Claude Skills by alunadev

Expert system for designing and architecting AI agent workflows. Use when building AI agents, designing multi-agent systems, integrating tools into agent architectures, choosing between single vs. multi-agent setups, or translating a business problem into an agentic solution. Triggers on: "build an agent", "design agent workflow", "multi-agent system", "agent architecture", "how should I structure this agent". Covers 9-step building process, 8-layer architecture framework, MCP integration, an...

Expert strategy advisor for products built on LLMs or agents — not general product strategy (see `product-strategy` for that). Use this — proactively and without waiting to be asked — whenever choosing where to apply AI in a product, deciding between RAG and fine-tuning, designing how much autonomy an AI feature should have, evaluating whether an AI feature is actually defensible, or deciding whether to add AI to a feature at all. Also triggers for: "should this be an agent or a simple LLM ca...

Implementation and taxonomy skill for analytics tracking — event naming, properties, tracking plans, GA4/GTM/Amplitude setup, and debugging. Use this for the "how do we actually wire this up" layer, not the "what should we measure and why" layer (that's `product-analytics` — use this skill alongside it, after the metrics/tracking-plan decisions are made). Use this — without waiting to be asked — whenever the user mentions "set up tracking," "GA4," "Google Analytics," "Amplitude," "event track...

Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and duration, how it interrupts, how it exits. Writes the implementation. Use when asked to animate something, add motion, make a component feel alive, or build a transition. For critiquing existing motion use `review-animations`; for auditing a whole codebase use `improve-animations`. Source: github.com/e...

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one. Source: github.com/emilkowalski/skills.

Designs REST and GraphQL APIs following production best practices for resource naming, error handling, versioning, authentication, and documentation. Use this skill when designing new API endpoints, reviewing API contracts, implementing GraphQL schemas, establishing API conventions for a project, or writing API documentation. Apply when creating any route in Next.js API routes or route handlers, any Supabase Edge Function, or any backend endpoint — even if it starts small, these patterns prev...

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces. Source: github.com/emilkowalski/skills.

Guide to Sonner, the React toast library — install and wire up the Toaster, pick the right toast() call, promise and loading toasts, updating, dismissing and persisting toasts, styling, theming and icons, positioning and multiple toasters. Use when working with Sonner or troubleshooting it — toasts that don't appear, appear twice, lose their styles, ignore Tailwind classes, sit behind a modal, or don't follow dark mode. Companion to `taste-skill`'s library table, which recommends Sonner for t...

Expert Socratic discovery skill for exploring ideas, architecture decisions, and technical design before writing any code. Use this skill — proactively and always first — when requirements are vague, when the user is debating between technical approaches, when the problem is unclear, or when a design decision could have significant architectural consequences. Triggers on: "should we use X or Y", "help me think through", "I'm not sure how to approach this", "what's the best architecture for", ...

Generates a bespoke brand identity for a new project through a short interview, then writes it as a DESIGN.md file (Google Stitch format) in that project's own repo. Use when starting a new project and its visual identity isn't defined yet, when asked "what's the brand for X", "define the brand for this project", "new project design system", or before the first UI work on a fresh project. Do NOT use this to restyle or elevate a project that already has an identity — that's `taste-redesign`.

Structured methodology for solving, writing, and presenting hiring case studies for Senior Product Manager and Technical PM roles. Use when resolving a case study, reviewing a case study response, or building a presentation prototype from a completed case study. Covers the full process from problem understanding to final delivery, including data analysis, written response, and interactive presentation.

Transforms technical git commits into a clear, compact, user-friendly changelog. Use when preparing release notes, creating product update summaries, documenting changes for customers, or maintaining a public changelog page.

Shared vocabulary for designing deep modules — a small interface hiding a lot of behavior. Use when designing or improving a module's interface, deciding where a seam belongs, deciding whether to extract or merge modules, or making code more testable.

