Art & Design

Run a full pre-launch audit on a web app before it goes public. Use when the user says "am I ready to launch", "pre-launch check", "audit my app before launch", "what am I missing before shipping", or asks for a launch checklist. Produces a scored report with blockers, fixes, and a go/no-go verdict.

Audit and write SaaS landing-page copy using MicroConf customer-research and emotional-copy methods. Use for a landing-page URL, pasted copy, local website code, or a blank-slate SaaS page when the founder wants a rigorous copy review and an iterative interview to resolve customer, positioning, proof, and CTA gaps before drafting or rewriting.

Write, rewrite, or critique conversion copy for homepages, landing pages and search-driven pages (service pages, comparisons, glossary and "what is" pages, guides, cost guides, integration and use-case pages), and the templates or LLM prompts that generate them at scale. Covers hero headlines, subheads, section headings, proof, CTAs, FAQ, form microcopy, title tags and meta descriptions, especially for B2B services firms, agencies, consultancies and technical products sold to expert buyers. Use this whenever the user asks for website copy, a homepage or landing page rewrite, a value proposition, headline or CTA options, SEO page copy, programmatic page templates, "make this page convert", or "our copy sounds generic / AI-written", even if they never say "copywriting". Not for blog articles, emails, ads, or social posts.

Draft one landing page as one https URL, one offer, and one action, then score it. Use when someone asks for a landing page, a single-offer page, or a page with one call to action. Refuses a sitemap or a list of pages. Not for writing the value line (use evp), setting price tiers (use pricing), or the emails after opt-in (use email-sequence).

>- GitHub Actions conventions for Nuvraxis Next.js apps — exactly three workflows: pr.yaml (every PR to any branch: Biome, stylelint, typecheck/test/build with turbo --affected, Docker build + health check, helm lint + kubeconform; publishes nothing), main.yaml (push to main: one multi-arch image to GHCR tagged sha-SHORTSHA and main, provenance + SBOM, gha cache), release.yaml (tag vX.Y.Z: verify on main, retag the existing image without rebuilding, package and push the Helm chart to OCI, GitHub Release with chart, digest and SBOM). Minimal permissions per job, GITHUB_TOKEN only, pinned action majors. Use when editing .github/workflows/*, adding a CI step, or debugging a failed run or release.

按用户主题创作完整字效作品，保护明确锁定项，统一随包指导与真实动效验收。

审查主题辨识、构图、字面与完整入退场；按当前需求修订，避免把旧反馈变成全局禁令。

Splits the copy of a web page into blocks (hero, benefits, how it works, testimonials, pricing, FAQ, CTA and others) and writes 1 reusable prompt per block. Each prompt writes the same kind of text for a different product and has an example checked against it. Copy only; the design is ignored. Use when the user gives a URL and asks to break down or reverse-engineer the copy of a landing page, make prompts per section, write a similar block for their site, or see how a competitor's page is written.

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pg_cron, pgmq), vector/semantic search (pgvector), and restoring dumps (pg_restore) or importing data. Also load it when diagnosing slow queries, high CPU, timeouts, EXPLAIN plans, connection exhaustion, locking, bloat, or rows visible to the wrong user or tenant. This is not just a performance guide — schema, migration, security, and SQL authoring tasks need these rules too, even for a one-column change or a single query.

Add or review an accessible portfolio project-preview reader for ordered long images, document pages, or staged visual modules.

Validate a statically exported portfolio website for GitHub Pages release readiness. Use before publishing or diagnosing deployment regressions.

Prepare, optimize, and register portfolio images and documents while preserving provenance, accessibility, and responsive rendering contracts.

Review or implement portfolio UI motion against an existing motion system, including reduced-motion, keyboard, performance, and responsive constraints.

Validate Chinese and English portfolio routes, content states, metadata, and fallbacks. Use when adding or reviewing localized portfolio content.

Compare a portfolio website route with an approved visual reference at desktop and mobile sizes, then report evidence-backed visual defects and fixes.

Prüft Websites auf SEO, GEO und KI-Sichtbarkeit, Seitenarchitektur, strukturierte Daten, Nutzerführung, Barrierefreiheit und Conversion. Verwenden für belegbare Website-Audits, Verbesserungspläne und regelmäßige Qualitätskontrollen, einschließlich Shops, lokaler und internationaler Websites.

Set up and work with Far & Wide, the AI-visibility platform that measures whether ChatGPT, Gemini, Perplexity, Copilot and Google's AI answers mention and recommend a brand, and writes the fixes behind it. Use when the user mentions Far & Wide or farandwide, wants to connect Far & Wide to their agent, fill in their brand on Far & Wide, check their AI visibility, read their Far & Wide audit, or apply Far & Wide recommendations or fixes. Covers connecting the MCP server, the steps only the person can do, filling in the brand from their repository and website, and the day-to-day loop of reading results and applying fixes.

Check whether a website has a valid /llms.txt (llmstxt.org format, working links, size) and whether robots.txt lets AI crawlers such as GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot and Google-Extended in. Use when the user asks about llms.txt, AI crawler access, blocking or allowing AI bots, or whether ChatGPT/Claude/Perplexity can read their site. Read-only.

Give one web page a quick 0-100 AI search visibility (GEO/AEO readiness) score from its server-rendered HTML - AI crawler access, Organization/WebSite JSON-LD, structured data, title/meta, question headings, answer-first opening, llms.txt and freshness - with the top 5 fixes. Use when the user asks if a page is ready for ChatGPT, Perplexity, Google AI Overviews or other AI search, or wants a GEO/AEO score.

Polish, translate, or faithfully revise Chinese or English TeX academic manuscripts; verify source-to-output TeX, math, citation, numerical, and claim preservation; audit cross-section terminology, mathematical notation, and numerical consistency; or apply an author-approved notation mapping. Use for sentence-level through full-manuscript engineering-journal language work when technical truth and protected TeX must remain fixed. For full manuscripts, run terminology, notation, and numerical-consistency audits by default. Do not use as the main skill for novelty review, literature selection, or argument redesign.

Develop and maintain existing repositories, implement features, fix bugs, refactor, and update dependencies with project context, verification, documentation, and clean commits. Use for hands-on repository work that should read AGENTS, PRD, design, state, and worklog documents and keep them aligned with the delivered change.

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.