libformat - Markdown formatting utilities. toHtml converts markdown to sanitized HTML safe for web display. toTerminal converts markdown to ANSI terminal output with colors. createToHtml and createToTerminal are factories for dependency injection. Use for rendering markdown in web apps and CLI tools.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants.

Clean up old cached plugin versions to free disk space. Use when the user says "clean cache", "cleanup plugins", "prune old versions", "free disk space", "plugin cache", "clear old plugins", or asks about plugin cache size.

Use when writing or reviewing C# code in this repo that builds an interactive Deepgram Voice Agent over WebSocket. Covers `ClientFactory.CreateAgentWebSocketClient()`, `SettingsSchema`, event subscriptions, microphone audio streaming, injected user messages, and function-call-related message types. Use `deepgram-dotnet-text-to-speech` for one-way synthesis and STT skills for transcription-only flows.

Use when writing or reviewing C# code in this repo that calls Deepgram Speech-to-Text for prerecorded or live transcription. Covers `ClientFactory.CreateListenRESTClient()` with `TranscribeUrl` / `TranscribeFile`, and `ClientFactory.CreateListenWebSocketClient()` with `Connect`, `Subscribe`, and `Send`. Use `deepgram-dotnet-audio-intelligence` for summaries/sentiment/topics overlays, `deepgram-dotnet-conversational-stt` for Flux-specific work, and `deepgram-dotnet-voice-agent` for full-duplex assistants.

Read, parse, and summarize iCalendar (.ics) files from Google Calendar, Apple Calendar, and similar providers. Use when extracting upcoming events, filtering by date range, converting ICS events to JSON/text, or debugging calendar fields like DTSTART/DTEND/TZID/RRULE.

Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift frontend diagnostics, then produce a recommend-first source-level optimization plan. Use when a developer reports slow compilation, type-checking warnings, expensive clean-build compile phases, long CompileSwiftSources tasks, warn-long-function-bodies output, or wants to speed up Swift type checking.

OWASP Top 10 audit checklists for Web Applications (2021), APIs (2023), and Mobile (2024). Use when performing any security review, PR review, or codebase audit touching web, mobile, or API code.

Multi-perspective framing — a pure lens-formation tool. When the right framework is absent, places analytical lenses before the user, then for each selected lens declares the substrate it needs (an abstract persona/capability) with advisory binding hints and a channel need, and hands lens↔substrate pairs off — without executing, isolating, arranging, or synthesizing. A single lens returns directly; multiple lenses where at least one needs a specialized substrate become a substrate-correspondence handoff that nudges /conduct for the isolation + arrangement + reconciliation + synthesis apparatus, which the isolated substrate runs. frame never synthesizes a multi-perspective result in its own context and never realizes isolation — convergence is claimable only by a substrate that ran the lenses in genuine isolation. Factual lookup or verification routes to fact-finding delegation; contested design, value, interpretation, or scope judgment routes to lens-conditioned inquiry. Type: (FrameworkAbsent, AI, DESIGN, Inquiry) → FramedInquiry. Alias: Prothesis(πρόθεσις).

Infer context insufficiency before execution. Surfaces uncertainties through information-gain prioritized inquiry when AI infers areas of context insufficiency, producing informed execution. Type: (ContextInsufficient, AI, INQUIRE, Prospect) → InformedExecution. Alias: Aitesis(αἴτησις).

This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate definitions", "run pre-commit checks", "verify soundness", or wants to ensure epistemic protocol quality. Invoke explicitly with /verify for pre-commit validation.

⚠️ DEPRECATED: This SDK has been renamed to Call Automation. For new projects, use azure-communication-callautomation instead. This skill is for maintaining legacy code only.

Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants.

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command.

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

Evaluate open source package health before adoption. Use when the user says "should I use this package", "is lodash well-maintained", "endor score express", "package health", "compare lodash vs underscore", "evaluate this dependency", or wants activity, popularity, security, and quality scores. Do NOT use for checking known CVEs in a package (/endor-check) or scanning the whole repo (/endor-scan).

Remove Gemini logos, watermarks, or AI-generated image markers using OpenCV inpainting. Use this skill when the user asks to remove Gemini logo, AI watermark, or any logo/watermark from images.

DuckDuckGo를 사용한 웹 검색. 텍스트, 뉴스, 이미지 검색을 지원. 빌트인 WebSearch가 제한적이거나, 뉴스/이미지 검색, 지역/기간 필터가 필요할 때 사용. "검색해줘", "찾아줘", "search", "뉴스 검색", "이미지 검색" 등의 요청 시 활성화.

Remove Gemini logos, watermarks, or AI-generated image markers using OpenCV inpainting. Use this skill when the user asks to remove Gemini logo, AI watermark, or any logo/watermark from images.