Research

Use when working with DeepResearchAgent/AgentOrchestra - a hierarchical multi-agent system for complex task solving, deep research, and automation. Achieved 83.39% accuracy on GAIA benchmark. Includes planning agents, research agents, browser automation, and MCP tool integration.

Extract and persist learnings from the current session. This skill should be used when the user wants Claude to analyze the conversation and capture insights, patterns, preferences, or knowledge discovered during work. Triggers on requests like "learn from this session", "what did we learn", or "capture insights".

Provides specialized knowledge and content creation for Physical AI and Humanoid Robotics topics with focus on accuracy and peer-reviewed sources.

Database seeding toolkit for Supabase projects. Use when: (1) Creating seed data files, (2) Populating lookup/reference tables, (3) Generating test data, (4) Bulk loading data with COPY, (5) Running seed files against database, (6) Managing large seed files with DVC

Create epistemically honest Source of Truth documents that pass Clarity Gate verification. Use when consolidating research, documenting project state, creating verification baselines, or building authoritative references. Triggers on "create source of truth", "document verified state", "consolidate research", "create verification baseline", "build authoritative reference".

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

Verify claims against referenced sources. Checks if blog content accurately represents external resources, APIs, or documentation.Trigger phrases: "fact check", "verify", "check claims", "verify claims", "check sources", "verify sources"

Adapts AndesRC content for specific regional markets (Mexico, Spain, LATAM). Handles lexical adaptation, cultural references, and geographic narratives. CRITICAL for Mexican market due to term sensitivities.

Handles MMKV storage operations and data persistence patterns with encryption. Use when implementing data persistence, caching, or user preferences in Fitness Tracker App.

Multi-phase research orchestration for thorough codebase, documentation, and external knowledge investigation. Invoked by /ai-eng/research command. Use when conducting deep analysis, exploring codebases, investigating patterns, or synthesizing findings from multiple sources.

Comprehensive research and analysis of books with actionable insights, hidden gems, and personalized recommendations. Use when the user requests book research, book reports, book analysis, or says "Research Book" followed by a book title. Adapts to project context (professional, personal, academic, hobby).

Fetch and manage work items from issue trackers. Use this skill when:- User references an issue number (#42, PROJ-123)- User asks about requirements or acceptance criteria- User needs to understand current task scope

Quick reference cheatsheets for Kailash SDK patterns, nodes, workflows, and best practices. Use when asking about 'quick tips', 'cheat sheet', 'quick reference', 'common mistakes', 'node selection', 'workflow patterns library', 'cycle patterns', 'production patterns', 'performance optimization', 'monitoring', 'security config', 'multi-tenancy', 'distributed transactions', 'saga pattern', 'custom nodes', 'PythonCode data science', 'ollama integration', 'directoryreader patterns', or 'environment variables'.

Generate professional product mascot character reference sheets with a specific multi-panel layout. Use this skill when creating character design sheets, mascot documentation, brand mascot references, or character consistency guides with multiple views (isometric, front/back/left/right, emotion poses). Optimized for product mascots and brand characters using Gemini image generation with Libre Baskerville typography.

This skill should be used when refining hypotheses, checking testability, improving specificity, or designing verification strategies. Triggered by requests like "refine hypothesis", "validate hypothesis", "check if testable", or "improve this hypothesis". Used AFTER experiments to refine hypotheses based on results.

Maintain a structured web research registry: analyze provided URLs, summarize pages, tag them, and update docs/research/web-research registries and site READMEs. Use when the user shares web links or asks to build/expand the research registry, tags, or site/page listings.

Reference skill for Splatoon ability families, AP rungs, token constraints, and domain rules for mechinterp experiments

Multi-round web search with low-frequency query generation. Prioritize GitHub/StackOverflow for actionable code, extract AI Overview insights, and perform deep link analysis. Use proactively for complex problems requiring external knowledge or when stuck on implementation challenges.

Specialize the workspace for the current customer. Use when the user wants to migrate, customize, or update a devcontainer for a new customer. Handles cleaning up repository lists, updating customer references in devcontainer.json, README.md, and powershell scripts in the scripts folder.

Verify claims in tacosdedatos content before publication. Use this skill when reviewing drafts for factual accuracy, checking code examples work correctly, validating statistics and sources, or verifying quotes and attributions. Produces a structured fact-check report with verdicts for each claim. For deep verification requiring extended research, delegate to the fact-checker subagent instead.