IDE & Editors

Role definition for code reviewer agents. Defines review criteria, feedback patterns, and approval workflows. Use to understand how to review PRs and provide constructive feedback.

This skill should be used when the user asks to "verify this works", "prove it's done", "show me evidence", or as Phase 5 of the /dev workflow before claiming completion. Requires fresh runtime evidence.

Research file storage conventions and templates for dokhak agents. Use when: (1) saving research results from research-collector or researcher agents, (2) reading cached research files, (3) checking if research exists for a section. Provides directory structure, file format templates, and naming conventions.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Standardized remediation workflow presenting three options for handling config violations - Conform to template, Update template, or Ignore. Adapts recommendations based on repository type (library vs consumer). Use when audit violations are found and user needs to decide how to address them.

CRITICAL development guide for Microsoft Agent Framework (MAF) in IPA Platform.MUST READ when working with:- Agents (ChatAgent, AgentThread)- Builders (ConcurrentBuilder, GroupChatBuilder, HandoffBuilder, MagenticBuilder)- Workflows (Executor, Edge, WorkflowExecutor)- Multi-agent orchestration- Any code in backend/src/integrations/agent_framework/builders/PREVENTS: Custom implementations instead of wrapping official API.REQUIRES: Import official classes, use Adapter pattern with self._builder = OfficialBuilder()

Download YouTube video transcripts with timestamps. Use when asked to transcribe a YouTube video, get transcript, or extract text from a video URL.

Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.

Creates and improves Claude Code skills using best practices. Use when user wants to build, modify, or enhance a skill. Guides through skill architecture, progressive disclosure, workflow design, and testing patterns.

Create, optimize, and debug high-performing prompts for Claude 4 models with production-ready templates and evidence-based techniques. Use this skill when the user asks to create a prompt, write a prompt, improve a prompt, build a prompt chain, design a system prompt, or needs prompt engineering guidance. Also handles prompt refinement and follow-up modifications.

Rapid MVP validation and launch framework following Y Combinator and lean startup principles. Use when user wants to validate a business idea, launch an MVP, define product strategy, calculate unit economics, or needs structured approach to test product-market fit. Includes monetization models, metrics frameworks, and execution templates.

Comprehensive Next.js project setup from scratch following industry best practices. Use when creating new Next.js projects, requiring template selection, design system ideation, specifications, wireframes, implementation with TDD, QA validation, and complete documentation. Handles both simple quick-start and complex multi-phase projects with sub-agent orchestration.

Use when working on web development tasks involving NextJS, React, TypeScript, Tailwind CSS, testing, deployment, APIs, databases, authentication, cloud infrastructure, or any modern web development stack. Provides access to 22 specialized web development skills covering frontend, backend, DevOps, and best practices.

PHANTOM v6: Ultimate cognitive architecture for debugging, code review, generation, and self-analysis. Combines Abductive Fault Inversion, Spectral Execution Tracing (Ghost/Demon dual traces), Dialectical Assumption Collapse, Cognitive Immune System (CIS) with 16 antibodies, Intelligence Amplification Framework (IAF) with 7 enhancement methods, Cognitive Capability Activation (CCA), 7-Level Architecture (ARCH), and Mem0 as primary unlimited memory system. Features 58 capabilities, monitoring checkpoints, persona verification (Constructor/Destroyer/Defender/Judge), calibrated confidence, Responsive Generator Model (RGM), GRIMOIRE spell format, and cross-conversation persistence via Mem0. Activates for: debugging, code review, "why isn't this working", architecture design, high-stakes reasoning, ULTRATHINK sessions, or understanding code/cognitive behavior.

Guide for using the Line 6 HX Effects device library in MMD files. Use when the user mentions HX Effects, HX Effects processor, effects-only processor, or needs help with 4-snapshot control, sequential preset addressing (banks), 5-pin DIN MIDI, or amp integration workflows.

This skill should be used when the user asks to "review this code", "check the implementation", "verify spec compliance", or as Phase 6 of the /dev workflow. Combines spec compliance and code quality checks with confidence scoring.

Analyzes existing project structure and design system, then provides contextually relevant UI/UX design options with visual descriptions. Helps users choose layouts, color schemes, component patterns, and interactions that integrate seamlessly with their current codebase. Activates for any UI, design, frontend, or visual-related development questions.

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).

Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.

Guide for implementing Google Gemini API audio capabilities - analyze audio with transcription, summarization, and understanding (up to 9.5 hours), plus generate speech with controllable TTS. Use when processing audio files, creating transcripts, analyzing speech/music/sounds, or generating natural speech from text.