发现 Skills

Build VoIP calling apps on iOS using the Telnyx WebRTC SDK. Covers authentication, making/receiving calls, CallKit integration, PushKit/APNS push notifications, call quality metrics, and AI Agent integration. Use when implementing real-time voice communication on iOS.

Transform approved plans into ralph loop infrastructure. Triggers on: '/ralph-loop-init', '/ralph-init', 'setup ralph loop', 'generate ralph loop'. Creates .ralph/ directory with prd.json, loop.py, CLAUDE.md, and supporting files.

Inspect Sentry issues, summarize production errors, and pull health data via the Sentry API (read-only). Use when a user says "check Sentry", "what errors in production?", "summarize Sentry issues", "recent crashes", or "production error report". Requires SENTRY_AUTH_TOKEN. Do NOT use for setting up the Sentry SDK, configuring alerts, or for non-Sentry error monitoring.

Complete Shopify development reference covering Liquid templating, OS 2.0 themes, GraphQL APIs, Hydrogen, Functions, and performance optimization (API v2026-01). Use when working with .liquid files, building Shopify themes or apps, writing GraphQL queries for Shopify, debugging Liquid errors, creating app extensions, migrating from Scripts to Functions, or building headless storefronts. Triggers on "Shopify", "Liquid template", "Hydrogen", "Storefront API", "theme development", "Shopify Functions", "Polaris". Do NOT use for non-Shopify e-commerce platforms.

Project and feature planning with 4 adaptive phases - Specify, Design, Tasks, Execute. Auto-sizes depth by complexity. Creates atomic tasks with verification criteria, atomic git commits, requirement traceability, and persistent memory across sessions. Stack-agnostic. Use when (1) Starting new projects (initialize vision, goals, roadmap), (2) Working with existing codebases (map stack, architecture, conventions), (3) Planning features (requirements, design, task breakdown), (4) Implementing with verification and atomic commits, (5) Quick ad-hoc tasks (bug fixes, config changes), (6) Tracking decisions/blockers/deferred ideas across sessions, (7) Pausing/resuming work. Triggers on "initialize project", "map codebase", "specify feature", "discuss feature", "design", "tasks", "implement", "validate", "verify work", "UAT", "quick fix", "quick task", "pause work", "resume work". Do NOT use for architecture decomposition analysis (use architecture skills) or technical design docs (use create-technical-design-doc).

Extract structured domain knowledge from AI models in-session or from local open-source models via Ollama. No API key needed.

Automated documentation maintenance and generation skill. Triggers when: (1) Code is added, changed, updated, or deleted in any skill, (2) New scripts or references are created, (3) SKILL.md files are modified, (4) User requests documentation updates, (5) Skills catalog needs regeneration, (6) README or AGENTS.md need updates reflecting code changes. Use for generating technical documentation, updating docs after code changes, producing changelogs, ensuring documentation stays synchronized with the codebase, and maintaining the skills catalog.

Automate Render tasks via Rube MCP (Composio): services, deployments, projects. Always search tools first for current schemas.

Use when user asks "where should I put this?" or wants to add new content. Automatically analyzes content type and recommends appropriate folder in chrome-extension-tcs (algorithms/client_cases/data_sources). Ensures proper organization by division and purpose.

Upload current Claude Code session to Google Drive and optionally share with team members. Automatically handles authentication on first use. Use when need to share conversation context, archive session work, or collaborate with colleagues.

Backend microservice development guidelines covering directory structure, layered architecture (API/Service/DAO), dependency injection, configuration management, and Spring Boot best practices. Intended for use when performing backend development, creating new microservices, writing Kotlin/Java code, or designing service architectures.

Generate comprehensive documentation for undocumented or poorly documented codebases. Use when a user asks to document code, add JSDoc/docstrings, create README files, generate architecture docs, explain what a codebase does, produce onboarding guides, or document internal APIs. Works with any language.

Offload tasks to local LLMs via LM Studio. Use when a user asks to run local models with LM Studio, save API costs by using local LLMs, create subagents with local models, offload summarization or classification to a local model, or use LM Studio's API for batch processing. Covers local model inference, task delegation, and cost optimization.

Run LLMs locally with Ollama. Use when a user asks to run AI models locally, self-host a language model, use LLaMA or Mistral on their machine, run offline AI, build a local chatbot, avoid sending data to cloud AI providers, generate text without API costs, fine-tune or customize local models, or set up a private AI inference server. Covers model management, API usage, Modelfile customization, GPU acceleration, and integration with LangChain and other frameworks.

PandasAI enables natural language queries on pandas DataFrames using LLMs. Learn to ask questions in plain English, generate charts, clean data, and integrate with OpenAI and local models for conversational data analysis.

Achieve PCI DSS compliance for handling payment card data — scoping, controls, and SAQ selection. Use when storing, processing, or transmitting payment card data, building e-commerce security, or achieving payment processing compliance.

Integrate with the QuickBooks Online API via OAuth2 to manage invoices, bills, expenses, customers, vendors, and pull financial reports. Use when: connecting SaaS apps to QuickBooks, automating financial data pipelines, syncing transactions, or building accounting integrations for small business clients.

Force LLMs to return typed, validated JSON — not free-text. Use when someone asks to "get structured data from LLM", "parse LLM response as JSON", "make AI return typed output", "validate LLM output", "extract structured data with AI", "use instructor with OpenAI", or "get reliable JSON from Claude/GPT". Covers OpenAI structured outputs, Anthropic tool_use for structured data, Instructor library, Zod schemas, Pydantic models, and retry strategies for malformed responses.

Core engineering standards for implementation. TRIGGERS - error handling, constants management, progress logging, code quality.

Systematically debug errors, bugs, and unexpected behavior in Home Assistant integrations. Use when investigating errors, analyzing stack traces, fixing bugs, or troubleshooting unexpected behavior.

Structured morning briefing skill — daily summaries covering calendar, tasks, weather, news, and priorities. Supports cron, heartbeat, and on-demand triggers.

Use when configuring Docker environments for act, selecting runner images, managing container resources, or troubleshooting Docker-related issues with local GitHub Actions testing.

Use when implementing SIP authentication, security mechanisms, and encryption. Use when securing SIP servers, clients, or proxies.

Use when working with Vue component patterns including props, emits, slots, and provide/inject. Use when building reusable Vue components.