技能列表

Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.

Configurable quality evaluation for AI agent outputs. Define criteria, run evaluations, track quality over time. No LLM-as-judge, no API calls, pattern-based automated checks."

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging coze studio, typescript, agent, agent-platform.

Build and deploy local RAG (Retrieval-Augmented Generation) systems with offline document processing, embedding models, and vector storage.

Create images from text prompts. Use when you need to generate/draw/create images based on descriptions.

CoVerify by MO§ES™ — the falsification instrument for the Commitment Conservation Law. Extract kernels, score Jaccard, detect ghost tokens, run model swap tests. Proves meaning survived transformation — or names exactly what leaked.

Apply Robert C. Martin (Uncle Bob) principles for clean code, SOLID design, and clean architecture. Use when: (1) reviewing or refactoring code for quality, (2) designing modules, classes, or functions, (3) asked to "clean up" or improve code structure, (4) evaluating architectural boundaries, (5) naming things, (6) reducing coupling or increasing cohesion. Triggers on phrases like "clean code", "SOLID", "uncle bob", "clean architecture", "refactor for quality", "code smells", "single responsibi

|

Generate QR codes from text, URLs, or data. Use when: (1) user asks to create/generate/make a QR code, (2) converting a URL or text into a scannable QR code, (3) generating QR codes for payments (wechat, alipay, crypto), (4) creating QR codes for WiFi sharing, or (5) any task requiring a visual QR code image output.

Court Preparation Tool. Use when you need court prep capabilities. Triggers on: court prep.

Send emails via the gomail sender CLI with attachments, templates, and recipient management. Use when sending or testing email delivery from OpenClaw.

Apply counterfactual thinking to explore "what if" alternative histories and understand causation. Use when the user needs to analyze past decisions, understand what truly caused an outcome, learn from mistakes without hindsight bias, or evaluate whether different choices would have led to better results.