全部能力

Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor

Run automated liquidity provision strategies on concentrated liquidity (CLMM) DEXs using Hummingbot API.

Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug…

Performance optimization guide for Capacitor apps covering bundle size, rendering, memory, native bridge, and profiling. Use this skill when users need to…

Investigate incidents, debug performance issues, analyze logs, and manage observability resources in Dynatrace using the dtctl CLI. Use this skill whenever the…

在需要评估或改进或优化现有 LLM 智能体的输出质量时使用——包括提升工具选择准确性、回答质量等……

Analyze MSBuild binary logs to diagnose build failures by replaying binlogs to searchable text logs. Only activate in MSBuild/.NET build context. USE FOR:…

使用阿里云模型服务灵积 Qwen TTS Realtime 模型进行实时语音合成。适用于需要低延迟交互式语音的场景，包括…

Guide for interpreting ResolveProjectReferences time in MSBuild performance summaries. Only activate in MSBuild/.NET build context. Activate when…

Database access patterns for performance. Separate read/write models, avoid N+1 queries, use AsNoTracking, apply row limits, and never do application-side…

Best practices for Capacitor app development including project structure, plugin usage, performance optimization, security, and deployment. Use this skill when…

Guide for using MSBuild Server to improve CLI build performance. Only activate in MSBuild/.NET build context. Activate when developers report slow incremental…

Amazon Agent 是一款高性能工具，旨在将海量电商数据集转化为结构化、可用的智能信息。当用户…时使用此技能。

Extracts key learnings from conversations, debugging sessions, and failed attempts. Use at session end or after solving complex problems to capture insights. Stores discoveries in memory (via amplihack.memory.discoveries), suggests PATTERNS.md updates, and recommends new agent creation. Ensures knowledge persists across sessions via Kuzu memory backend.

Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging…

Use when the user asks to design database schemas, plan data migrations, optimize queries, choose between SQL and NoSQL, or model data relationships.

Framework for automated search over task-specific model harnesses — the code around a fixed base model that decides what to store, retrieve, and show while the…

Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform…

Use when the user asks to write SQL queries, optimize database performance, generate migrations, explore database schemas, or work with ORMs like Prisma,…

Performance Profiler