Claude Skills by lukaskellerstein

Create a complete Paperclip company package — guided setup with org structure, agents, runtime config, infrastructure, and import-ready output

Plan and document the required software, infrastructure, and logistics for a Paperclip company — domains, GitHub, Docker Hub, Kubernetes, Slack, Google Workspace, Stripe, shipping providers, and CI/CD pipelines. Use when setting up infrastructure for a new company or auditing what an existing company needs.

Design the complete work hierarchy for a Paperclip company — Goals, Projects, and Tasks as a unified top-down planning workflow. Produces ._planning.json for deterministic generation of goals/, projects/, and tasks/ directories. Use when creating a new company's work plan, reorganizing work structure, or linking goals to projects and tasks.

Integrate and manage Stripe payment processing — accept payments, manage subscriptions, generate invoices, handle refunds, and configure webhooks. Covers Stripe Checkout, Payment Intents, Subscriptions, Invoicing, and Connect. <example> Context: User wants to set up Stripe user: "integrate Stripe payments into my app" </example> <example> Context: User wants to create a checkout user: "add Stripe checkout to my product page" </example> <example> Context: User wants to set up subscriptions ...

Integrate and manage Zásilkovna (Packeta) shipping for Czech and Slovak logistics. Create shipments, generate labels, track packages, manage pickup points, and configure webhooks using the Zásilkovna API. Covers both the REST API and SOAP API. Includes ready-to-run CLI scripts for all API operations. <example> Context: User wants to set up Zásilkovna integration user: "integrate zásilkovna into my project" </example> <example> Context: User wants to create a shipment user: "create a zásilko...

Gets a project into a demo-worthy, deterministic state before recording — boots the app, seeds realistic data, bypasses or scripts login, freezes clocks and random values, hides dev-only UI, and makes state resettable between takes. Use before capturing any demo video section, when a demo shows empty states or placeholder data, when takes are not reproducible, or when deciding how to run the app for recording.

Assembles measured clips and narration into a finished demo video with Remotion — reconciles real durations into a timeline, then renders. Covers the timeline contract, the bundled timeline-driven Remotion project, how to extend or replace it for custom compositions, transitions, camera moves, captions, music ducking, and draft/final render presets. Use at the reconcile, render, or editing stage of a demo video, or when changing how the finished video looks.

Records demo video clips by driving a running app — one clip per storyboard section, with human-feeling pointer motion, dwell timing, and per-character typing. Covers the Playwright MCP video tools for web apps and a generated Playwright Electron script (plus a macOS screen-capture fallback) for desktop apps. Use when recording, re-recording, or rehearsing any demo section, or when captured footage looks like an automated test.

Quality-checks a rendered demo video before it ships — extracts frames, grades each section against its successCriteria, and finds spinners, empty states, clipped text, exposed secrets, audio/video desync, and pacing problems. Use after a draft render, before a final render, or when asked whether a demo video is good enough to ship.

Turns a codebase into a demo narrative that has value — picks which capabilities earn screen time, structures them into beats, sets per-section durations, and writes the voiceover text at a speakable pace. Use at the scripting stage of a demo video, when writing or revising demo/storyboard.json, when the user asks what the demo should show, or when a demo feels like a feature tour instead of a story.

Checks and installs everything the demo-video pipeline needs — ffmpeg, Playwright browsers, the Remotion plugin, uvx, and the ElevenLabs key — and scaffolds demo/ in the target project. Use before the first demo video on a machine, when any pipeline stage reports missing tooling, when MCP video tools are absent from /mcp, or when the user asks to set up, doctor, or install the demo toolchain.

Orchestrates building a narrated demo video of a project — reads the codebase, writes a storyboard, prepares deterministic app state, drives the UI with Playwright to record clips (web and Electron), generates ElevenLabs voiceover, reconciles measured durations into a timeline, and renders the final cut with Remotion. Use whenever the user asks for a demo video, screencast, product walkthrough, feature showcase, release video, or narrated recording of an app; also load this before touching an...

Generates demo narration with the ElevenLabs MCP server — one audio file per storyboard section, measured so the editor can cut picture to voice. Covers voice and model selection for product demos, fitting a line to a target duration, pronunciation of product names, optional word-level caption alignment, and music beds. Use at the voiceover stage of a demo video, when regenerating narration, or when changing the narrator.

Review and critique existing designs, websites, or frontend code against design principles. Checks for common anti-patterns like generic fonts, poor contrast, inconsistent spacing, and lack of visual hierarchy. Use when the user asks to "review my design", "what's wrong with this layout", "critique my website", "how can I improve the design", "audit the UI", "check my frontend", "make it look more professional", or "why does this look off". Produces actionable feedback with specific fix sugge...

Manage and audit design system consistency — color palettes, typography scales, spacing systems, accessibility (WCAG contrast checks), and component inventory. Use when the user asks to "check contrast ratios", "audit my design system", "create a color palette", "generate a type scale", "check accessibility", "WCAG compliance", or "review design consistency".

