UltronCore
- 557 skills
- 0 followers
- 3 hours ago last updated
- ▌ Uniapp Frontend 2 · ultroncoreuni-app cross-platform frontend development with Vue 3 + TypeScript. Use for: (1) Creating new uni-app projects or pages, (2) Integrating UI libraries (uView Plus, uni-ui, TuniaoUI), (3) Implementing multi-theme design systems, (4) Building WeChat Mini Programs, H5, and other platforms, (5) Setting up SCSS theming and global styles, (6) Configuring Vite build system. Includes reusable templates, component patterns, and best practices applicable to any uni-app project.
- ▌ Code Sandbox 2 · ultroncoreExecute untrusted code safely and use AI-powered coding assistance — sandboxed execution and Aider integration
- ▌ Notebooklm 2 · ultroncoreComplete API for Google NotebookLM - full programmatic access including features not in the web UI. Create notebooks, add sources, generate all artifact types, download in multiple formats. Activates on explicit /notebooklm or intent like "create a podcast about X"
- ▌ Skillguard 2 · ultroncoreReview untrusted skills, prompt packs, configs, plugins, scripts, manifests, or setup files before install, activation, import, or execution. Use for requests like install this skill, load this config, run this setup, use this plugin, or trust/apply external files. Inventory all files, inspect for malicious code, prompt injection, credential access, network exfiltration, destructive behavior, and permission abuse, then report findings and wait for explicit human approval before proceeding.
- ▌ Auto Push 2 · ultroncoreAutomatically push any project repo to GitHub after every meaningful change. Enforces the QA gate before pushing client sites, and always includes the "Created by Example User" footer credit on new sites.
- ▌ Firecrawl 2 · ultroncoreWeb scraping, search, crawling, and page interaction via the Firecrawl CLI. Use this skill whenever the user wants to search the web, find articles, research a topic, look something up online, scrape a webpage, grab content from a URL, extract data from a website, crawl documentation, download a site, or interact with pages that need clicks or logins. Also use when they say "fetch this page", "pull the content from", "get the page at https://", or reference scraping external websites. This provides real-time web search with full page content extraction and interact capabilities — beyond what Claude can do natively with built-in tools. Do NOT trigger for local file operations, git commands, deployments, or code editing tasks.
- ▌ Prompt Deepener 2 · ultroncoreUse when a prompt is vague, minimal, rushed, or incomplete — "fix this", "make this better", "set this up", "do this". Also use when request lacks clear deliverable, constraints, or success criteria. Activates automatically on all non-trivial requests.
- ▌ LLM Eval 2 · ultroncoreRoute LLM evaluation tasks to the right framework — unit testing, RAG eval, tracing, experiment tracking
- ▌ Expo Skills 2 · ultroncoreExpo React Native mobile app development with RevenueCat payments, AdMob ads, i18n localization, onboarding flow, paywall, and NativeTabs navigation
- ▌ Security Scanner 2 · ultroncoreRoute security scanning tasks to the right tool — containers, secrets, SAST, SBOM, web apps
- ▌ Agent Safety 2 · ultroncoreDetect and block prompt injection, PII/PHI leakage, repo poisoning, and adversarial inputs in LLM agents
- ▌ RAG Pipeline 2 · ultroncoreBuild and optimize RAG pipelines — document ingestion, indexing, retrieval, search backends
- ▌ Output Guardrails 2 · ultroncoreAdd safety validation, output constraints, and content guardrails to Claude Code skill outputs. Use when skill outputs need to be validated against business rules, safety policies, or format constraints before being used. Trigger when users mention guardrails, output validation, safety checks, content filtering, or LLM output constraints.
- ▌ New Website Repo 2 · ultroncoreComplete workflow for spinning up a new client website from the local-service-site-template. Creates a private GitHub repo, copies the template, customises for the client, ensures the "Example User" footer credit is present, runs QA to 100%, and pushes — then updates the auto-push skill table and creates a project memory file.
- ▌ Ubiquitous Language 2 · ultroncoreExtract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
- ▌ Firecrawl Agent 2 · ultroncoreAI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, product listings, directory entries, or any data as JSON with a schema. Triggers on "extract structured data", "get all the products", "pull pricing info", "extract as JSON", or when the user provides a JSON schema for website data. More powerful than simple scraping for multi-page structured extraction.
- ▌ System Builder 2 · ultroncoreUse when the user's request can produce a reusable system, skill, workflow, or execution-ready output — not just an answer. Apply as default operating mode for all non-trivial tasks.
