, IDOR, etc.)- Creating AI tool security analysis (Cursor, Claude Code, Bolt patterns)- Writing stack security guides (Next.js + Supabase, Express, etc.)- Generating fix prompts for AI coding tools- Creating security checklists and glossary entries- Writing research content (Vulnerability Index, methodology)- Any security-related KB content for vibeship.co/kb/security/Expertise: SEO optimization, LLM citation optimization, OWASP vulnerabilities, CWE database, AI-generated code patterns, vibe coder audience, technical writing for non-security-experts.

Using Qwen 2.5 models via Ollama for local LLM inference, text analysis, and AI-powered automation

Generate a plan for how an agent should accomplish a complex coding task. Use when a user asks for a plan, and optionally when they want to save, find, read, update, or delete plan files in $CODEX_HOME/plans (default ~/.codex/plans).

World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.

Local LLM inference with Ollama. Use when setting up local models for development, CI pipelines, or cost reduction. Covers model selection, LangChain integration, and performance tuning.

Expert in creating Claude Code subagents, skills, slash commands, plugins, and plugin marketplaces. Automatically activates when working with .md files in .claude/ directories, agent/command/skill frontmatter, marketplace.json, or when discussing Claude Code extensibility and component creation.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PermissionRequest, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

LangGraph parallel execution patterns. Use when implementing fan-out/fan-in workflows, map-reduce over tasks, or running independent agents concurrently.

Enforce mandatory npm test and npm run lint execution after every code change with no exceptions for code quality and test coverage compliance

Validate test coverage meets minimum thresholds (default 80% overall, 80% statements, 75% branches, 80% functions). Parses coverage reports from coverage/coverage-summary.json or test output. Returns pass/fail status with detailed metrics and identifies uncovered files.

LLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings, or attributing costs to agents in multi-agent systems.

LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with tool calls.

Guide for adding new AI platform support (e.g., Gemini, Mistral, Anthropic) to the Chrome extension with strategy pattern and testing requirements

Guides you through creating well-structured Claude Code skills with proper modularization, templates, and best practices. Use when creating new skills or improving existing ones.

Complete quality validation workflow combining TypeScript checking, linting, tests, coverage, and build validation. Works with any TypeScript/JavaScript project. Returns structured pass/fail with detailed results for each check. Used in conductor workflows and quality assurance phases.

sqlite-vec extension for vector similarity search in SQLite. Use when storing embeddings, performing KNN queries, or building semantic search features. Triggers on sqlite-vec, vec0, MATCH, vec_distance, partition key, float[N], int8[N], bit[N], serialize_float32, serialize_int8, vec_f32, vec_int8, vec_bit, vec_normalize, vec_quantize_binary, distance_metric, metadata columns, auxiliary columns.

Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, constructing context from retrieved documents, adding citations, or implementing hybrid search.