flight505

Create uncontested market space using value innovation instead of competing head-to-head. Use when the user mentions "blue ocean", "red ocean", "strategy canvas", "ERRC framework", "value innovation", "non-customers", "buyer utility map", "eliminate-reduce-raise-create", or "uncontested market". Also trigger when comparing pricing strategies, exploring new market categories, finding underserved customer segments, or asking how to stop competing on price. Covers the Four Actions Framework, buyer utility map, and value-cost trade-offs. For tech adoption strategy, see crossing-the-chasm. For product positioning, see obviously-awesome.

Engineer word-of-mouth and virality using the STEPPS framework (Social Currency, Triggers, Emotion, Public, Practical Value, Stories). Use when the user mentions "go viral", "word of mouth", "shareable content", "social currency", "why people share", "viral loop", "referral program", or "organic growth". Also trigger when designing shareable features, crafting social media campaigns, or building products that spread through peer recommendation. Covers environmental triggers and high-arousal emotional content. For sticky messaging, see made-to-stick. For persuasion tactics, see influence-psychology.

Audit websites and landing pages for conversion issues and design evidence-based A/B tests. Use when the user mentions "landing page isnt converting", "conversion rate", "A/B test", "why visitors leave", "objection handling", "bounce rate", "split testing", or "conversion funnel". Also trigger when diagnosing why signups are low, designing experiment hypotheses, or auditing checkout flows for friction points. Covers funnel mapping, persuasion assets, and objection/counter-objection frameworks. For overall marketing strategy, see one-page-marketing. For usability issues, see ux-heuristics.

Navigate the technology adoption lifecycle from early adopters to mainstream market. Use when the user mentions "crossing the chasm", "beachhead segment", "whole product", "early adopters vs. mainstream", "tech go-to-market", "bowling pin strategy", "technology adoption lifecycle", or "pragmatist buyers". Also trigger when a startup has early traction but struggles to grow beyond initial users, or when planning go-to-market for technical products. Covers D-Day analogy, bowling-pin strategy, and positioning against incumbents. For product positioning, see obviously-awesome. For new market creation, see blue-ocean-strategy.

Design motivation systems using Autonomy, Mastery, and Purpose (AMP) for products and teams. Use when the user mentions "intrinsic motivation", "gamification isnt working", "team incentives", "autonomy", "mastery", "purpose-driven", "employee engagement", or "reward systems". Also trigger when designing onboarding progression systems, fixing broken gamification, or building team structures that sustain high performance. Covers why carrot-and-stick fails and how to build progress systems. For habit-forming product loops, see hooked-ux. For retention behavior design, see improve-retention.

Create irresistible offers using the Value Equation, bonus stacking, risk-reversing guarantees, and ethical scarcity. Use when the user mentions "pricing strategy", "irresistible offer", "bonuses and guarantees", "value-to-price ratio", "offer naming", "grand slam offer", "guarantee strategy", or "premium pricing justification". Also trigger when packaging products for higher perceived value, designing money-back guarantees, or structuring pricing tiers to maximize conversions. Covers the MAGIC naming formula and starving-crowd targeting. For product positioning, see obviously-awesome. For outbound sales, see predictable-revenue.

Apply the six principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", or "commitment and consistency". Also trigger when designing testimonial sections, crafting urgency messaging, or improving trust signals on landing pages. For deal negotiation tactics, see negotiation. For viral word-of-mouth, see contagious.

Discover what customers truly need by analyzing the "job" they hire your product to do. Use when the user mentions "customer discovery", "why customers churn", "what job does this solve", "competing against luck", "product-market fit", "switching behavior", "milkshake moment", or "functional vs emotional jobs". Also trigger when investigating why users choose competitors, designing features around real customer needs, or reframing product value propositions. Covers JTBD interviews, competition analysis, and jobs-oriented roadmaps. For product positioning, see obviously-awesome. For rapid validation, see design-sprint.

Complete Apple platform development toolkit — iOS, macOS, watchOS, Swift, SwiftUI, StoreKit, ASO, legal, security, testing, and growth. Install for any Apple-platform project.

