mermaid-diagram
Generate well-structured Mermaid diagrams for visual documentation. Use when designing systems, documenting workflows, creating architecture diagrams, or any task requiring visual representation of processes, relationships, or structures. Triggers include requests like "create a diagram", "visualize this", "show the flow", "draw the architecture", or when explaining complex systems that benefit from visual aids.
ralph-orchestrator
Build structured prompts for Ralph loops with TDD guidance, progress tracking, verification steps, and escape hatches. Invoke when starting a Ralph-based development task, creating orchestrated iteration loops, or converting PRDs to executable Ralph prompts. Wraps the official ralph-loop plugin to maximize loop success rates through careful prompt engineering and persistent state management.
meeting-insights-analyzer
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
brainstorm
Conversational brainstorming that refines ideas through targeted questions, triggers codebase exploration, and prepares context for planning
discoveryuser-research
Plan and structure moderated or unmoderated user research sessions that target the given persona and objectives.
visualization
Knowledge about pyecharts chart creation, HTML report generation, and visualization best practices
spec-workflow-orchestrator
Orchestrate comprehensive planning phase from ideation to development-ready specifications using 4 specialized agents
mermaid-diagram
Generate Mermaid diagrams including flowcharts, sequence diagrams, and class diagrams. Use when creating visual diagrams in documentation.
executive-dashboard
Эксперт executive dashboards. Используй для KPI визуализации, business intelligence и reporting.
gokart
M3社が開発したPythonの機械学習パイプラインツールgokartに関する深い知識とベストプラクティスを提供する。Use when reviewing gokart task designs, implementing type-safe ML pipelines, writing gokart tests, or working with gokart and Pandera integration. Trigger when user mentions gokart, TaskOnKart, TaskInstanceParameter, Pandera DataFrames with gokart, or requests code review for ML pipeline tasks.
mermaid-diagrams
Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.
retrospective-workflow
Systematic post-story retrospective process with automated metrics gathering, structured feedback collection, and Agent Package Manager handoff generation
data-quality-monitoring
Techniques and tools for ensuring the accuracy, completeness, and reliability of data across the pipeline.
diagram
Create diagrams and visual explanations with iterative render-and-check workflow. Use when asked to create Venn diagrams, architecture diagrams, flow charts, data charts, or any conceptual visual. Renders SVG to PNG, self-critiques using CRAP principles, iterates until right. Composes with brand skills (e.g., itv-brand) for styling. (user)
ralph-runner
Run long-running autonomous AI agents using PRD-based task scoping.
visualization
Knowledge about pyecharts chart creation, HTML report generation, and visualization best practices
memory-summary-retrieve
Retrieve memory summaries by ID, project, or recency. Returns structured JSON with compression metrics. Use to access compressed historical context for LLM prompts.
multi-mind
Subagent-based collaborative analysis. Launch 4-6 specialist subagents in parallel to analyze a topic from different perspectives, then cross-pollinate and synthesize. Usage: /multi-mind <topic> [rounds=3]
marp-slide-quality
Analyze and improve Marp markdown presentations using SlideGauge. Use when working with Marp presentations, slide decks, or when user asks to check, analyze, improve, or validate slide quality.
phoenix-brand-reporting
Press On Ventures brand-consistent reporting. Use when designing charts, dashboards, exports, or LP-facing documents.
retrospective-process
This skill should be used when the user asks to 'run a retrospective', 'review this session', 'extract learnings', 'what did we learn', 'analyze our conversation', 'session review', or wants to reflect on work done during the conversation.
