Research

Perform comprehensive exploratory data analysis on research data. Automatically analyze data structure, quality, distributions, and generate insights. Use when the user provides a dataset, asks to "explore data", "analyze this file", or needs to understand their data before formal analysis.

Comprehensive guide to Learning Path patterns for the Plataforma B2B de treinamento técnico corporativo educational platform. This skill covers the conceptual difference between Study Areas (courses) and Proposed Paths (sequences of courses), data modeling, UI/UX patterns, and implementation guidelines. Learn how to structure Learning Paths correctly: a Proposed Path is NOT a container of loose flashcards, but a curated sequence of Study Areas (courses). Each path references existing courses with metadata like order, availability status, and estimated hours. Real-world examples are taken from the Hub MVP implementation (US-044), including caminhoExemploData.js, HubView.jsx, and LearningPathView.jsx. The skill demonstrates the reference pattern used for "Desenvolvedor Backend" path that sequences Bash, Linux, Docker, and DevOps courses. Key topics include data schema design (cursos array with ordem, areaId, disponivel flags), computed properties (getters for statistics), navigation patterns (path -> course -> lesson), availability states (disponivel: true/false with badges), and how to add new paths without duplicating course data. This skill is essential for implementing new Learning Paths, maintaining the Hub MVP pattern, scaling to multiple paths, and ensuring UI/UX consistency across the educational platform. Includes the correct mental model for Course vs Path separation.

Fine-tuning Text-to-Speech (TTS) models with Unsloth for voice cloning and synthetic speech (triggers: TTS, text-to-speech, voice cloning, Orpheus-TTS, audio fine-tuning, speech synthesis).

Generate tight, one-page PRDs for CustomGPT.ai Labs projects aligned to Why/How/What, success metrics, and fast experimentation constraints.

WasteWise Complete Analysis with automated regulatory compliance research and LLM Judge validation. Includes all standard analysis features PLUS automated ordinance research, compliance checklists, and quality-scored evaluation. Use when you need both waste analysis AND regulatory compliance documentation.

Designs and documents control testing procedures. Creates test plans, executes walkthroughs, and documents results for audit workpapers.

Create patent-style technical diagrams including flowcharts, block diagrams, and system architectures using Graphviz with reference numbering

Generate and edit images using the Gemini API (Nano Banana). Use this skill when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

Research-driven PyIceberg development. Injects research steps for Iceberg table operations, ACID transactions, catalog integration, and schema evolution. Use when working with Iceberg table storage, time-travel queries, or data lake operations.

Generate song lyrics with citations from pinned sources. Enforces rhyme scheme, meter, syllable counts, hook strategy, and profanity filter while retrieving from MCP sources with deterministic hash-based pinning. Use when creating lyrics with structural constraints, source attribution, and policy compliance.

Search Practice Hub documentation for architecture, API reference, database schema, integrations, and implementation patterns. Triggers when user asks about multi-tenancy, authentication, tRPC routers, database, Better Auth, pricing calculator, Client Hub, Proposal Hub, Admin Panel, Client Portal, design system, integrations (LEM Verify, Gemini AI, DocuSeal, S3), or implementation patterns.

Context preservation with semantic memory: six-tier importance system (constitutional/critical/important/normal/temporary/deprecated), hybrid search (FTS5 + vector), 90-day half-life decay for recency boosting, checkpoint save/restore for context safety, constitutional memories (always surfaced), confidence-based promotion (90% threshold), session validation logging, context type filtering (research/implementation/decision/discovery/general), auto-indexing (memory_save/memory_index_scan). Manual trigger via keywords or /memory:save command.

PostgreSQL query optimization and performance tuning reference. Use when analyzing slow queries, interpreting EXPLAIN output, optimizing indexes, or troubleshooting database performance issues.

Create and manage Google Slides presentations. Load when user mentions 'google slides', 'slides', 'presentation', 'create presentation', 'add slide', or references creating/editing slide decks.

Daily journaling for mood, energy, and experiential tracking

Agent Skill: Systematic TYPO3 extension upgrades to newer LTS versions. Covers Extension Scanner, Rector, Fractor, PHPStan, and testing. Use when upgrading extensions to newer TYPO3 versions or fixing compatibility issues. By Netresearch.

Complete Figma design extraction for pixel-perfect implementation. Extracts design tokens, component specs, layouts, and responsive behavior systematically. Use when user provides Figma design: - Figma URL or file link provided - User mentions "Figma", "design file", "mockup", or "design system" - During /create-plan phase when design needs extraction - User says "extract from Figma" or references Figma link Extract systematically: - Design tokens: ALL colors (hex + usage), typography (sizes, weights, line heights), spacing scale, border radius, shadows, opacity values - Components: ALL states (default, hover, active, focus, disabled, loading, error), ALL variants (size/style/intent), exact dimensions, spacing, visual properties - Layouts: page structure, grid systems (columns, gutters), component hierarchy - Responsive: mobile/tablet/desktop differences explicitly documented - Assets: icons (names, sizes), images (dimensions, alt text), illustrations Goal: Extract ONCE completely during planning phase. Implementation should never need to re-fetch from Figma MCP. Focus on exact values only - no approximations, no guessing. Completeness prevents re-work and design inconsistencies. Critical for /create-plan workflow. Validates MCP connection before extraction. Documents everything in structured format for /execute-plan to implement accurately. Do NOT load for: Building UI without design (use theme-factory), implementing from already-extracted specs, responsive layout questions, or backend work.

Use when merging parallel worktrees back together after parallel implementation. Orchestrates systematic 3-way diff analysis, dependency-ordered merging, and intelligent synthesis of parallel work streams.

Review educational content against the Four Learning Design Pillars framework. Use when users want to evaluate course materials, lessons, tutorials, e-learning modules, or any instructional content for alignment with evidence-based learning design principles. Provides structured feedback with specific principle references (e.g., 1.1.1, 2.3.4) and actionable recommendations.

Enforces project documentation structure in docs/plans/ directories - research.md for facts, design.md for decisions, tasks.md for implementation, thoughts/ for explorations.