Profiles 5 competitors, identifies white space, and delivers a positioning recommendation — not a feature comparison table. Use this skill — proactively and without waiting to be asked — whenever entering a new market, before defining bets in product strategy, when pricing needs a competitive anchor, or when losing deals to a specific competitor. Also triggers for: "competitive analysis", "competitor research", "who are my competitors", "market landscape", "white space", "differentiation angl...

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Maps the end-to-end customer experience from awareness to advocacy — touchpoints, emotions, friction points, and improvement opportunities per stage. Use when identifying drop-off points, improving onboarding, or understanding the full user lifecycle. Triggers on: customer journey, user journey, journey map, touchpoints, onboarding experience, funnel analysis, churn points, aha moment, drop-off, user lifecycle.

General GitHub workflow — branching, commits, pull requests, code review, secrets hygiene, submodules, and git worktrees. Use when the user wants to save changes, push to GitHub, open a PR, work with a submodule, set up a worktree, or perform any git/GitHub operation.

Conduct a design interview, generate 5 distinct UI variations in a temporary route, collect real click-to-comment feedback on the live rendered variants via human-review, and produce an implementation plan. Use when the user wants to explore UI design options, redesign an existing component/page, or create new UI with multiple genuinely different approaches to compare — before writing production code or committing to a direction. For a lighter, single-component variant picker with no intervie...

Write, read, and apply DESIGN.md files — Google Stitch's open AI-readable design-system format (YAML design tokens + Markdown rationale). Use when asked to "create a design.md", "extract a design system from [brand/PDF/site/screenshots]", "document this brand for AI tools", or when reverse-engineering a brand's visual identity into reusable tokens for an AI coding agent to apply consistently.

Maintains a project's domain vocabulary and records architecturally-significant decisions as they're made — a CONTEXT.md glossary and gated ADRs, not passive documentation read once. Use when terminology conflicts or turns fuzzy, when making a decision that's hard to reverse/surprising/a real trade-off, or when a stated domain rule doesn't match what the code actually does.

Builds complete bilingual email drafts from intent and audience. Use when the user asks to write, rewrite, localize, polish, or generate an email, campaign email, outreach message, customer update, follow-up, announcement, invite, sales email, internal note, or lifecycle email and wants clear subject lines, preheaders, body copy, CTAs, variants, or English and Spanish versions.

Encodes Emil Kowalski's design engineering philosophy — UI polish, component design, animation decisions, and the invisible details that make software feel great. Use as the reference/philosophy layer for interaction craft. For the narrower, task-specific pieces of this same philosophy, see `animate` (build one animation), `review-animations` (review a diff), `improve-animations` (audit a codebase), `find-animation-opportunities` (find what's missing motion), `animation-vocabulary` (name an e...

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when adding try/catch blocks, handling async errors, fixing silent failures, or designing fallback strategies. Triggers on: unhandled exception, error boundary, async error, retry logic, fallback, graceful degradation, API error response, catch block, error state.

Translates stakeholder feature requests into validated outcome statements before any work is committed. Use this skill — proactively and without waiting to be asked — whenever a stakeholder, exec, or customer arrives with a pre-packaged solution: "we need a dashboard", "add a Slack notification", "build an export feature", "create a report", "let's add a filter", "can we just add X". Also triggers for: "how do I push back on this request", "what outcome does this feature solve", "outcome vs o...

Reverse engineering de diseños Figma para generar especificaciones técnicas completas listas para implementar en código. Usar cuando el usuario comparte capturas, exports o descripciones de un diseño en Figma y quiere documentarlo técnicamente, extraer tokens de diseño, entender la estructura de layouts, o preparar una spec para que un desarrollador o Claude Code lo implemente. También usar cuando el usuario dice "reverse engineering del diseño", "documenta este Figma", "quiero implementar es...

Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animations, use `improve-animations` or `review-animations` instead. Source: github.com/emilkowalski/skills.

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. If the project already has a DESIGN.md, uses its tokens instead of the 12 built-in presets. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

Short clarifying interview before starting non-trivial engineering work — surfaces the actual requirement, what's explicitly out of scope, and what proves it's done. Use before writing code when the task's requirement, scope, or definition of done isn't already unambiguous. Not for trivial or fully-specified changes — that's ceremony, not clarity.

