Research

Systematic approach to gathering book research including source evaluation, citation formatting, fact-checking, and research organization. Use when conducting research, evaluating sources, or managing citations.

Research-backed prompting techniques for improved AI response quality (+45-115% improvement). Use when optimizing prompts, enhancing agent instructions, or when maximum response quality is critical. Invoked by /ai-eng/optimize command. Includes expert persona, stakes language, step-by-step reasoning, challenge framing, and self-evaluation techniques.

Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.

Use this skill for early-stage project planning. It leverages the Gemini CLI to generate high-quality first drafts of Product Briefs, Research Documents, and full PRDs, guiding users from idea to validated requirements. Triggers include "create PRD", "product brief", or "validate requirements".

Document citations and RAG (Retrieval-Augmented Generation) patterns for Claude. Activate for source attribution, document grounding, citation extraction, and contextual retrieval.

Deep code review with web research to verify against latest ecosystem. Use when user says 'double check against latest', 'verify versions', 'check security', 'review against docs', or needs deep analysis beyond automatic quality hook.

Deep research on features before building with co-founder mindset. Use when user wants to research a feature idea, explore if something is worth building, or says 'research this feature', 'is this worth building', 'explore this idea', or wants product + market + tech analysis.

Use when multiple tools are available for a task and intelligent routing is needed. Activates when routing-detector hook suggests it, or when user asks "which tool should I use" or "what's the best plugin for this". Provides context-aware tool ranking based on file context, user preferences, and tool specialization.

Execute AI security CTF challenges across any competition platform with adaptable workflows for indirect prompt injection, jailbreaks, agent exploitation, and evidence collection with research-grounded techniques

WHEN: Machine Learning/Deep Learning code review, PyTorch/TensorFlow patterns, Model training optimization, MLOps checksWHAT: Model architecture review + Training patterns + Data pipeline checks + GPU optimization + Experiment trackingWHEN NOT: Data analysis only → python-data-reviewer, General Python → python-reviewer

Deep research specialist for finding GitHub repos, tools, AI models, APIs, and real data sources. Searches repositories, compares libraries, researches latest AI benchmarks, discovers APIs, locates datasets, and performs competitive analysis to accelerate development.

Expert on Shelby Protocol architecture, erasure coding, placement groups, read/write procedures, Clay Codes, chunking, storage providers, RPC servers, and decentralized storage system design on Aptos blockchain. Triggers on keywords Shelby Protocol, erasure coding, Clay Codes, placement groups, Shelby architecture, storage provider, blob storage, chunking, Shelby whitepaper.

Alex (Legis-AI) - Senior UK Legal Counsel with 20+ years experience in English & Welsh Law. Use for legal advice, contract drafting, compliance checks, GDPR, employment law, property disputes, or risk assessment. Auto-triggers penalty warnings and statute citations. Also responds to 'Alex' or /alex command.

This skill should be used when the user asks about "Unity lifecycle", "MonoBehaviour methods", "Awake vs Start", "Update vs FixedUpdate", "Unity serialization", "[SerializeField]", "GetComponent", "component references", "Unity prefabs", "prefab workflow", or needs guidance on fundamental Unity patterns and best practices.

Generate boilerplate code for new CasareRPA automation nodes. See templates/ for category-specific templates and references/ for the complete checklist. Use when: creating new nodes, adding node categories, implementing BaseNode patterns, @properties decorator, node registration, get_parameter usage.

Detect hints about unreleased AI research or capabilities from lab researcher communications. Use when analyzing tweets, posts, or interviews from people at major AI labs to identify signals about upcoming work.

Fetch and summarize web content for any research task - documentation, design inspiration, competitor analysis, tutorials, API docs. Use when you need to understand web pages, extract key information, research patterns, or gather context for development work.

Expert software product manager who works directly with stakeholders to understand their needs and create comprehensive product specifications. Use when users need help designing software, defining requirements, creating PRDs, writing user stories, or developing functional specifications. Guides product management aspects of software development, asks clarifying questions, uncovers unstated preferences and assumptions, determines happy paths and error handling, and creates documentation understandable to both stakeholders and engineers.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Comprehensive PostgreSQL-specific table design reference covering data types, indexing, constraints, performance patterns, and advanced features