- ▌
- ▌ Firecrawl Scrape 2 · ultroncoreExtract clean markdown from any URL, including JavaScript-rendered SPAs. Use this skill whenever the user provides a URL and wants its content, says "scrape", "grab", "fetch", "pull", "get the page", "extract from this URL", or "read this webpage". Handles JS-rendered pages, multiple concurrent URLs, and returns LLM-optimized markdown. Use this instead of WebFetch for any webpage content extraction.
- ▌ Firecrawl Browser 2 · ultroncoreDEPRECATED — use scrape + interact instead. Interact lets you scrape a page and then click, fill forms, and navigate without managing sessions manually. Use this skill when the user needs to interact with a webpage, log into a site, click buttons, fill forms, navigate multi-step flows, handle pagination, or when regular scraping fails because content requires JavaScript interaction. Triggers on "click", "fill out the form", "log in to", "paginated", "infinite scroll", "interact with the page", or "scrape failed".
- ▌ LLM Observability 2 · ultroncoreAdd observability, tracing, and monitoring to Claude Code skill executions. Track prompt versions, response quality, latency, and costs across runs. Use when building production Claude workflows that need debugging, performance tracking, or A/B testing of prompts. Trigger when users mention LLM observability, langfuse, prompt tracing, agentops, mlflow, or monitoring Claude calls.
- ▌
- ▌ Context Engineer 2 · ultroncoreUse when tasks are complex, multi-step, vague, or involve debugging, building, research with execution, or skill creation — any work where wrong scope, missing inputs, or poor framing would cause drift or incorrect output. Activates automatically before execution.
- ▌ UI Visual Creation Stack 2 · ultroncoreUse when the task involves UI design, UX ideation, web visuals, app screens, mockups, wireframes, landing pages, design systems, component visuals, visual iteration, layout generation, redesigns, style directions, or handoff-ready design workflows. Activates automatically for any visual product work.
- ▌ Temporal Developer 2 · ultroncoreThis skill should be used when the user asks to "create a Temporal workflow", "write a Temporal activity", "debug stuck workflow", "fix non-determinism error", "Temporal Python", "Temporal TypeScript", "Temporal Go", "Temporal Golang", "workflow replay", "activity timeout", "signal workflow", "query workflow", "worker not starting", "activity keeps retrying", "Temporal heartbeat", "continue-as-new", "child workflow", "saga pattern", "workflow versioning", "durable execution", "reliable distributed systems", or mentions Temporal SDK development.
- ▌ Adaptive Codex Utilization 2 · ultroncoreUse when deciding whether to handle a task in Claude or offload it to Codex via terminal. Activates automatically for execution-heavy tasks (terminal commands, file ops, repo scanning, batch edits, test runs, log parsing, env setup, Obsidian vault operations) and when usage efficiency matters. Routes work to the lightest sufficient tool without sacrificing quality.
- ▌ Data Orchestration 2 · ultroncoreRoute data pipeline tasks — ETL, workflow orchestration, stream processing, transformation, ingestion
- ▌ Self Healing Execution 2 · ultroncoreUse when executing code, scripts, automations, configurations, integrations, or system setups — any task where partial or broken results are unacceptable. Activates automatically to ensure work is complete, stable, and verified before stopping.
- ▌ Agent Loop Patterns 2 · ultroncoreDesign patterns for building autonomous agent loops, task queues, and multi-agent crew systems with Claude. Use when building self-directed agents, task decomposition systems, or role-based agent workflows. Trigger when users want autonomous execution, agent loops, task planning, crew-based agents, or self-improving workflows.
- ▌ Vector DB Integration 2 · ultroncoreIntegrate vector databases (Chroma, Qdrant, Weaviate) into Claude Code projects for semantic search and embedding storage. Use when building RAG systems, semantic memory, or similarity search features. Trigger when users mention vector database, embeddings storage, semantic search, Chroma, Qdrant, Weaviate, or similarity retrieval.
- ▌ Multi Repo Push Workflow 2 · ultroncoreManage git push discipline across multiple repos (client site, skill vault, template repo). Defines where each type of work belongs, when to push, QA gates, and quick backup aliases. Configure your repo map once and use everywhere.
- ▌ Cloudflare Pages Autopush 2 · ultroncoreAuto-commit and push any Cloudflare Pages project to GitHub — both on-demand and proactively at session end. Set PROJECT_PATH and REMOTE_REPO once and never think about it again.