Identifies and designs growth loops (flywheels) for sustainable traction — evaluating 5 loop types: Viral, Usage, Collaboration, User-Generated, and Referral. Use when designing growth mechanisms or reducing reliance on paid acquisition. Triggers on: growth loop, flywheel, viral loop, referral program, product-led growth, PLG, user acquisition, growth strategy, retention loop, compounding growth.

Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff. Source: github.com/emilkowalski/skills.

Writes LinkedIn posts in the user's own voice, from a real observation or earned insight — not engagement-bait or growth-hacking templates. Use when drafting a LinkedIn post, turning a work observation or lesson into a post, or reviewing a LinkedIn draft for tone. Normally invoked by `writing-system` once LinkedIn is the chosen platform, but works standalone too. Companion skill: `x-thread-writer`, for the same voice on X/Twitter.

Maintains a product repo's canonical docs structure (CLAUDE.md, progress.txt, docs/product+system+design-system, context/) as single source of truth, and keeps the log.md session history separate from the progress.txt state snapshot. Trigger after feature completion, before git push, on architecture changes, at session end, or explicit "update docs"/"sync documentation" requests. Skip for trivial changes (<10 LOC, no logic/schema/UI changes).

Structured verbal communication framework for Senior PM and TPM interviews. Use when preparing for interviews, rehearsing answers, practicing English (or Spanish) delivery under pressure, or when any interview question needs to be answered in a crisp, structured way. Covers SCQA/STAR/C-F-I scaffolding, answer templates by question type, pushback handling, English- and Spanish-under-pressure tactics, and post-interview debrief methodology. Trigger on any variant of "how do I answer this?", "re...

Creates decision-focused PRDs and product specs — the kind that make explicit decisions, not document hopes. Make sure to use this skill whenever someone asks to write, review, draft, or improve any product document, including PRDs, feature specs, requirements docs, or product specifications. Trigger even when the user doesn't say "PRD" explicitly — phrases like "write a spec for X", "define requirements for Y", "what should my PRD include", "help me document this feature", or "my spec feels ...

Expert product analytics advisor for Senior PMs. Use when defining success metrics for a PRD, designing an A/B experiment, setting up an analytics tracking plan, analyzing post-launch impact, or when data exists but there's no clarity on what to measure. Produces structured metrics frameworks that connect to product decisions, not dashboards.

Creates go-to-market plans and launch checklists for features and side projects. Use when preparing a feature for public release, planning a Product Hunt launch, defining a rollout strategy, creating a post-launch review framework, or coordinating the technical, product, and marketing work for a launch. Triggers on: "prepare launch", "go-to-market", "Product Hunt", "launch checklist", "rollout plan", "launch this feature".

Expert product strategy advisor for Senior PMs. Use this skill — proactively and without waiting to be asked — whenever defining a product vision, setting quarterly OKRs, building a roadmap, choosing between competing bets, entering a new product area, or when stakeholders disagree on direction. Also triggers for: "what should we prioritize", "we need a north star", "how do we choose between X and Y", "roadmap conflict", "what are our bets this quarter", "strategy alignment", "choosing what N...

Enriches vague, low-detail prompts into structured, agent-optimized XML before execution. INVOKE IMMEDIATELY — before any tool use or file reads — when you detect any of these signals: prompt under 10 words with no file path or error message; vague action verbs with no object ("fix the bug", "make it better", "clean this up", "refactor this", "optimize performance", "improve the UI", "add authentication", "add payments", "add notifications", "build the feature"); CLARIFIER_ADVISORY in your co...

A library of reusable, production-tested prompt engineering patterns for building AI-powered features. Use when designing system prompts for apps, building AI pipelines, selecting the right prompting technique for a use case, or reviewing prompts for common failure modes. Complements the prompt-engineering skill (which covers the optimization framework); this skill covers the pattern library itself.

