全部能力

Comprehensive pentesting toolkit using Kali Linux Docker container. Provides direct access to 200+ security tools without MCP overhead. Use when conducting…

Implements React Server Components (RSC) patterns with Next.js App Router including data fetching, streaming, selective hydration, and server/client…

Ensure investment firms satisfy CFA Institute GIPS requirements for composite construction, performance calculation, presentation, and verification. Use when…

Creates comprehensive disaster recovery procedures with automated backup scripts, restore procedures, validation checks, and role assignments. Use for…

Core ML, Create ML, Vision framework, Natural Language framework, on-device ML integration. Use when user wants image classification, text analysis, object…

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when the user has a plan or design doc and is about to start coding — to catch architecture issues before implementation. (gstack) Voice triggers (speech-to-text aliases): "tech review", "technical review", "plan engineering review".

Executes optimization hypotheses with keep/discard testing loop. Use when applying validated performance improvements.

Comprehensive Drupal patterns from "Drupal at Your Fingertips" by Selwyn Polit. Covers 50+ topics including services, hooks, forms, entities, caching, testing,…

Expert in building blazing-fast reactive dashboards with comprehensive testing. Masters React performance patterns, testing strategies for async components,…

Expert-level performance optimization, profiling, benchmarking, and tuning

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers…

Vite build tool patterns including config, plugins, HMR, env variables, proxy setup, SSR, library mode, dependency pre-bundling, and build optimization.…

Profile and optimize application performance including load times, memory usage, and rendering. Use when debugging slow performance, memory leaks, or…

Analyze production Agentforce agent behavior using session traces and Data Cloud. TRIGGER when: user queries STDM session data or Data Cloud trace records;…

Implements background job processing with BullMQ/Redis including job queues, workers, scheduling, retries, and monitoring. Use when users request "background…

Install, initialize, verify, and troubleshoot RTK (Rust Token Killer) for AI coding agents. Use when you need to reduce shell-command token output, confirm that the correct `rtk` binary is installed, choose between Homebrew, install.sh, or Cargo installation, wire `rtk init` for Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, or OpenCode, or use compact wrappers such as `rtk git status`, `rtk read`, `rtk grep`, `rtk test`, `rtk lint`, and `rtk gain`. Triggers on: rtk, rust token killer, token saver cli, rtk init, rtk gain, codex rtk, gemini rtk, opencode rtk, claude hook token reduction.

Design AWS architectures for startups using serverless patterns and IaC templates. Use when asked to design serverless architecture, create CloudFormation templates, optimize AWS costs, set up CI/CD pipelines, or migrate to AWS. Covers Lambda, API Gateway, DynamoDB, ECS, Aurora, and cost optimization.

Eva-skill v1.4 创作者思考陪练与表达工具箱。围绕想法、人群、标题、内容创作和表达资产，提供思考助理、表象问题归位、话题人群识别、对标文案拆解、点子卡沉淀与回溯、人设记忆采集、表达真实性审查、短视频创作主入口、标题即选题和思维流爆款内容创作。人设记忆采集是多轮表达资格采集，不是账号定位或人设包装。抖音/无标题五步模型是 /eva-script 的分支参考，不作为独立主入口。思想镜片、MBTI 和创作者思想工具不再作为独立入口，只作为 think 的轻量思考姿势；互动语气作为全局表达协议。 触发方式：/eva、/思维流、/eva-think、/eva-reframe、/eva-audience-finder、/eva-benchmark-copy、/eva-memory、/eva-persona-memory、/eva-ai-check、/eva-shortvideo、/eva-title、/eva-script、「帮我想想」「脑子乱」「问题归位」「这个话题戳中了谁」「这个选题讲给谁」「对标拆解」「AI味检测」「人设梳理」「沉淀一下」「回捞点子卡」「帮我做一条口播」「帮我写视频稿」

Optimize Amazon backend search terms for maximum discoverability. Generate the optimal 250-byte backend keyword set by deduplicating, prioritizing, and…

Prepare advisors for client review meetings by assembling context packages, performance summaries, drift analysis, talking points, and meeting agendas. Use…