solana-new

Guide a Solana project from devnet to mainnet production deployment. Use when a user says "deploy to mainnet", "go to production", "deployment checklist", "prepare for launch", "mainnet deployment", or "ship it". Reads build-context.md from a prior build phase if available.

Integrate Proof of Human (POH) API to distinguish real users from bots in any Solana app. Use when a user says "filter bots", "verify humans", "sybil protection", "airdrop eligibility", "bot detection", "proof of human", "POH", "verify wallet is human", "gate my airdrop", "DAO sybil resistance", "check if wallet is real", "human verification", or "anti-bot". Works for airdrops, DAO voting, NFT allowlists, and API gating.

Map the competitive landscape for a crypto product idea. Use when a user says "who are my competitors", "map the competitive landscape", "what exists in this space", "show me similar projects", or "competitive analysis". Leverages solana-new's catalogs of 106 repos, 78 skills, and 36 MCPs.

Guide a developer through building a DeFi protocol on Solana. Use when a user says "build a DEX", "AMM", "lending protocol", "vault", "yield", "liquidity pool", "DeFi protocol", "swap program", "build a DeFi app", "perpetual futures", "perps protocol", "leverage trading", or "derivatives". Reads build-context.md from a prior scaffold phase if available.

Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Use when a user says "security audit", "threat model", "pentest review", "OWASP", "CSO review", "check for vulnerabilities", or "is my code secure".

Design direction, judgment calls, and anti-AI-slop review for crypto UIs. Use when the user says "this looks generic", "this looks AI-generated", "anti-slop", "design judgment", "premium feel", "design direction", "what direction should this take", "make this feel more premium", "review for taste", "theme reference", "warm monochrome", "stark minimal", "gradient trust", "workstation dense", "soft consumer", "gallery editorial", "density", "page archetype", "design brief", "pitch deck style", "deck visual direction". Also use when building any new page-level component that needs aesthetic direction before implementation. Does NOT claim "make this look good" or "polish this" — those belong to frontend-design-guidelines.

Apply high-quality web interface design rules when building, reviewing, or styling frontend code. Use when the user says "build a frontend", "create a component", "style this", "review my UI", "build a landing page", "design this page", "make this look good", "add animation", "build a form", "improve the UI", "polish this", "make this feel right", "review for craft", "the interaction feels off", "make this look polished", or when generating any React/Next.js component. Defaults to Tailwind CSS and shadcn/ui. Reads brand.md at the project root (if present) and uses it as the source of truth for colors, typography, and voice. Covers interactions, layout, typography, forms, animation, states, accessibility, and a dedicated craft-and-polish layer for taste-level review. Use proactively whenever frontend code is being written — do not wait to be asked.

Apply consistent number formatting across crypto/Solana UIs. Use when the user says "format numbers", "number display", "token amounts", "price formatting", "zero subscript", "abbreviate numbers", "format currency", "format percent", "how should I display this number", "number formatting spec", or when generating any UI component that displays prices, balances, percentages, ratios, or token amounts. Use proactively whenever writing frontend code that renders numeric values — do not wait to be asked.

Fix janky page loads where everything appears at once. Production framer-motion recipes for choreographed page entrances, staggered lists, modal transitions, filter cross-fades, live data animations, and micro-interactions. Use when building or reviewing any page that loads content, when animations feel broken or janky, when framer-motion code needs production patterns, or when the user says "page load animation", "entrance choreography", "stagger animation", "framer-motion recipe", "page feels janky", "everything appears at once", "spring animation", "modal animation", "dropdown animation", "rolling numbers", "chart morph", "donut reveal", "filter transition", "tab animation", "micro-interaction", "hover animation", "button feedback", "AnimatePresence", or "framer-motion pattern". Use proactively whenever writing page-level components or reviewing animation code.

Create a structured pitch deck for a crypto project. Use when a user says "create a pitch deck", "help me pitch", "I need slides", "prepare for demo day", "investor presentation", or "grant application". Reads idea-context.md and build-context.md from prior phases if available.

Create marketing videos for Solana projects using Remotion (code-driven) and Renoise (AI-generated). Use when a user says "marketing video", "product video", "promo video", "deck review", "video pitch", "create a video", or "Remotion project".

Frame-level visual composition and product demo presentation for Remotion videos. Use when the user says "video looks generic", "make video frames look better", "video frame design", "device frame", "product demo video craft", "video CTA", "end card", "video composition", "video craft", "screenshot in video", "frame quality", or when reviewing Remotion compositions for visual quality. Sits on top of marketing-video — adds the visual design layer for each frame. Does NOT claim "create a video" or "marketing video" — those route to marketing-video.

Generate, preview, and apply a brand color palette (plus typography, gradients, and tone/voice) to a frontend project. Use when a user says "pick brand colors", "choose a color palette", "brand design", "generate a palette", "theme this project", "what colors should I use", "brand identity", "design my brand", "set up brand colors", "time to build the frontend", "let's start the UI", "make this look branded", or any time a project is about to start frontend work and has no brand.md yet. Presents 6 candidate palettes as a visual HTML preview opened in the user's browser, supports an infinite regenerate loop until the user is satisfied, then writes the chosen palette to shadcn CSS variables (light + dark), wires up typography via next/font, derives brand gradients, and writes brand.md for future reference.