Expert prompt optimization system for the prompts INSIDE an AI product you are building — system prompts, LLM feature prompts, chatbot/agent instructions. Use when the user wants to write or improve a system prompt for an AI feature they're shipping, review/critique an LLM prompt, apply prompt-engineering techniques (chain-of-thought, few-shot, structured output, hard constraints) to a product prompt, or optimize cost/latency of a production prompt. Do NOT use this to clarify or structure the...

Build multiple genuinely different versions of a UI piece you describe, rendered behind a visual picker so you can flip through them live and promote the one that feels right. Use this proactively, without waiting to be asked, whenever evaluating a new feature, a layout, a section, a visual, a design, or any UI decision — divergent options beat a single guess. Fast, no interview, single-component scope. For a full structured exploration (interview, 5 variants of a whole page, real feedback co...

React and Next.js performance optimization guidelines from Vercel Engineering. Use this skill when writing, reviewing, or refactoring React/Next.js code. Apply it proactively whenever working on React components, Next.js pages, API routes, data fetching (server or client), bundle size, rendering performance, re-renders, server actions, hydration, animations, or JavaScript optimizations. If the code involves React or Next.js, use this skill — even if performance isn't the stated goal, these pa...

Self-contained code review checklist — formatting, type safety, duplication, readable conditions, logic-out-of-UI, test coverage, comment quality. Adapts to whatever tooling the project actually has (skips Prettier/TypeScript/test-runner checks if unconfigured). Use before merging, after completing a feature, or any time you want a second pass on code quality. In Claude Code, prefer the official `code-review` skill or `pr-review-toolkit`/`feature-dev` code-reviewer agents instead — both are r...

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy (see `emil-design-eng`). Default to flagging; approval is earned. Use when reviewing a diff for motion quality — not for writing features, fixing unrelated bugs, or general (non-motion) code review. For building an animation from scratch, use `animate`; for a whole-codebase audit, use `improve-animations`. Source: github.com/emilkowalski/skills.

Plans a sprint with capacity estimation, story selection, dependency mapping, and risk identification. Use when preparing for sprint planning, estimating team capacity, or balancing scope against velocity. Triggers on: sprint planning, sprint plan, capacity planning, sprint scope, story points, sprint goal, backlog grooming, sprint prep, what do we build this sprint.

Builds a Power × Interest stakeholder map and generates a communication plan per quadrant. Use when managing a complex launch, aligning cross-functional teams, or preparing stakeholder engagement strategy. Triggers on: stakeholder management, stakeholder map, stakeholder alignment, communication plan, power interest grid, cross-functional alignment, executive alignment, managing up.

Audits an EXISTING UI/codebase for generic AI patterns and applies targeted craft fixes — layout, interactivity, content, iconography, and code quality — without discarding the project's own identity. Use when a UI looks flat, generic, or "AI-slop" and there is code to improve, not build from scratch. Triggers on: "improve the design", "looks generic", "not polished enough", "redesign this", "elevate the UI", "it looks boring", "make it better looking", "apply taste", "design review". Works w...

Anti-slop frontend design skill for building NEW landing pages, portfolios, and UI from a brief. Reads the brief and existing brand context first, infers a design direction from three configurable dials (variance, motion, density), and ships interfaces that don't look templated or default-AI. Use when starting a new page/UI with no existing identity to preserve, or when asked to design something "that doesn't look like every other AI landing page." For auditing and upgrading an EXISTING UI, u...

Red-green-refactor test-driven development discipline — write a failing test at the public interface first, minimal code to pass it, one slice at a time. Use when writing new logic or fixing a bug (write the regression test first), for any code where correctness matters more than raw speed.

Creates research-backed user personas with JTBD, pain points, gains, and unexpected behavioral insights. Use when building personas from survey or interview data, or segmenting users to inform product decisions. Triggers on: user persona, user profile, customer segment, jobs-to-be-done, JTBD, persona creation, user segmentation, target user, who are our users.