- ▌ Env Config Validator 2 · ultroncoreValidate environment configuration files across local, staging, and production environments. Ensure required secrets, database URLs, API keys, and public variables are properly scoped and set. Use this skill when setting up environments, validating configuration, checking for missing secrets, auditing environment variables, ensuring proper scoping of public vs private vars, or troubleshooting environment issues. Trigger terms include env, environment variables, secrets, configuration, .env file, environment validation, missing variables, config check, NEXT_PUBLIC, env vars, database URL, API keys.
- ▌ LLM Routing And Fallback 2 · ultroncoreRoute LLM API calls through cost-efficient proxy layers with automatic model fallback, budget caps, and retry logic. Use when building systems that need to switch between Claude models, fall back from expensive to cheaper models, or unify multiple LLM providers behind one interface. Trigger when users mention litellm, model routing, API cost reduction, model fallback, or budget-aware inference.
- ▌ Adaptive Private Memory Engine 2 · ultroncoreUse when recalling personal context, resuming prior work, looking up project state or preferences, writing to private memory, saving resumable state, or maintaining the memory system. Routes selectively — loads the minimum relevant subset. Never reads all memory. Activates on project names, aliases, "resume", "where were we", style questions, and explicit save/recall requests.
- ▌ Autonomous Knowledge System 2 · ultroncoreUse when executing any task — this is the default operating system. Activates automatically for all tasks to apply autonomous multi-agent execution, pre-task intelligence assessment, and Obsidian-style knowledge capture. Also use explicitly when a task benefits from parallel agents, structured planning, or long-term knowledge storage.
- ▌ Adaptive Private Memory Engine 3 · ultroncoreUse when recalling personal context, resuming prior work, looking up project state, writing to private memory, saving resumable state, or maintaining the memory system. Routes selectively — loads only the memory subset relevant to the current task. Never reads all memory.
- ▌ Adaptive Private Memory Engine 4 · ultroncoreUse when recalling personal context, resuming prior work, looking up project state or preferences, writing to private memory, saving resumable state, or maintaining the memory system. Routes selectively — loads the minimum relevant subset. Never reads all memory. Activates on project names, aliases, "resume", "where were we", style questions, and explicit save/recall requests.
- ▌ API Contracts And Zod Validation 2 · ultroncoreGenerate Zod schemas and TypeScript types for forms, API routes, and Server Actions with runtime validation. Use this skill when creating API contracts, validating request/response payloads, generating form schemas, adding input validation to Server Actions or route handlers, or ensuring type safety across client-server boundaries. Trigger terms include zod, schema, validation, API contract, form validation, type inference, runtime validation, parse, safeParse, input validation, request validation, Server Action validation.
- ▌ Agent Native Automation Research Install 2 · ultroncoreUse when installing CLI-Anything for Claude Code, managing Claude Code plugin marketplaces, researching or installing n8n community nodes, or processing screenshots of automation tools, repos, commands, or agent-native software ecosystems. Handles research, validation, install, and documentation in one pass.
- ▌
- ▌ Mutation Testing · ultroncore bundleConfigure and run mutation testing to evaluate test suite quality, revealing gaps in coverage and security-critical logic verification.
- ▌ Security Scanner · ultroncore bundleRoute security scanning tasks to the right tool — containers, secrets, SAST, SBOM, web apps
- ▌ Ada Wcag Compliance · ultroncore bundleFull ADA / WCAG 2.2 AA compliance skill for static HTML + Tailwind sites. Synthesized from 5 real GitHub accessibility repos (web-a11y-plugin, Heydon/inclusive-design-checklist, pa11y, wai-wcag-quickref, html2canvas). Covers semantic markup, contrast, focus, keyboard nav, ARIA, alt text, forms, motion, robots.txt / llms.txt / sitemap, and the accessibility statement page.
- ▌ D3 Viz · ultroncore bundleCreating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.
- ▌ Swiftui UI Patterns · ultroncore bundleBest practices and example-driven guidance for building SwiftUI views and components, including navigation hierarchies, custom view modifiers, and responsive layouts with stacks and grids. Use when creating or refactoring SwiftUI UI, designing tab architecture with TabView, composing screens with VStack/HStack, managing @State or @Binding, building declarative iOS interfaces, or needing component-specific patterns and examples.
- ▌ Huggingface Datasets · ultroncore bundleUse this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
- ▌ LLM Prompt Optimizer · ultroncore bundleUse when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and cut token usage.
