Claude Skills

Consumer-driven contract testing with Pact for API compatibility. Use when testing microservice integrations, verifying API contracts, preventing breaking changes, or implementing provider verification.

Idempotency patterns for APIs and event handlers. Use when implementing exactly-once semantics, deduplicating requests, or building reliable distributed systems.

Biome 2.0+ linting and formatting for fast, unified code quality. Includes type inference, ESLint migration, CI integration, and 421 lint rules. Use when migrating from ESLint/Prettier or setting up new projects.

Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.

LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning, data creation. Use when customizing models for specific domains.

LLM function calling and tool use patterns. Use when enabling LLMs to call external tools, defining tool schemas, implementing tool execution loops, or getting structured output from LLMs.

High-performance LLM inference with vLLM, quantization (AWQ, GPTQ, FP8), speculative decoding, and edge deployment. Use when optimizing inference latency, throughput, or memory.

Security patterns for LLM integrations including prompt injection defense and hallucination prevention. Use when implementing context separation, validating LLM outputs, or protecting against prompt injection attacks.

Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing async timeouts, or validating structured outputs from LLMs.

Comprehensive prompt engineering with Chain-of-Thought, few-shot learning, prompt versioning, and optimization. Use when designing prompts, improving accuracy, managing prompt lifecycle.

GPT-5/4o, Claude 4.5, Gemini 2.5/3, Grok 4 vision patterns for image analysis, document understanding, and visual QA. Use when implementing image captioning, document/chart analysis, or multi-image comparison.

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.

Statistical and quality drift detection for LLM applications. Use when monitoring model quality degradation, input distribution shifts, or output pattern changes over time.

LLM observability platform for tracing, evaluation, prompt management, and cost tracking. Use when setting up Langfuse, monitoring LLM costs, tracking token usage, or implementing prompt versioning.

PII detection and masking for LLM observability. Use when logging prompts/responses, tracing with Langfuse, or protecting sensitive data in production LLM pipelines.

Reference patterns for parsing skill metadata. Use when extracting phases, examples, or features from SKILL.md files for demo generation

Use when backing up, restoring, or validating golden datasets. Prevents data loss and ensures test data integrity for AI/ML evaluation systems.

Use when validating golden dataset quality. Runs schema checks, duplicate detection, and coverage analysis to ensure dataset integrity for AI evaluation.

LLM output evaluation and quality assessment. Use when implementing LLM-as-judge patterns, quality gates for AI outputs, or automated evaluation pipelines.

OKR framework, KPI trees, leading/lagging indicators, and success metrics patterns. Use when defining goals, measuring outcomes, or building measurement frameworks.

User stories, acceptance criteria, PRDs, and requirements documentation patterns. Use when translating product vision to engineering specs, writing user stories, or creating requirements documents.

Comprehensive API design patterns for REST, GraphQL, and gRPC. Use when designing APIs, creating endpoints, adding routes, implementing pagination, rate limiting, or authentication patterns.

API versioning strategies including URL path, header, and content negotiation. Use when migrating v1 to v2, handling breaking changes, implementing deprecation or sunset policies, or managing backward compatibility.

RFC 9457 Problem Details for standardized HTTP API error responses. Use when implementing problem details format, structured API errors, error registries, or migrating from RFC 7807.