Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when documenting significant technical decisions, reviewing past...

Divide-and-conquer implementation from specs/plans. Decomposes a reference document into independent tasks, assigns each to a builder agent, executes in parallel waves respecting dependencies,...

Grafana or CloudWatch dashboard definitions

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat),...

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat),...

Build and maintain AI-accessible knowledge bases for projects

Determine the best Anthropic architecture for your project by analyzing requirements and recommending the optimal combination of Skills, Agents, Prompts, and SDK primitives.

Determine the best Anthropic architecture for your project by analyzing requirements and recommending the optimal combination of Skills, Agents, Prompts, and SDK primitives.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or...

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or...

Create platform-optimized social media graphics

Documents OneKey push notification system across platforms. Use when implementing notification features, handling notification clicks, configuring backend payloads, or understanding cold start...

Complete X (Twitter) algorithm mastery - engagement weights, viral formulas, shadow ban avoidance, thread optimization, and growth strategies. Based on X's open-source code analysis and real creator data.

Coordinate multiple AI agents and skills for complex workflows

|

Design serverless function deployments for AWS Lambda, Azure Functions, and Google Cloud Functions with event sources, IAM, and cold start optimization.

Metrics, alarms, and observability configuration

Use when need explicit quality criteria and scoring scales to evaluate work consistently, compare alternatives objectively, set acceptance thresholds, reduce subjective bias, or when user mentions...

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for...

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for...