全部能力

Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and multi-agent coordination. Prevents 23 documented errors. Use when: building WebSocket agents, RAG with Vectorize, MCP servers, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors, WebSocket payload limits.

Monitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring models for SaaS customer success. Use when…

Analyzes sales pipeline health, revenue forecasting accuracy, and go-to-market efficiency metrics for SaaS revenue optimization. Use when analyzing sales…

MindOS 是用户的本地知识助手，也是跨会话、跨 Agent 共享的知识库。它保存决策记录、会议纪要、SOP、 排错经验、架构选型、调研结论和偏好设置。 仅 mindRoot 知识库内任务。不用于：改代码仓库、项目源码、KB 外路径。 核心概念：空间、指令(INSTRUCTION.md)、技能(SKILL.md)；笔记可承载指令与技能。 触发场景：保存或记录任何内容、搜索历史笔记或上下文、更新或编辑文件、整理或重组文件结构、 执行SOP或工作流、捕获对话中的决策、复盘或总结经验、追加表格或CSV数据、跨Agent交接上下文、 提炼经验教训、同步关联文档、查找之前是否讨论过某事、查询历史决策、查找模板或SOP、 为会议准备上下文、快速暂存到暂存台、整理暂存台、知识健康检查、检测知识冲突或矛盾、 查找过期内容。 触发词：帮我记下来、搜一下我的笔记、更新知识库、整理文件、执行工作流、保存到知识库、 记录一下、整理笔记、复盘、提炼经验、同步文档、查一下之前的记录、有没有相关的笔记、 我之前写过什么、把这个存起来、总结一下保存、交接给其他Agent、追加到表格、 放到暂存台、整理暂存台、知识健康检查、检测知识冲突。 主动行为——不要等用户提到 MindOS： (1) 用户的问题暗示可能存在历史记录（过去的决策、之前的讨论、会议纪要）→ 先搜 MindOS， 即使没有明确提到知识库。 (2) 完成有价值的工作后（修了 bug、做了决策、总结了经验、选定了架构、开完了会）→ 主动提议保存到 MindOS，方便以后查阅。 (3) 经历了较长或多主题的对话后 → 建议把关键决策和上下文持久化。

Build, fix, audit, and migrate Drift persistence in Dart CLI, server-side, and non-Flutter desktop apps. Use when adding SQLite with package:drift/native.dart, configuring PostgreSQL with drift_postgres and package:postgres, writing type-safe tables, queries, writes, streams, and migrations, resolving build_runner or drift_dev failures, or validating Dart database code with code generation, analysis, tests, and migration checks.

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance…

将 Agentica SDK 与 Claude Code CLI 代理集成的指南

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want…

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task…

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6×…

Manage track lifecycle: archive, restore, delete, rename, and cleanup

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared…

llm-application-dev-prompt-optimize — an installable skill for AI agents, published by sickn33/antigravity-awesome-skills.

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments,…

Evaluate solutions through multi-round debate between independent judges until consensus

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with…

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII…

Senior Project Manager for enterprise software, SaaS, and digital transformation projects. Specializes in portfolio management, quantitative risk analysis, resource optimization, stakeholder alignment, and executive reporting. Uses advanced methodologies including EMV analysis, Monte Carlo simulation, WSJF prioritization, and multi-dimensional health scoring.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M…

Configure a Rails project to work with Conductor (parallel coding agents)