Prepare an Agentic Engineering Grant application by gathering project data, git history, and context files, then presenting all fields needed to fill the Solana Earn grant form. Use when the user says "apply for grant", "agentic engineering grant", "apply-grant", "grant application", "fill grant form", "200 USDG grant", "ST earn", "Superteam earn", "Superteam grant", "earn grant", "help me apply for grant", "solana earn grant", or "submit grant".

Interview users sharply to discover, rank, or validate what they should build in crypto. Use when a user asks what to build in crypto, wants startup ideas in a crypto niche such as DeFi or AI x crypto, wants blunt feedback on an existing crypto idea, or wants a concrete artifact comparing the best next ideas. Treat the bundled idea datasets as inspiration, not constraints, and always combine them with fresh market research.

Meta skill — browse all installed solana-new skills, repos, and MCPs to find the right tool for any task

Set up a complete Solana project workspace from a validated idea. Use when a user says "scaffold my project", "set up my workspace", "what stack should I use", "create the project structure", or "initialize my project". Reads idea-context.md from a prior idea phase if available. Leverages solana-new's catalogs of 106 repos, 77 skills, and 36 MCPs.

Run a structured validation sprint on a crypto startup idea. Use when a user says "validate this idea", "is this worth building", "run a validation sprint", "help me test demand", or "should I build this". Reads idea-context.md from a prior idea phase if available.

Guide a developer through building a Solana data pipeline or indexer. Use when a user says "build an indexer", "data pipeline", "analytics", "track transactions", "monitor wallets", "webhook", "index accounts", or "real-time data". Reads build-context.md from a prior scaffold phase if available.

Help a developer debug a failing Solana program or transaction. Use when a user says "debug my program", "program error", "transaction failed", "stuck", "help me fix", "why is this failing", "error code", or "instruction failed". Reads build-context.md if available.

Guide a developer through building their Solana MVP step by step using Claude Code. Use when a user says "help me build this", "start the MVP", "guide me through implementation", "what should I build first", or "walk me through the code". Reads build-context.md from a prior scaffold phase if available.

Deep technical Solana bootcamp — SVM architecture, Rust patterns, program development. Use when a user says "Solana incubator", "teach me Rust for Solana", "SVM deep dive", "Solana bootcamp", "learn Solana development", "deep dive Solana", "PDA tutorial", "CPI tutorial", or "Anchor tutorial". Structured curriculum that assesses level and assigns exercises.

Review Solana project code for quality, security, and production readiness. Use when a user says "review my code", "is this production ready", "audit my program", "what should I fix", "code review", or "check for security issues".

Guide a developer through launching a token on Solana. Use when a user says "launch a token", "create a token", "pump.fun", "bonding curve", "token launch", "create a memecoin", or "SPL token". Reads build-context.md from a prior scaffold phase if available.

Guide a developer through building a Solana mobile app. Use when a user says "build a mobile app", "React Native Solana", "Solana mobile", "mobile wallet", "mobile dApp", "Android Solana", or "iOS Solana". Reads build-context.md from a prior scaffold phase if available.

Prepare and optimize a hackathon submission for a Solana project. Use when a user says "submit to hackathon", "prepare my submission", "hackathon entry", "write project description", "demo video", or "help me win the hackathon". Reads all prior phase context if available.

Research DeFi protocols and market opportunities using DefiLlama data. Use when a user says "show me TVL data", "which protocols are growing", "DeFi market research", "what should I build in DeFi", "find DeFi opportunities", "analyze protocol TVL", or "which chains are trending". Uses TVL as a trust metric to suggest protocols worth building on or integrating with.

Teach Solana fundamentals to developers new to the ecosystem. Use when a user says "what is Solana", "why Solana", "new to Solana", "explain Solana to me", "Solana basics", "EVM to Solana", "getting started with Solana", or "Solana fundamentals". Adapts to user's background — EVM devs, backend devs, or complete beginners.

Search and analyze 5,400+ Solana hackathon projects using Colosseum Copilot. Find similar projects, discover winner patterns, identify gaps, and explore ML clusters. Use when a user says "colosseum copilot", "hackathon projects", "winner patterns", "gap analysis hackathon", "similar Solana projects", or "colosseum landscape". Requires a Colosseum Copilot token.

Product quality review — UX flows, onboarding, feature completeness, and user value. Use when a user says "product review", "review my product", "UX review", "is my product good", "product quality", "user experience review", "onboarding review", or "feature audit". Different from code review (review-and-iterate) and product roast (roast-my-product) — this is structured, balanced evaluation.

Harsh, honest product critique — find every weakness before users do. Use when a user says "roast my product", "harsh feedback", "be brutal", "what sucks", "find weaknesses", "product critique", "tear it apart", or "what would kill this". Deliberately harsh but constructive — scores each dimension and explains exactly what to fix.

Manage project learnings across sessions. Review, search, prune, and export what superstack has learned. Use when asked to "what have we learned", "show learnings", "prune stale learnings", "export learnings", or "remember this". Proactively suggest when the user asks about past patterns or wonders "didn't we fix this before?"