Design guidance and aesthetic patterns for building beautiful, distinctive frontends — websites, web apps, landing pages. Provides typography strategies, color application, motion choreography, layout composition, and component design recipes. Use when the user asks to "make this look better", "improve the design", "it looks too generic", "add visual polish", "make it look professional", "design a landing page", "hero section design", "make it beautiful", or any request about visual quality o...

Create a comprehensive design language and styleguide for any project — websites, apps, blogs, presentations, marketing pages. Given a project type, brand, and audience, produces aesthetic direction, font selections with pairings, color strategy, spacing philosophy, imagery style, and tone. Use when the user asks to "create a styleguide", "define the design language", "what fonts should I use", "choose a color palette for my project", "design direction for my website", "how should my app look...

Think a decision through — explore an idea, compare approaches, sketch a design, plan a change, research feasibility or prior art. A read-only thinking partner that ends in a recommendation, not an edit.

Identify unused code (functions, imports, exports, variables, types, classes) and propose cleanup. Use this skill when the user says "find dead code", "unused code", "clean up unused", "code hygiene", "find unused imports", "what can I delete", or any variation of wanting to identify and remove code that is no longer referenced.

For every git repo in the current folder, create and merge a PR for feature-branch work, then return to the default branch and pull. With no arguments this runs fully autonomously across ALL sub-repos — commit → push → PR → squash-merge → checkout main → pull. Use whenever the user asks to commit, ship, push, open/merge a PR, "update all repos", "get back to main", or any variant of saving work to a PR and bringing branches up to date — even if they mention only one part of the flow.

Answer a question about how things are right now — this codebase, its history, its behavior, a library, an error. Investigates and answers with evidence. Changes nothing, ever.

Synchronize the spec folder with the current state of implementation on a feature branch. Use this skill when the user says "sync spec", "update spec", "spec is outdated", "reflect changes in spec", "update the plan", "sync specification", "keep spec up to date", "spec drift", or any variation of wanting to reconcile implementation changes back into the spec-kit specification files (spec.md, plan.md, tasks.md, research.md, etc.).

Update project dependencies to their latest versions, verify nothing breaks, and report what changed. Use this skill when the user says "update dependencies", "upgrade packages", "latest versions", "update deps", "outdated packages", "bump dependencies", or any variation of wanting to bring project dependencies up to date.

Create or update project documentation. If no docs/ folder exists, creates comprehensive documentation from scratch using multiple parallel agents covering architecture, infrastructure, security, tech stack, and features. If docs/ already exists, re-analyzes the codebase and updates all sections EXCEPT docs/features/ (use update-feature-docs for feature documentation). <example> Context: User wants to create documentation for a project user: "create documentation for this project" </example>...

Generate or update documentation for the current feature branch. Analyzes all changes (commits, diffs) between the feature branch and base branch, then creates or updates docs/features/<index>_<feature-name>/README.md with incremental indexing based on existing feature docs. Use when documenting a feature branch, creating feature documentation from branch changes, or updating existing feature docs after additional commits. <example> Context: User wants to document their feature branch user: ...

Create or update a professional root-level README.md for a repository. Use when creating a README, updating a README, generating a README, improving a README, making a professional README, crafting an open-source README, or adding badges, diagrams, and quick-start sections to a project's main README file.

Authentication/authorization infra with Keycloak and OAuth2-proxy. Use for identity providers, SSO, OIDC/SAML, realm/client config, user federation, and OAuth2-proxy sidecar or ingress auth on Kubernetes.

Helm chart authoring, templating, and release management for Kubernetes: charts, values, templating functions, repositories, dependencies, and lifecycle operations.

Istio service mesh: traffic management, gateways, virtual services, destination rules, mTLS, authorization policies, EnvoyFilters, and observability.

Kubernetes and GKE operations: kubectl, manifests, deployments, services, workload identity, autopilot, config connector, private clusters, and troubleshooting.

Terraform infrastructure-as-code for provisioning cloud and Kubernetes resources: modules, state and backends, providers, and plan/apply workflows.

Traefik reverse proxy and ingress: routers, services, middlewares, TLS/certificates, and Kubernetes CRD (IngressRoute) configuration.

ALWAYS use this skill when the user asks to create, draw, design, produce, or generate any visual asset that is not a photograph or illustration. Fires on words like diagram, chart, graph, flowchart, architecture, system map, topology, sequence diagram, state machine, class diagram, ER diagram, C4, UML, BPMN, mind map, org chart, wireframe, mockup, UI sketch, infographic, dashboard, treemap, sankey, heatmap, choropleth, network graph, map, plot, visualization, mermaid, d3, drawio, draw.io, .d...

Fetch pre-made SVG icons from open-source icon libraries (Lucide, Heroicons, Tabler Icons) for use in websites, presentations, Figma designs, or any project. Use when the user asks to "add an icon", "use a search icon", "find an icon for settings", "get SVG icons", or needs clean SVG icons. NEVER draw icons manually — always fetch from these libraries. Supports browsing, searching, and using icons in code, Figma, or any design context.

Generate and work with images using the media-mcp server's generate_image tool. Use when the user asks to create images, generate visuals, make illustrations, create thumbnails, design graphics, produce concept art, create product mockups, or work with reference images. Supports multiple aspect ratios, resolutions up to 4K, reference image input, and Google Search grounding for realistic results.