USE THIS SKILL for any question about Claude API, Claude Code CLI, hooks, plugins, skills, subagents, MCP servers, SDKs, extended thinking, tool use, streaming, or deployment. This skill has complete local documentation — do not use web search, WebFetch, or claude-code-guide instead.

Drop-in DESIGN.md design-system files for 71 popular brands (Claude, Linear, Stripe, Vercel, Apple, Figma, Tesla…). Use when the user wants to match a brand's look and feel, asks to "apply a design system", says "make it look like <brand>", mentions DESIGN.md, or needs design tokens (colors, typography, components) extracted from a known site.

Create interactive HTML learning material that teaches a topic INTUITIVELY (not just informationally) — single-file, animation-rich explainers in the spirit of 3Blue1Brown, Distill.pub, Bartosz Ciechanowski, and Quantum Country. Use when the user wants to LEARN a topic deeply, asks to "teach me X", points at a paper/URL/PDF they want to understand, or wants a self-paced interactive explainer instead of slides. Builds the page, opens it, then tutors the user in conversation about it.

USE THIS SKILL for any question about Google Gemini API — models, function calling, structured output, Live API, embeddings, pricing, or SDKs. This skill has complete local documentation — do not use web search or WebFetch instead.

USE THIS SKILL for NVIDIA topics not covered by the local spark-docs-skill snapshot — community discussion on the NVIDIA developer forum, NVIDIA developer blog posts, and adjacent NVIDIA product docs (CUDA, NeMo, Jetson, Brev, Dynamo, and others listed in the docs.nvidia.com llms.txt catalog). This is a dispatcher skill that routes queries to WebSearch and WebFetch; it does NOT bundle bulk documentation.

USE THIS SKILL for any question about OpenRouter API, model routing, pricing, available AI models, API keys, or provider configuration. This skill has complete local documentation — do not use web search or WebFetch instead.

Strategy guide for Perplexity MCP tools (perplexity_search, perplexity_ask, perplexity_reason, perplexity_research). Helps pick the right tool, craft queries, and use recency/domain filters. Reference when planning complex searches, literature reviews, or multi-step research — not needed for simple one-shot queries.

Strategic advisor for evaluating software/AI product ideas and generating defensible startup strategies. Use this skill whenever the user wants to evaluate a product idea, brainstorm startup directions, assess defensibility against foundation model companies, choose between build-vs-buy for AI components, or needs a strategic positioning check for a development project. Trigger on phrases like "is this idea defensible", "what should I build", "will OpenAI/Anthropic eat this", "startup idea", "product strategy", "moat", "competitive positioning", "should I build X", "vertical AI opportunity", "business model for AI", or any discussion about whether a software product is worth building given the current AI landscape. Also trigger when the user is evaluating technical architecture decisions through a strategic lens — e.g. "should I use a fine-tuned model or API calls" where the answer has competitive implications.

Component specification toolkit for breaking software projects into discrete, buildable blocks. Create detailed specifications with interfaces, dependencies, test criteria, and effort estimates for Claude Code to build incrementally.

Document toolkit (.docx). Create/edit documents, tracked changes, comments, formatting preservation, text extraction, for professional document processing.

PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.

Presentation toolkit (.pptx). Create/edit slides, layouts, content, speaker notes, comments, for programmatic presentation creation and modification.

Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data, visualization, recalculate formulas, for spreadsheet processing and analysis.

Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that isn't a technical diagram or schematic. For flowcharts, architecture diagrams, and technical diagrams, use the project-diagrams skill instead.

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with project-diagrams and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.

Use this skill when the user writes/edits components, asks to "fix accessibility issues", "add ARIA labels", "improve accessibility", "check WCAG compliance", "remediate a11y violations", mentions "screen reader support", "keyboard navigation", or wants AI-powered accessibility fixes with one-click application. Automatically analyzes components for a11y issues and suggests context-aware fixes. Trigger on PostToolUse hook or explicit request.

Use this skill when the user asks to "setup CI/CD", "configure GitHub Actions", "deploy Storybook", "setup Chromatic", "add visual regression to CI", "create deployment pipeline", or wants to generate complete CI/CD workflows for Storybook deployment and testing.

