Claude Skills by a5c-ai

Human-in-the-loop integration for LangGraph workflows with approval and intervention points

Conditional edge routing and state-based transitions for LangGraph workflows

LangGraph StateGraph builder with state schema design. Create stateful agent workflows with cycles, conditionals, and persistence.

Subgraph composition and modular workflow design for LangGraph

LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.

LlamaIndex agent and query engine setup for RAG-powered agents

LLM-based zero-shot and few-shot classification for flexible intent detection

Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.

Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.

Comprehensive Content Security Policy audit for MCP Apps in sandboxed iframes. Discovers all network origins, traces them to source, and generates CSP configuration for registerAppResource.

Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.

Implements the core MCP Apps architectural pattern where a Tool declares _meta.ui.resourceUri referencing a registered Resource. Covers registerAppTool, registerAppResource, text fallback, structuredContent, and app-only helper tools.

Build medical AI agents for clinical decision support, medical record summarization, diagnostic assistance, and healthcare workflow automation.

Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.

Conversation summarization for memory compression and context management

Milvus distributed vector database configuration for large-scale RAG applications

Orchestrate workflows across multiple applications and APIs — inter-app coordination, data handoff, and multi-system task completion.

Design agents for multi-turn tool use — sequential tool calls, result accumulation, error recovery, and complex task decomposition over multiple turns.

NVIDIA NeMo Guardrails configuration for conversational safety and control

OpenTelemetry instrumentation for LLM applications with distributed tracing

Arize Phoenix observability platform setup for LLM debugging and evaluation

PII detection and redaction utilities for privacy-compliant conversational AI

Pinecone vector database setup, configuration, and operations for RAG applications

Token-efficient prompt compression techniques for cost optimization

Prompt injection detection and prevention for secure LLM applications

Structured prompt template creation with variables, formatting, and version control

Qdrant vector database with filtering, payloads, and quantization support

Document chunking with multiple strategies including semantic, recursive, and fixed-size chunking

Batch embedding generation with caching, rate limiting, and multiple provider support

Hybrid search combining semantic and keyword retrieval for RAG pipelines. Implement BM25 + dense vector search with fusion strategies.

Query expansion, HyDE, and multi-query generation for improved retrieval

Cross-encoder reranking and MMR diversity filtering for improved retrieval quality

Rasa NLU pipeline configuration and training for intent and entity extraction

Redis backend for conversation state persistence and caching

Microsoft Semantic Kernel planner and plugin setup for orchestrated AI

SetFit few-shot learning for efficient intent classification with minimal data

Configure Vite with vite-plugin-singlefile for mandatory single-file HTML bundling of MCP Apps. All assets (JS, CSS, images, fonts) must be inlined into a single HTML file for sandboxed iframe compatibility.

spaCy NER model training and entity extraction for conversational AI

Induce visual patterns from examples — few-shot visual reasoning, grid-based pattern recognition, and ARC-style inductive inference.

Weaviate vector database setup with GraphQL queries and hybrid search

Zep memory server integration for long-term conversation memory and user profiling

Provide implementations of advanced data structures

Generate visual representations of algorithm execution

Interface with AtCoder for Japanese competitive programming contests

Profile code performance and identify bottlenecks

Manage and generate competitive programming templates

Interface with Codeforces API for contest data, problem sets, and submissions

Calculate combinatorial values with modular arithmetic

Automated Big-O complexity analysis of code and algorithms. Performs static analysis of loop structures, recursive call trees, space complexity estimation, and amortized analysis with detailed derivation documents.

Select optimal data structure based on operation requirements