全部能力

Create a persistent HeyGen avatar — a reusable face + voice identity for the agent, the user, or any named character — powered by HeyGen Avatar V technology. Prompt-based creation by default (description → HeyGen builds it); photo upload is optional for real-person digital twins. Use when: (1) giving the agent a face + voice so it can present videos ("bring yourself to life", "create your avatar", "give yourself an avatar", "design a presenter", "set up an avatar", "let's make an avatar"), (2) the user wants to appear in videos as themselves ("create my avatar", "I want my face in a video", "digital twin of me", "build me an avatar"), (3) building a named character presenter ("create an avatar called Cleo", "design a character named X"), (4) establishing HeyGen identity before making videos — the correct FIRST step when no avatar exists yet. Chain signal: when the user says both an identity/avatar action AND a video action in the same request ("create an avatar AND make a video", "set up identity THEN create a video", "design a presenter AND immediately record"), run heygen-avatar first, then heygen-video. Returns avatar_id + voice_id — pass directly to heygen-video to create HeyGen videos. NOT for: generating videos (use heygen-video), translating videos, or TTS-only tasks.

Build stateful Durable Objects for real-time apps, WebSocket servers, coordination, and persistent state. Prevents 20 documented errors. Use when: implementing chat rooms, multiplayer games, rate limiting, session management, WebSocket hibernation, or troubleshooting class export, migration, WebSocket state loss, boolean binding, RPC streams, or binding errors.

Grafana OSS core features — dashboards, panels, visualization types, data sources, template variables, alerting, annotations, provisioning, RBAC, service accounts, and configuration. Use when building dashboards, configuring data sources, setting up provisioning YAML, managing users and permissions, writing PromQL/LogQL/TraceQL in panels, or configuring Grafana server settings.

Cancel any active OMC mode (autopilot, ralph, ultrawork, ultraqa, swarm, ultrapilot, pipeline, team)

Use RepoPrompt CLI for token-efficient codebase exploration

Generate images, videos, and audio/music via Lovart AI. Also manages Lovart projects, threads (conversation history), and user settings. Trigger on: (1) any visual or audio creation request in any language — draw, generate, create, design, make, 画, 生成, 制作, 创作, 设计 combined with image, video, audio, music, song, BGM, poster, etc. (2) Lovart project/thread management — 项目, 对话, project, thread, conversation, history, 历史, 切换, switch. You CAN generate directly - never say you cannot.

Guidance on how to upgrade your Qdrant version without interrupting the availability of your application and ensuring data integrity.

Identifies missing tests for unique critical local logic: money, auth, permissions, data integrity, algorithms, and domain rules. Use when auditing critical…

Fast file editing via Morph Apply API (10,500 tokens/sec, 98% accuracy)

Generate engaging, localized App Store release notes (What's New) from git log, bullet points, or free text using canonical metadata under `./metadata`.…

使用阿里云模型服务灵积平台（Model Studio）的 Qwen VL 模型（qwen3-vl-plus/qwen3-vl-flash 及其最新别名）理解图像。适用于构建图像问答、视觉…

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text…

Rapid implementation for small, low-risk, well-defined changes. Use when the task is narrow in scope, has clear acceptance criteria, and can be completed…

Guides Qdrant deployment selection. Use when someone asks 'how to deploy Qdrant', 'Docker vs Cloud', 'local mode', 'embedded Qdrant', 'Qdrant EDGE', 'which…

Checks hardcoded secrets, SQL injection, XSS, insecure deps, input validation. Use when auditing security.

Fast codebase search via WarpGrep (20x faster than grep)

Analyze spreads, over/unders, prop bets. Historical trends, situational stats, value bet identification. For entertainment/education only.

When the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages…

Diagnose sentence-level issues after structure is solid. Use when prose feels flat, sentences are monotonous, word choices are generic, or voice is…

Implement robust batch processing systems with job queues, schedulers, background tasks, and distributed workers. Use when processing large datasets, scheduled tasks, async operations, or resource-intensive computations.