Scaffold new components with stories, tests, and documentation following SOTA patterns and best practices

Use this skill when the user asks to "generate dark mode", "create dark theme", "add dark mode support", "convert to dark mode colors", "generate dark color palette", or wants to automatically generate dark mode variants for their components with intelligent color inversion and accessibility preservation.

Use this skill when the user uploads a design screenshot, shares a Figma export, provides a mockup image, or asks to "convert design to code", "build from mockup", "generate component from screenshot", "extract design to React", or wants to transform visual designs into production-ready components using Claude's vision capabilities.

Use this skill when the user describes a component in natural language, says "create a component with...", "I need a card that has...", "build a form with fields for...", "generate component from description", or provides detailed component requirements in plain English. Enables non-technical stakeholders to generate production-ready components through natural language descriptions.

Use this skill when the user asks to "analyze performance", "check bundle size", "optimize component", "analyze imports", "reduce bundle", "check for performance issues", or wants to identify and fix performance bottlenecks in their Storybook components with AI-powered suggestions.

Use this skill when the user asks about "Storybook with Tauri", "Storybook with Electron", "desktop app components", "Tauri IPC mocking", "Electron limitations", mentions "cross-platform development", "native APIs in Storybook", or wants to develop Storybook stories for Tauri or Electron applications. This skill provides platform-specific guidance and architectural patterns for multi-platform component development.

Generate and open the harness run dashboard. Reads .harness/*.json state files, builds a self-contained HTML file, and opens it in the browser. Use when the user asks to see the dashboard, check run status, or view experiment history. For live monitoring during a run, suggest /loop 30s /harness:dashboard.

Analyze the current project for autoresearch optimization opportunities. Scans the project, identifies candidates matching the keep/revert loop pattern (single mutable artifact, scalar metric, fixed time budget, repeatable execution), and presents ready-to-run suggestions with workflow.yaml snippets. Use when the user asks what they can optimize, what to autoresearch, or how to apply the optimization loop to their project.

Approve or reject a pending approval gate in a harness workflow. Used when a conductor run pauses at a type: approval phase.

Interactive workflow builder — helps create workflow.yaml files for the harness orchestrator. The ONE interactive entry point. Use when user wants to build a harness workflow, create a pipeline, or compose subsystems together.

Match a task description to the best default workflow, collect the required values interactively, write .harness/workflow.yaml with everything filled in, and hand off to /harness:run. Full path from description to ready-to-run — no manual file copying or placeholder editing.

Signal that an ultraplan phase's plan has been saved and the conductor can resume. Used after the user reviews and teleports a plan from Claude Code on the web.

Configure harness optimize-subsystem hardware targets — Apple Silicon (MLX), NVIDIA server (CUDA), or RunPod cloud GPU. One-time setup stored persistently. Use when user mentions hardware setup, SSH targets, GPU configuration, or says 'configure optimization targets'.

Generate publication-quality technical diagrams using Nano Banana Pro (gemini-3-pro-image) with AI-powered quality review. Smart iteration only regenerates when quality is below threshold. Supports style presets (technical, visual-abstract, minimal), aspect ratio, and resolution control (512-4K).

Generate and edit images using Nano Banana 2 (gemini-3.1-flash-image, fastest) or Nano Banana Pro. Supports aspect ratio and resolution control via Google GenAI SDK.

Create Nature-quality visual abstracts — scientific figures using visual metaphors, isometric depth, and physical analogies to convey complex technical systems. Use for README hero images, paper figures, blog graphics, or when the user wants diagrams that go beyond boxes and arrows. Triggers on: 'visual abstract', 'scientific figure', 'Nature-quality', 'publication graphic', 'infographic', 'visual metaphor', or requests for rich/expressive/artistic diagrams.

Generate videos using Veo 3.1 — text-to-video, image-to-video, frame interpolation, and video extension

Render text-based diagrams (Mermaid, PlantUML, GraphViz, D2, and 23 more) to PNG/SVG via Kroki.io. Use ONLY when the user explicitly asks for text-based diagram rendering or a specific diagram language.

Explains a programming or Claude Code concept using your project as context, adapted to your experience level. Use when encountering an unfamiliar term, wanting to understand an architecture pattern, learning how a Claude Code feature works, or when you'd say 'what does X mean' or 'how does Y work.'

