Claude Skills by tstapler

Deploy and operate Temporal Workers on serverless compute (AWS Lambda) driven by the Worker Controller Instance (WCI). Use when the user mentions: "serverless worker", "Temporal serverless", "Worker Controller Instance", "WCI", "deploy Temporal worker on Lambda", "Lambda packaging", "Lambda timeout", "WCI inspection", "CloudFormation Temporal".

Enforce Red-Green-Refactor TDD cycle. Use when implementing any new class or method — write the failing test first, then make it pass. Never write production code before a failing test exists.

Design, implement, or review config.d-style layered configuration using Tyler's standard precedence model: tracked universal base, tracked overlay fragments, untracked machine-local base, and untracked machine-local fragments. Use whenever adding configuration that varies by machine, employer/work overlay, environment, or repository; when replacing a monolithic settings file; or when deciding how multiple dotfiles repositories can contribute configuration without owning the same file.

Write, review, or model-check TLA+/PlusCal specs for distributed systems — leader election, consensus (Raft-style), message passing, network partitions/reordering/loss, crash-restart, clocks, CAS/optimistic-concurrency fields. Use whenever the user asks to model a protocol formally, write a TLA+ spec, run TLC, interpret a TLC counterexample, or asks "does this design have a race/lost-update/split-brain bug" for a distributed or concurrent system. Also use before trusting a spec's "no error fo...

Given a brief note describing a topic you want researched, research it (web search across authoritative sources) and write the findings into the personal Logseq wiki as atomic, cross-linked pages, then log it in today's journal. Use for prompts like "synthesize <topic> to my wiki", "research X and add it to my notes", or "look into Y and write it up" — for a *new* topic, not a video game (→ `game-guide-synthesis`) and not content you already have in hand from one specific source (→ `knowledge...

Encode invariants and business logic into the type system so illegal states are unrepresentable. Use when designing domain models, reviewing code for primitive obsession, building Value Objects, modeling state machines, or applying Parse-Don't-Validate. Covers Go, Python, and Java with concrete before/after examples.

Apply Android Material Design 3 (Material You) UX best practices when implementing Android UI features, reviewing Compose code, or making design decisions for gesture navigation, edge-to-edge layout, touch targets, accessibility, and motion. Use when writing or reviewing Jetpack Compose UI code targeting Android, choosing between navigation patterns, sizing touch targets, handling system insets, or answering questions about Android-specific UX guidelines. Essential for KMP projects with Andro...

Apply React composition patterns to eliminate boolean prop proliferation. Use when refactoring components or designing flexible component APIs.

Generate a complete design system for any product type. Use when building UI, choosing colors/fonts/styles, or starting any frontend project.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Design and iterate on logos using SVG. Use this skill when the user asks to "create a logo", "design a logo", "make me a logo", "iterate on this logo", "logo for my project", or discusses logo design, branding icons, or wordmarks.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Apply Vercel's 70-rule React/Next.js performance optimization guide. Use when writing, reviewing, or refactoring React components or Next.js pages.

Audit UI code against 100+ web best practices - accessibility, focus states, forms, animation, typography, images, performance, dark mode, i18n. Use when asked to review UI or check accessibility.

Identify commits/changes in a locally-checked-out source repo that should

Use this agent when you need expert guidance on User Experience (UX),

Map user journeys for an existing app using parallel lean agents — a PM story-map backbone, a UX flow analysis, and Mermaid diagram generation — then synthesize into a structured documentation artifact. Minimizes coordinator context by having each agent write full output to /tmp and return only a structured summary. Grounded in Jeff Patton (User Story Mapping), Jakob Nielsen (Usability Heuristics), and the lean-agent-loop pattern.

Generate design recommendations and guidance for new features using ux-expert agent

Conduct comprehensive UX review using ux-expert agent and document findings with project-coordinator

Use when about to claim work is complete, fixed, or passing, before committing

Work out W-4 withholding elections (new job, job change, mid-year income jump, or an annual check-up) using the official IRS Tax Withholding Estimator, and translate the result into concrete W-4 form entries.

Scan Gmail for clothing purchase receipts, extract item details (brand, product, color, size, price, purchase date), download product images, then catalog each item in the Logseq wiki: update Wardrobe.md in the correct section, create/update brand pages, and link to the product page, Internet Archive snapshot, and original receipt email. TRIGGER when the user wants to sync recent clothing purchases to their wiki, catalog new wardrobe items from email receipts, or audit what they've bought.

Review and rewrite text to reduce AI detection signals and increase authenticity. Flags overrepresented AI vocabulary, structural signatures (uniform paragraph lengths, formulaic openers/closers, transition-word overuse), burstiness flatness, hedging, abstract nominalizations, and missing specificity. Produces flagged audit with line-level rewrites. Use on cover letters, personal statements, blog posts, essays, and documentation where the author's voice must read as genuinely human.

Full writing-quality workflow — scope (audience/tone) -> multi-facet review (structure, readability, visuals, tone, humanize) as parallel subagents -> fix loop with fresh re-verification -> report. Entry point for improving any piece of writing, not just design docs.

Establish or confirm a piece of writing's audience, tone, and purpose before reviewing it. Phase 1 of the writing pipeline — run standalone or via writing:full.

Check whether a piece of writing's actual register matches its declared audience and tone (from writing:scope). One check in the writing pipeline — run standalone or via writing:full.

Diagnosing and resolving zombie process accumulation; measuring leak rate; identifying cmd.Start() without Wait; killing residual zombies; validating a zombie fix

Use this skill when breaking a large change into a stack of reviewable PRs

Analyze code systematically: clone repos, inspect JARs, search documentation, reverse-engineer binaries. Triggers: analyzing unknown codebases, finding API endpoints, understanding compiled code, security auditing.

Profile the Claude proxy to identify performance bottlenecks, event loop blocking, and optimization opportunities using py-spy and other profiling tools.