Integrate CoreWeave deployments into CI/CD pipelines with GitHub Actions. Use when automating container builds, deploying inference services from CI, or validating GPU manifests…
Score 70/100
Collect CoreWeave cluster diagnostics for support tickets. Use when preparing a support case, collecting GPU node status, or documenting pod failures.
Score 70/100
Deploy inference services on CoreWeave with Helm charts and Kustomize. Use when deploying multi-model inference, managing GPU deployments at scale, or templating CoreWeave…
Score 70/100
Deploy a GPU workload on CoreWeave with kubectl. Use when running your first GPU job, testing inference, or verifying CoreWeave cluster access.
Score 70/100
Configure CoreWeave Kubernetes Service (CKS) access with kubeconfig and API tokens. Use when setting up kubectl access to CoreWeave, configuring CKS clusters, or authenticating…
Score 70/100
Set up local development workflow for CoreWeave GPU deployments. Use when building containers locally, testing YAML manifests, or iterating on model serving configurations before…
Score 70/100
Production readiness checklist for CoreWeave GPU workloads. Use when launching inference services, preparing GPU training for production, or validating deployment configurations.
Score 70/100
Handle CoreWeave API and GPU quota limits. Use when hitting quota limits, managing GPU resource allocation, or implementing request queuing for inference endpoints.
Score 70/100
Reference architecture for CoreWeave GPU cloud deployments. Use when designing ML infrastructure, planning multi-model serving, or establishing CoreWeave deployment standards.
Score 70/100
Upgrade CoreWeave deployments and migrate between GPU types. Use when migrating from A100 to H100, upgrading CUDA versions, or updating inference server versions.
Score 70/100
Master Kotlin coroutines with suspend functions, flows, channels, and structured concurrency for building async applications.
Score 70/100
Genera el código completo de archivos React para corregir errores de ejecución (como propiedades indefinidas), respondiendo siempre en español y sin proporcionar ejemplos…
Score 70/100
Implement distributed tracing with correlation IDs, trace propagation, and span tracking across microservices.
Score 70/100
Automatically validates Cloudflare Workers CORS configuration, ensuring proper headers, OPTIONS handling, and origin validation for cross-origin requests
Score 70/100
Debug and fix memory system issues — validate memories, rate quality, manage protection, forget bad memories, and restore from checkpoints.
Score 70/100
Design and implement an AI feature integration — model selection, architecture pattern, system prompt, data flow, error handling, cost estimate.
Score 70/100
Search and retrieve memories from Cortex persistent memory. Use when the user asks 'what did we decide about X', 'do you remember', 'what was the fix for', 'find that thing…
Score 70/100
Search and retrieve global memories — knowledge that applies across all projects. Use when the user asks 'what are our coding standards', 'what conventions do we follow', 'what's…
Score 70/100
Store important decisions, patterns, errors, lessons, and context into Cortex persistent memory. Use when the user says 'remember this', 'save this', 'store this for later', 'note…
Score 70/100
Clean Architecture and Cosmic Python guidance for well-tested, layered Python systems. Use for designing Python projects with layered architecture (models, adapters, services,…
Score 70/100
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
Score 70/100
Infrastructure and development cost estimation for technical projects. Use when planning budgets, evaluating build vs buy decisions, or projecting TCO for architecture choices.
Score 70/100
Reduces LLM costs and improves response times through caching, model selection, batching, and prompt optimization.
Score 70/100
Get a help or a second opinion from other agents. Bundle a prompt and a curated file set, then ask other LLMs for advice (debug, refactor, design, ...).
Score 70/100
Use for systematic debugging and root cause analysis with both Codex and Gemini. Triggers on "council debug", "council root cause", "have council investigate this bug", "council…
Score 70/100
Execute a Carmack Council plan task by task. Use when explicitly asked to implement a plan, do a "council implement", "carmack implement", "council build", or invoke…
Score 70/100
Spawn 5 Opus subagents with randomly-generated distinct personas to debate a problem from multiple angles.
Score 70/100
Route code reviews to appropriate council members. Use when reviewing PRs, architecture decisions, or significant code changes that need expert perspective.
Score 70/100
Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".
Score 70/100
Ensure test coverage percentage is displayed in README.md for Next.js and Python projects following industry standards
Score 70/100
Expert guidance on writing in Chamath Palihapitiya's communication style across 5 formats (Annual Letters, Customer Briefs, Emails, Policy Ideas Briefs, Learn with Me…
Score 70/100
When the user wants to design CPG (Consumer Packaged Goods) distribution networks, optimize DC locations for retail distribution, or plan omnichannel fulfillment networks.
