Skill UI

AgentPhone is an API-first platform designed for developers building AI agents with advanced telephony capabilities. It allows agents to manage phone numbers, make/receive voice calls, and handle SMS messages. Developers can utilize hosted mode for simple AI interactions or webhook mode for custom, complex logic, making it ideal for building sophisticated customer support bots or virtual assistants.

Guides calling Feishu IM APIs to retrieve chat histories, thread replies, cross-chat searches, and media/file downloads while handling pagination, time filters, and permission constraints so agents can answer questions about past conversations.

Generates complete, runnable Python scripts utilizing the python-pptx library to automatically build polished PowerPoint presentations. This skill transforms a topic brief into a structured slide deck script, ensuring real content, logical flow, and a working save function, perfect for demos, reports, or educational materials.

This skill provides a comprehensive guide on securely integrating and calling Firebase Cloud Functions from Flutter applications. It covers the proper use of `httpsCallable` to invoke structured server-side logic, handling data serialization, implementing robust error handling (including permission denial and timeouts), configuring regional deployments, and utilizing the Firebase Emulator Suite for reliable local testing.

Diagnoses and explains fixes for Flutter runtime and layout errors such as RenderFlex overflow, unbounded constraints, scroll-controller conflicts, and inappropriate setState calls during build, helping developers resolve issues quickly.

This skill provides a comprehensive framework for measuring Go application performance. It guides users through writing robust benchmarks using `testing.B`, running tests with various flags (`-benchmem`, `-cpuprofile`), interpreting complex profiling data (pprof), statistically comparing results using tools like `benchstat`, and setting up CI regression detection. It is essential for deep performance analysis and making statistically sound optimization decisions.

This comprehensive guide covers Dependency Injection (DI) patterns specifically for Golang. It explains why DI is crucial for building testable, loosely coupled, and maintainable services. The skill compares manual constructor injection for small projects with advanced DI libraries (like google/wire, uber-go/dig) for complex architectures, focusing on best practices such as interface-based design and managing service lifecycles.

samber/oops provides a structured, context-rich replacement for standard Go error handling. It allows engineers to attach critical metadata—such as domain, user ID, stack traces, error codes, and request details—directly to the error object. This ensures that variable data travels with the error through the call stack, enabling advanced APM tools (like Sentry or Datadog) to group and diagnose issues accurately, treating errors as structured, actionable data.

Guides developers to wrap Feishu API calls into reusable lark-cli skills, covering API research, command templates, and best practices for authentication, permissions, and orchestration.

Build interconnected Excel financial models (income statement, balance sheet, cash flow, DCF, cap table, scenarios) driven by an assumptions sheet so each output updates automatically from provided inputs.

Subscribe to Google Drive file or folder change notifications via the gws CLI recipe, keeping active subscriptions listed and renewed so downstream systems can react to updates automatically.

This tool generates a comprehensive context map of a codebase before making any modifications. It guides developers to systematically analyze all relevant files, dependencies, existing tests, and common patterns. Use it to assess the full scope of a task, identify potential breaking changes, and ensure a robust and stable development cycle.