- ▌ Vector DB Production · ultroncoreDeploy and operate vector databases in production — Qdrant, Pinecone, Weaviate, and pgvector. Covers HNSW index tuning, replication, sharding, monitoring query latency, filtering strategies, batch upserts, and disaster recovery for embedding-heavy workloads.
- ▌ Claude API · ultroncore bundleBuild apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
- ▌ Keyboard Maestro · ultroncore bundleCreate and manage Keyboard Maestro macros via CLI and KM's macro XML format. Triggers on: Keyboard Maestro, kmtrigger, KMVAR_, macro trigger, Keyboard Maestro Engine, kmmacros.
- ▌ Prisma Patterns · ultroncore bundlePrisma ORM advanced patterns: schema design, migrations, relation queries, transactions, and performance. Triggers on: Prisma, prisma.client, PrismaClient, schema.prisma, prisma migrate, include, select, createMany, transaction.
- ▌ API Gateway Design · ultroncoreDesign and implement API gateways for microservices. Covers Kong, AWS API Gateway, custom gateway with Node.js, authentication/authorization, rate limiting, request transformation, load balancing, and observability.
- ▌ Mockery Go Mocking · ultroncoreGenerate type-safe interface mocks for Go tests with Mockery — no hand-written boilerplate, full testify integration
- ▌ Websocket Realtime · ultroncoreReal-time features with WebSockets, Server-Sent Events, and Supabase Realtime. Triggers on: WebSocket, socket.io, SSE, ReadableStream, Supabase Realtime, .on('INSERT'), channel.subscribe, EventSource.
- ▌ Invoice Organizer · ultroncore bundleAutomatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.
- ▌ Docker Expert · ultroncore bundleYou are an advanced Docker containerization expert with comprehensive, practical knowledge of container optimization, security hardening, multi-stage builds, orchestration patterns, and production deployment strategies based on current industry best practices.
- ▌ Senior Devops · ultroncore bundleComprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup, infrastructure as code, deployment automation, and monitoring. Use when setting up pipelines, deploying applications, managing infrastructure, implementing monitoring, or optimizing deployment processes.
- ▌ Risk Management Specialist · ultroncore bundleMedical device risk management specialist implementing ISO 14971 throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production information analysis. Use when user mentions risk management, ISO 14971, risk analysis, FMEA, fault tree analysis, hazard identification, risk control, risk matrix, benefit-risk analysis, residual risk, risk acceptability, or post-market risk.
- ▌ Soc2 Compliance · ultroncore bundleUse when the user asks to prepare for SOC 2 audits, map Trust Service Criteria, build control matrices, collect audit evidence, perform gap analysis, or assess SOC 2 Type I vs Type II readiness.
- ▌ Zod Expert · ultroncore bundleZod v3 schema validation: complex schemas, transformations, refinements, and TypeScript type inference. Triggers on: z.object, z.string, z.number, zod, ZodSchema, z.infer, .parse(), .safeParse(), z.union, z.discriminatedUnion.
- ▌ Devbox Environments · ultroncoreCreate isolated, reproducible development environments using Devbox (Nix-backed) without Docker overhead
- ▌ Private Repo Backup · ultroncoreAuto-backup skill for the Example Client Site private production repo and the Claude Skill Vault. Defines where all client work, new skills, and reusable templates must be committed and pushed.
- ▌
- ▌ Deep Research · ultroncore bundleThis skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API. It automates prompt enhancement through interactive clarifying questions, saves research parameters, and executes deep research with web search capabilities. Use when the user asks for in-depth analysis, investigation, research summaries, or topic exploration.
- ▌ Firecrawl Map · ultroncore bundleDiscover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where something is on a domain, or says "map the site", "find the URL for", "what pages are on", or "list all pages". Essential when the user knows which site but not which exact page.
- ▌ IOS Architecture · ultroncore bundleiOS app architecture expert skill covering MVVM with @Observable, Clean Architecture, The Composable Architecture (TCA), modular architecture with SPM, Repository pattern, Coordinator/Router pattern, Dependency Injection (Factory, Environment), error handling patterns, and protocol-oriented programming. Use this skill when the user architects an iOS app, designs feature modules, sets up project structure, implements MVVM/Clean/TCA patterns, creates repositories or use cases, or asks about iOS code organization. Triggers on: architecture, MVVM, clean architecture, TCA, composable architecture, repository pattern, coordinator, dependency injection, DI, view model, use case, interactor, modular, SPM package, feature module, project structure, folder structure, app architecture, design pattern, unidirectional data flow, reducer, store, or any iOS app structure discussion.