Explains the reasoning behind the last non-trivial decision with alternatives considered and concepts worth knowing. Use when curious about a choice Claude made, when you want to understand a tradeoff, after any architecture or library decision, or when you'd describe something as 'that thing Claude just did.'

Suggests Claude Code features and workflows that would improve how you're working right now, with exact commands to use. Use when something feels inefficient, when doing repetitive manual work, when starting a new project, or when you want to discover features you didn't know existed.

Reviews the session and teaches proper programming terms for concepts described casually, with memory so it never re-teaches. Use when you want to learn the right words for what you just did, build programming vocabulary, or after a session where you described things informally.

Surfaces available coaching commands at session start. Use when starting any conversation — provides command awareness for Code Coach plugin.

Web-grounded SOTA discovery using Perplexity Sonar models via OpenRouter. Use when academic APIs return foundational papers but you need to know what's CURRENT — what has superseded older methods, what practitioners actually use today, and what was released in the last weeks/months.

AI frontier plugin — gives Claude and agents access to latest scientific research, SOTA discovery, and architecture evaluation. Use when needing SOTA methods, research consensus, implementation guidance, or evaluating whether a codebase uses optimal patterns and architectures.

Search arXiv for latest AI/ML preprints. Use when Claude needs bleeding-edge research not yet in peer-reviewed journals — newest methods, architectures, training techniques, benchmarks.

Search Hugging Face Papers for AI/ML research with AI-generated summaries, keywords, community upvotes, and trending papers. Use when Claude needs community-curated research, AI-generated paper summaries, or trending ML papers.

Search Semantic Scholar for papers with rich metadata — citation counts, AI-generated TLDRs, influence scores, citation graphs. Use for finding established research, tracing citation chains, understanding paper impact and field structure.

Context-preservation dispatcher — routes ALL work to subagents, keeping main context thin for conversation and coordination.

Applies TDD methodology to skill authoring — test before deploy. Use when creating new skills, editing existing skills, writing SKILL.md files, or verifying skills before deployment. Also use when authoring plugin skills, improving descriptions, structuring directories, or when the user says 'make a skill' or 'turn this into a skill'. If you're about to modify a SKILL.md without testing, this skill applies.

Guides branch integration with structured options: merge, PR, keep, or discard. Use when implementation is complete and tests pass, when a worktree task is done and needs cleanup, when the user says they're finished with a branch, or when it's time to merge, create a PR, or discard experimental work.

Creates isolated git worktrees for parallel development without branch switching. Use when starting feature work that needs isolation, before executing implementation plans in parallel, or when the user asks to work on a feature without affecting current changes. Also use when brainstorm produces a design ready for implementation, or when switching branches would disrupt in-progress work.

Run NotebookAI's full audit — phase tests, pytest suite, frontend build, ruff. Use when verifying repo health after a refactor or before release.

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Convert markdown PRDs into prd.json execution format for SDK Bridge autonomous agents. Use when a PRD document exists and needs to be converted to SDK Bridge's JSON format. Trigger on 'convert prd', 'convert to prd.json', 'turn this PRD into sdk-bridge format', 'create prd.json from this PRD'. Also used internally by /sdk-bridge:start at the conversion checkpoint. Do NOT trigger on general JSON conversion or plan execution requests.

Generate a Product Requirements Document (PRD) for SDK Bridge autonomous execution. Use when the user explicitly asks to create a PRD, write requirements, generate user stories for sdk-bridge, or scope a feature into a PRD. Also trigger on 'create prd', 'write prd for', 'spec out for sdk-bridge', 'generate requirements document'. Do NOT trigger on general planning, brainstorming, or task decomposition — those belong to other skills.

Save a mid-session recall checkpoint — captures what happened so far to episodic memory without ending the session. Use when the user says 'save recall', 'checkpoint', 'save memory', 'save session state', or before restarting/exiting a long session. Also use when the user worries about losing context in a long-running session.

Search session memory — episodic logs and semantic facts captured by the recall plugin. Use when the user asks about previous sessions, past decisions, what happened yesterday, what files were changed, or says /recall. Also use when the user asks 'what did we do', 'remind me', 'what was that thing', or references work from prior sessions.