发现 Skills

Make tests pass. Invoke after /write-tests produces failing tests.

Interview user in-depth to create a detailed spec with strict implementation details and tradeoff analysis

Read Codex logs for this repo and synthesize docs in docs/.

Search a codebase for a pattern and open the top matches.

Task orchestrator that receives work, decomposes it, and dispatches background agents or teams for parallel execution. Use when managing multiple tasks, coordinating agents, or optimizing work distribution. Triggers on: 'manage', 'orchestrate', 'dispatch', 'coordinate', 'delegate'.

Control and monitor your smart home with Home Assistant. Get device states, call services to control lights, switches, and climate devices, trigger events, and query history. Use this when the user asks about smart home topics such as Home Assistant, lights, switches, sensors, thermostats, automation, or general home control.

Audit web pages for WCAG 2.1 AA compliance and ADA accessibility concerns. Uses agent-browser for runtime inspection and source analysis for static checks. Reports findings by severity with WCAG criterion references.

Creates product requirements documents through collaborative workshopping. Guides users from product idea to a structured PRD with user stories, acceptance criteria, and business rationale. Use when someone wants to define requirements, write user stories, document a feature, or needs help structuring product thinking before development.

Autonomous iterative code review and quality auditing loop with externalized state, convergence detection, severity-weighted findings (P0/P1/P2), and fresh context per iteration

Automatic semantic code review triggered after file modifications. Hook-driven skill that logs file changes via PostToolUse and runs the automatic-code-reviewer agent on Stop. Not user-invocable — triggered automatically by lifecycle hooks.

Retrieve normalized, render-ready HTML from any URL using fetch or headless prerender. Use when users need to get rendered HTML from JavaScript-heavy pages, normalize relative URLs to absolute for downstream parsing, prepare HTML for metadata extraction pipelines, or choose between fast fetch and full browser rendering per URL.

Expert guidance for designing Azure solutions using Azure Architecture. Covers reference architectures, solution ideas, design patterns, technology choices, architecture styles, best practices, anti-patterns, example workloads, and migration guides. Use when selecting architecture patterns, choosing Azure services, or implementing production-ready solutions.

Expert knowledge for Azure Static Web Apps development including troubleshooting, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building, debugging, or optimizing Azure Static Web Apps applications. Not for Azure App Service (use azure-app-service), Azure Functions (use azure-functions), Azure Container Apps (use azure-container-apps), Azure Kubernetes Service (AKS) (use azure-kubernetes-service).

Azure AI Agents Persistent SDK for Java. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Triggers: "PersistentAgentsClient", "persistent agents java", "agent threads java", "agent runs java", "streaming agents java".

Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgentDefinition, running evaluations, managing connections/deployments/datasets/indexes, or using OpenAI-compatible clients. This is the high-level Foundry SDK - for low-level agent operations, use azure-ai-agents-python skill.

Build AI applications using the Azure AI Projects SDK for JavaScript (@azure/ai-projects). Use it when working with Foundry project clients, agents, connections, deployments, datasets, indexes, evaluations, or when obtaining OpenAI-compatible clients.

Azure AI Text Analytics SDK for sentiment analysis, entity recognition, key phrases, language detection, PII, and healthcare NLP. Use for natural language processing on text. Triggers: "text analytics", "sentiment analysis", "entity recognition", "key phrase", "PII detection", "TextAnalyticsClient".

Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with Azure AI, including voice assistants, voice-enabled chatbots, real-time speech-to-speech translation, voice-driven avatars, or any WebSocket-based audio streaming with AI models. Supports Server VAD (Voice Activity Detection), turn-based conversation, function calling, MCP tools, avatar integration, and transcription.

Azure Container Registry SDK for Python. Use for managing container images, artifacts, and repositories. Triggers: "azure-containerregistry", "ContainerRegistryClient", "container images", "docker registry", "ACR".

Azure Key Vault Keys SDK for Rust. Use for creating, managing, and using cryptographic keys. Triggers: "keyvault keys rust", "KeyClient rust", "create key rust", "encrypt rust", "sign rust".

Transform the agent into a Cloud Solution Architect following Azure Architecture Center best practices. Use this when designing cloud architectures, reviewing system designs, selecting architecture styles, applying cloud design patterns, making technology choices, or conducting Well‑Architected Framework reviews.

Guide for implementing continual learning in AI coding agents — hooks, memory files, reflection patterns, and session persistence. Use when setting up learning infrastructure for agents.

Generates AGENTS.md files for repository folders — coding agent context files with build commands, testing instructions, code style, project structure, and boundaries. Only generates where AGENTS.md is missing.

MUST be loaded when setting up, installing, migrating, reviewing, auditing, or checking CLAUDE.md files in projects. Covers installing the promode CLAUDE.md into new projects, migrating existing CLAUDE.md content to AGENT_ORIENTATION.md (progressive disclosure), and auditing projects for conformance. Invoke PROACTIVELY when user mentions CLAUDE.md, project setup, agent configuration, or code meta files.