Research-driven design system creation. Understands your product, researches the competitive landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion) with explicit SAFE vs RISK breakdown, and generates HTML preview pages. Produces DESIGN.md as the project's design source of truth. Use this skill whenever the user wants to create a design system, brand identity, visual direction, or says things like 'design system', 'what should this look like', 'brand guidelines', 'create DESIGN.md', 'visual direction', 'help me design this', 'what fonts should I use', 'color palette for', 'how should the UI look'. Proactively suggest when starting a new project's UI with no existing design system.
Systematic debugging with root cause investigation. Enforces the Iron Law: no fixes without root cause. Four phases: investigate (gather symptoms, trace code, check history), pattern-match (race condition, nil propagation, state corruption, stale cache, config drift, integration failure), hypothesize and test (confirm before fixing, 3-strike escalation), implement (minimal fix + regression test). Use this skill whenever the user reports a bug, error, unexpected behavior, or says things like 'debug this', 'fix this', 'why is this broken', 'investigate this error', 'root cause analysis', 'this stopped working', 'getting an error', 'something is wrong'. Proactively suggest when the user is troubleshooting or applying fixes without investigating first.
Deep, autonomous domain decomposition and landscape research for any idea or problem statement. Takes a raw idea (from one sentence to a paragraph) and runs a 6-phase research process: decomposes the idea into problem space, target users, domain, adjacent domains, and assumed solution direction; performs exhaustive parallel web research on current state of the art, key players, recent momentum, technical foundations, and user sentiment; synthesizes gaps, blind spots, friction points, challenges, and opportunities; maps 3-5 distinct solution directions with feasibility and differentiation analysis; runs contrarian and timing checks including cross-domain analogies; and scores all findings by confidence level with full source attribution. Outputs a structured research dossier to /docs/idea-scout/. Use this skill whenever the user has a raw idea they want explored before building, wants to understand a problem landscape, needs domain research, or wants to validate whether an idea is worth pursuing. Triggers on:
Generates a comprehensive Product Requirements Document from a research dossier or raw idea. Takes structured research (from idea-scout) or a direct problem statement and produces a full PRD with vision, user journeys, functional and non-functional requirements, architecture sketch, risk matrix, prioritized roadmap, and validation plan. If no idea-scout research dossier exists, automatically triggers idea-scout first. Integrates with idea-forge for adversarial validation of the solution direction before finalizing. Outputs a structured PRD to /docs/prd/. Use this skill whenever the user wants to create a PRD, product spec, requirements document, or formalize an idea into a buildable plan. Triggers on: 'create a PRD', 'write a PRD', 'generate PRD', 'product requirements', 'prd-generator', 'turn this into a spec', 'write the requirements', 'make this into a plan', 'formalize this idea', 'I want to build this — what do I need?', 'create a product spec', 'write requirements for', 'spec this out', 'product specifi
Exhaustive API, database, dataset, and documentation discovery for any domain. Takes a domain (e.g. 'health app', 'climate monitoring', 'fintech platform') and runs a multi-phase research process: expands the domain into fine-grained subcategories, spawns parallel research agents per subcategory to find public APIs, commercial APIs, open datasets, government databases, research repositories, SDKs, and relevant documentation (specs, guides, tutorials, whitepapers). Outputs a single structured markdown catalog with doc links per source. Use this skill whenever the user wants to find APIs for a project, discover datasets for a domain, research available data sources, find documentation, scout integrations, map the API landscape, or asks 'what APIs exist for X'. Triggers on: 'find APIs for', 'what databases exist for', 'data sources for', 'API landscape', 'discover APIs', 'scout APIs', 'dataset discovery', 'what data is available for', 'find integrations for', 'API research', 'data catalog', 'find docs for', 'doc
Multi-agent swarm simulation with REAL independent subagents for scenario prediction. Each population runs as a separate agent process that cannot see other populations' decisions — producing genuinely emergent behavior. Spawns 40-100 AI agents across 3-5 populations, researches via web search, runs 5 rounds with parallel execution, and delivers an interactive HTML dashboard. Use this skill when the user wants to predict outcomes, simulate scenarios, test strategies, forecast reactions, model market dynamics, or run what-if analyses. Triggers on: '/simulate', 'simulate', 'swarm simulation', 'what would happen if', 'predict the outcome', 'run a scenario', 'agent simulation', 'market simulation', 'how would people react'.
Interactive UI design consultant that guides you through a 6-phase design process (Discovery, Design System, Architecture, Section Spec, Assembly, Review) and outputs production-ready pixel-spec prompts. Supports image reference analysis. Use when designing UI pages, sections, or components for AI code generators.