Score 70/100
中文优先：用于C++codingstandards相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: C++ coding standards based on the C++ Core Guidelines (isocpp.github.io).
Score 70/100
C++20 coroutines skill for understanding coroutine mechanics and debugging. Use when working with co_await, co_yield, co_return, implementing promise_type, understanding coroutine…
Score 70/100
C++ development guidelines for modern C++17/20 projects. Use when creating C++ classes, functions, headers, or working with CMake, templates, smart pointers, RAII, memory…
Score 70/100
C++20 modules skill for modern C++ projects. Use when working with named modules, module partitions, header units, CMake MODULE_SOURCES, Clang -fmodules-ts, BMI caching issues, or…
Score 70/100
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.
Score 70/100
AUTOSAR C++14およびCERT C++コーディング規約に準拠したC++14コードレビュー。安全性重視のC++システムのコードレビュー、セキュリティ監査、品質評価、静的解析ツール設定を行う際に使用。
Score 70/100
Use when implementing Salesforce CPQ plugin interfaces in Apex or JavaScript (JS QCP) to customize quote calculation, product search, order creation, contracting, or configuration…
Score 70/100
CPQ solution architecture covering bundle design, pricing engine performance, multi-currency strategy, and integration patterns.
Score 70/100
Use when deploying Salesforce CPQ (Steelbrick/SBQQ) configuration between orgs — Product Rules, Price Rules, Price Actions, Price Conditions, Option Constraints, Quote Templates,…
Score 70/100
Use when deploying Salesforce CPQ configuration between environments in a CI/CD pipeline — covers the required data record dependency order (Price Books > Products > Price Rules >…
Score 70/100
Use when writing, reviewing, or debugging test classes for Salesforce CPQ (Steelbrick) functionality — including quote creation, price rules, contracting, ordering, and CPQ API…
Score 70/100
Expert on K1810VM86 (Intel 8086) CPU architecture for ES-1841. Provides guidance on registers, instruction decoding, memory segmentation, interrupts, bus cycles, and x86-16…
Score 70/100
Cpu Profiler Config - Auto-activating skill for Performance Testing. Triggers on: cpu profiler config, cpu profiler config Part of the Performance Testing skill category.
Score 70/100
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced…
Score 70/100
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced…
Score 70/100
CQRS (Command Query Responsibility Segregation) patterns with MediatR for .NET Clean Architecture projects. Covers commands, queries, handlers, validation, and pipeline behaviors.
Score 70/100
Command Query Separation (CQS) and CQRS patterns for .NET. Use when designing methods, handlers, and application architecture. Ensures predictable, testable code.
Score 70/100
Craft professional README.md files for GitHub open source projects. Generates hero sections, installation instructions, feature tables, and architecture diagrams.
Score 70/100
When the user wants to monitor, triage, or reduce their app's crash rate — including setting up Crashlytics, prioritizing which crashes to fix first, interpreting crash data, and…
Score 70/100
Crash log analysis, symbolication, and debugging workflows for iOS apps. Use when investigating app crashes, analyzing crash reports, symbolicating stack traces, or identifying…
Score 70/100
Parse and analyze macOS crash logs to identify crash causes and debugging information
Score 70/100
Run web crawling and scraping workflows with Crawl4AI, an open-source crawler built to produce LLM-ready markdown and structured extraction output.
Score 70/100
Crawl4AI is an open source crawler and scraper built for LLM-ready web extraction, with structured markdown output, browser support, and Python package distribution.
Score 70/100
Create a new ABP.IO project using CLI commands with proper template selection, configuration, and setup.
Score 70/100
Gerencia o ciclo de vida dos ADRs (Architecture Decision Records) no repositório. Executa arqueologia de software, análise de gaps, proposta de decisões e escrita de ADRs em…
Score 70/100
Create Architecture Decision Records (ADRs) documenting strategic technical decisions while acknowledging ecosystem E(t) constraints.
Score 70/100
Use Dagu to define file-backed workflow jobs in YAML, run them locally or across workers, and inspect failures through a lightweight operator surface instead of a heavyweight…
Score 70/100
Creates a new API module following Clean Architecture with TDD. Use when adding new API endpoints, creating backend features, implementing domain entities, or when the user says…
Score 70/100