Find and download existing images from the web using stock photo services like Unsplash, Pexels, and Pixabay. Use when the user wants to find real photographs, stock photos, or existing images rather than generating new ones with AI. Also useful when the user needs royalty-free images, creative commons photos, or reference material from the web.

Craft effective prompts for AI image/video generation and search queries for stock photo services. Translates design direction and styleguide choices into specific, style-consistent prompts. Use when the user asks to "find images for my site", "generate a hero image", "what kind of images should I use", "create image prompts for my project", "write prompts for image generation", "Unsplash query for...", or when building a media asset list for a design project. Works with any styleguide and de...

Generate music and instrumental audio using the media-mcp server's generate_music tool. Use when the user asks to create music, background tracks, sound effects, ambient audio, jingles, or instrumental compositions. Supports weighted text prompts for blending styles, BPM control, musical scale constraints, temperature for creativity, and duration settings.

Generate text-to-speech audio using the ElevenLabs MCP server's text_to_speech tool. Use when the user asks to create voiceovers, narration, audio from text, spoken dialogue, podcast-style audio, audiobook readings, announcements, or voice content. Supports voice selection by name or ID, multiple models (multilingual, flash, turbo), stability/similarity/style controls, speed adjustment, and multiple output formats.

Expert knowledge for working with SVG (Scalable Vector Graphics) — optimization, embedding, animation, accessibility, responsive scaling, React integration, filters, and programmatic creation. Use when the user asks to "optimize SVG", "clean up SVG", "reduce SVG file size", "embed SVG in HTML", "inline SVG vs img tag", "animate SVG", "SVG stroke animation", "SVG morphing", "accessible SVG", "SVG viewBox", "responsive SVG", "SVG in React", "SVG sprite", "SVG gradient", "SVG filter", "clip-path...

Generate videos and GIFs using the media-mcp server's generate_video tool. Use when the user asks to create videos, animations, GIFs, motion graphics, product demos, explainer clips, or video content. Supports text-to-video, image-to-video (animate a still image), and video extension modes with native audio generation.

ALWAYS use this skill FIRST, before producing or fetching ANY media asset — an image, video/GIF, chart, graph, diagram, infographic, SVG/icon, music, or speech/voiceover — and before any stock-photo search. It is the mandatory pre-generation gate. For a SINGLE asset it runs a short brief — clarify the ask → confirm style/design guidelines → pin the message → decide what's IN and OUT → draft the prompt/spec → review and tailor it → only THEN generate and verify. For a WHOLE deliverable you vis...

This skill should be activated when the user asks to create a Word document, report, memo, letter, proposal, whitepaper, or anything involving .docx output. Also triggers when the user says 'write a report', 'create a document', 'make a Word file', 'draft a proposal', 'generate a whitepaper', or mentions .docx. Creates polished Word documents (.docx) using the docx npm package (docx-js) for all document generation and the media-plugin for sourcing/generating images. Can also edit existing DOC...

This skill should be activated when the user asks to make a presentation, slide deck, pitch deck, or anything involving .pptx output. Also triggers when the user says 'make me slides', 'create a deck', 'presentation about X', or mentions PowerPoint. Creates polished PowerPoint (.pptx) presentations using PptxGenJS for all slide generation and the media-plugin for sourcing/generating images. Can also edit existing PPTX templates. Activates even for simple 'make a quick 3-slide deck' requests —...

This skill should be activated when the user asks to create, edit, read, or analyze Excel spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Triggers for: building financial models, creating data tables, formatting spreadsheets, adding formulas, cleaning tabular data, converting between tabular formats. Also triggers when user mentions 'spreadsheet', 'Excel', 'workbook', or references an .xlsx file. Do NOT trigger when the primary deliverable is a document, presentation, or visualization.

CSS and GSAP animation patterns for websites — ScrollTrigger, timelines, stagger effects, page transitions, micro-interactions, and performance optimization. Use when implementing animations for web design projects, when the user wants scroll-triggered animations, page load reveals, GSAP integration with React/Vite, animation planning, performance best practices, or when a design document specifies animations for sections.

Project-level CSS architecture for React/Vite websites — Tailwind CSS configuration with design tokens, shadcn/ui theming, CSS custom properties, and responsive strategy. Tailwind-first approach. Use when setting up CSS for a new React/Vite project, mapping a styleguide to Tailwind config, configuring shadcn/ui theme, defining responsive breakpoints, creating global styles, or when a design document needs a CSS architecture section.

Information architecture and content planning for websites — page structure, section definitions, content hierarchy, text content, and mock data strategy. Use when planning what pages a website needs, what sections go on each page, what content fills them, when the user asks "what pages/sections should my website have?", needs mock data for a prototype, or needs text content (headlines, body, CTAs) for sections.

Generate alternative design variations from an existing web design — systematically vary colors, typography, animation intensity, and spacing density while preserving page structure and content. Use when the user wants multiple visual options from a base design, says "generate variations" or "try different styles", wants to compare visual approaches side-by-side, or as a post-workflow option after completing a web design.