You are an expert in automotive supply chain management and manufacturing operations. Your goal is to help optimize complex multi-tier supply networks, implement just-in-time delivery, manage supplier

Use when starting any work session - establishes autonomous operation mode, overriding token limits and time pressure to work until goal is achieved

Configure autoscaling for Kubernetes, VMs, and serverless workloads based on metrics, schedules, and custom indicators.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

AWS Bedrock AgentCore comprehensive expert for deploying and managing all AgentCore services. Use when working with Gateway, Runtime, Memory, Identity, or any AgentCore component. Covers MCP target deployment, credential management, schema optimization, runtime configuration, memory management, and identity services.

AWS CLI 操作

AWS cloud operations for CloudWatch, S3, Lambda, EC2, and IAM

Optimize AWS costs through resource rightsizing and savings strategies

Build optimized serverless functions with Lambda

Use when build times are slow, investigating build performance, analyzing Build Timeline, identifying type checking bottlenecks, enabling compilation caching, or optimizing incremental builds - comprehensive build optimization workflows including Xcode 26 compilation caching

Use when app runs at unexpected frame rate, stuck at 60fps on ProMotion, frame pacing issues, or configuring render loops. Covers MTKView, CADisplayLink, CAMetalDisplayLink, frame pacing, hitches, system caps.

Complete energy optimization API reference - Power Profiler workflows, timer/network/location/background APIs, iOS 26 BGContinuedProcessingTask, MetricKit monitoring, with all WWDC code examples

Use when writing ANY code with async, actors, threads, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns, performance optimization.

Use when app feels slow, memory grows, battery drains, or diagnosing ANY performance issue. Covers memory leaks, profiling, Instruments workflows, retain cycles, performance optimization.

Use when building, fixing, or improving ANY iOS UI including SwiftUI, UIKit, layout, navigation, animations, design guidelines. Covers view updates, layout bugs, navigation issues, performance, architecture, Apple design compliance.

MetricKit API reference for field diagnostics - MXMetricPayload, MXDiagnosticPayload, MXCallStackTree parsing, crash and hang collection

Use when optimizing large value type performance, working with noncopyable types, or reducing ARC traffic. Covers borrowing, consuming, inout modifiers, consume operator, ~Copyable types.

Use when UI is slow, scrolling lags, animations stutter, or when asking 'why is my SwiftUI view slow', 'how do I optimize List performance', 'my app drops frames', 'view body is called too often', 'List is laggy' - SwiftUI performance optimization with Instruments 26 and WWDC 2025 patterns

Use when needing thread-safe primitives for performance-critical code. Covers Mutex (iOS 18+), OSAllocatedUnfairLock (iOS 16+), Atomic types, when to use locks vs actors, deadlock prevention with Swift Concurrency.

subject not detected, hand pose missing landmarks, low confidence observations, Vision performance, coordinate conversion, VisionKit errors, observation nil, text not recognized, barcode not detected, DataScannerViewController not working, document scan issues

Use when automating Instruments profiling, running headless performance analysis, or integrating profiling into CI/CD - comprehensive xctrace CLI reference with record/export patterns

azure-ai-evaluation-py

Retrieve and monitor log files from B2C Commerce instances. Use when fetching recent errors, searching log entries, filtering by level/time, or real-time tailing. The `logs get` command is optimized for coding agents with JSON output.

Comprehensive backend development guidelines covering API design, database patterns, security, performance, and production-ready code standards.

Backend and API implementation patterns for scalability, security, and maintainability. Use when building APIs, services, and backend infrastructure.

Master Python asyncio, concurrent programming, and async/await patterns for high-performance FastAPI applications. Use when building async APIs, concurrent systems, or I/O-bound applications requiring non-blocking operations.

**Deep research-driven skill for finding optimal backend architectures and patterns.**

Find and fix API performance bottlenecks.

Write secure, optimized database queries using parameterized statements, eager loading, and proper indexing to prevent SQL injection and N+1 query problems. Use this skill when writing database queries, using ORM query methods, implementing data fetching logic, or optimizing database performance. When working with SQL queries, ORM query builders, repository patterns, or data access layers. When implementing joins, eager loading, query optimization, transactions, or query caching. When selecting data, filtering records, or fetching related associations in service files, repository files, or controller methods.

Manage data flow when producers outpace consumers. Bounded buffers, adaptive flushing, and graceful degradation prevent OOM crashes and data loss.

Process data with custom algorithms

Analyze and optimize bash scripts according to strict standards: performance, modern tooling, consolidation patterns.

Use when storing project artifacts in basic memory storage.

This skill should be used when users need to rent GPUs, run ML training jobs, or manage compute resources on Basilica's decentralized GPU marketplace. Use it for PyTorch/TensorFlow training, distributed training setup, GPU rental management, cost monitoring, or any Basilica CLI workflows. Includes workaround for non-TTY environments like Claude Code.

Integrate multiple scRNA-seq samples/batches using Harmony, scVI, Seurat anchors, and fastMNN. Remove technical variation while preserving biological differences. Use when integrating multiple scRNA-seq batches or datasets.

Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.

Set up and orchestrate multi-agent workflows using Beads (shared issue tracking/memory) and MCP Agent Mail (agent messaging). Use when coordinating multiple agents, setting up agent villages, tracking work across agent sessions, or implementing swarm workflows.

Use Beads CLI (`bd`) commands to manage tasks, status, and progress tracking for Ralph's autonomous execution. Use when: (1) Querying ready tasks with `bd ready`, (2) Updating task status (open → in_progress → closed), (3) Adding progress comments to tasks, (4) Managing task details (priority, design, notes, labels), (5) Handling task dependencies. This skill enables Ralph to use Beads' native memory and state management.

Creating, updating, and closing Beads issues with proper types, priorities, and metadata

Track complex, multi-session work with dependency graphs using beads (beads) issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.

>

This skill provides patterns for MongoDB integration using Beanie ODM with async Motor driver, optimized for FastAPI applications.

Amazon Bedrock AgentCore Memory for persistent agent knowledge across sessions. Episodic memory for learning from interactions, short-term for session context. Use when building agents that remember user preferences, learn from conversations, or maintain context across sessions.

AI operasyonel modları (beyin fırtınası, uygulama, hata ayıklama, inceleme, öğretme, dağıtım, orkestrasyon). Görev türüne göre davranışı uyarlamak için kullanın.

Talk to Ben Heath Youtuber about their expertise. Ben Heath Youtuber provides authentic advice using their mental models, core beliefs, and real-world examples.

Measure function performance and compare implementations. Use when optimizing critical code paths.

Benchmark Neovim startup time and identify slow plugins or configurations

Quick-start command to run SWE-bench Lite evaluation with sensible defaults.

Benchmarking and competitive analysis techniques. Compares performance, processes, and practices against industry standards, competitors, and best-in-class organizations.

Add a complete account settings page with profile editing, password changes, email updates, session management, and account deletion.