- ▌ Swiftdata Expert · ultroncore bundleSwiftData model persistence, relationships, migrations, and CloudKit sync for iOS 17+. Triggers on: SwiftData, @Model, ModelContainer, ModelContext, @Query, SwiftData schema, migration, SchemaMigrationPlan.
- ▌ Churn Prevention · ultroncore bundleWhen the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers or wants to build systems to prevent it. For post-cancel win-back email sequences, see email-sequence. For in-app upgrade paywalls, see paywall-upgrade-cro.
- ▌ Content Strategy · ultroncore bundleWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," "content planning," "editorial calendar," "content marketing," "content roadmap," "what content should I create," "blog topics," "content pillars," or "I don't know what to write." Use this whenever someone needs help deciding what content to produce, not just writing it. For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit. For social media content specifically, see social-content.
- ▌ Growth Marketing · ultroncoreFull growth marketing toolkit — ad copy and creative, paid campaigns, social content, product launches, email sequences, lead magnets, referral programs, and competitor SEO pages.
- ▌ Pricing Strategy · ultroncore bundleWhen the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' 'monetization,' 'how much should I charge,' 'my pricing is wrong,' 'pricing page,' 'annual vs monthly,' 'per seat pricing,' or 'should I offer a free plan.' Use this whenever someone is figuring out what to charge or how to structure their plans. For in-app upgrade screens, see paywall-upgrade-cro.
- ▌ Programmatic SEO · ultroncore bundleWhen the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pages," "[keyword] + [city] pages," "comparison pages," "integration pages," "building many pages for SEO," "pSEO," "generate 100 pages," "data-driven pages," or "templated landing pages." Use this whenever someone wants to create many similar pages targeting different keywords or locations. For auditing existing SEO issues, see seo-audit. For content strategy planning, see content-strategy.
- ▌ Referral Program · ultroncore bundleWhen the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' 'partner program,' 'referral incentive,' 'how to get referrals,' 'customers referring customers,' or 'affiliate payout.' Use this whenever someone wants existing users or partners to bring in new customers. For launch-specific virality, see launch-strategy.
- ▌ Sales Enablement · ultroncore bundleWhen the user wants to create sales collateral, pitch decks, one-pagers, objection handling docs, or demo scripts. Also use when the user mentions 'sales deck,' 'pitch deck,' 'one-pager,' 'leave-behind,' 'objection handling,' 'deal-specific ROI analysis,' 'demo script,' 'talk track,' 'sales playbook,' 'proposal template,' 'buyer persona card,' 'help my sales team,' 'sales materials,' or 'what should I give my sales reps.' Use this for any document or asset that helps a sales team close deals. For competitor comparison pages and battle cards, see competitor-alternatives. For marketing website copy, see copywriting. For cold outreach emails, see cold-email.
- ▌ Agent Safety · ultroncore bundleDetect and block prompt injection, PII/PHI leakage, repo poisoning, and adversarial inputs in LLM agents
- ▌ RAG Pipeline · ultroncore bundleBuild and optimize RAG pipelines — document ingestion, indexing, retrieval, search backends
- ▌ Brainstorming · ultroncoreYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
- ▌ Writing Plans · ultroncoreUse when you have a spec or requirements for a multi-step task, before touching code
- ▌ Vault Push Guardian · ultroncore bundlePre-push safety review and smart sync for Skill Vault (UltronCore/claude-skill-vault) and Project Vault (UltronCore/claude-project-vault). Runs automatically before any push to either vault repo. Also invoke when the user says "sync the vaults", "push vaults", "vault review", "weekly vault push", "check vaults", or "vault maintenance". Scans for secrets, credentials, personal info, and memory violations before allowing a push. Runs silently unless a blocking issue is found. Manages usage-threshold and weekly push scheduling automatically.
- ▌
- ▌ Output Guardrails · ultroncore bundleAdd safety validation, output constraints, and content guardrails to Claude Code skill outputs. Use when skill outputs need to be validated against business rules, safety policies, or format constraints before being used. Trigger when users mention guardrails, output validation, safety checks, content filtering, or LLM output constraints.
- ▌ Vercel React Best Practices · ultroncore bundleReact and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
- ▌ React Query Tanstack · ultroncore bundleTanStack Query v5 for server state management: queries, mutations, invalidation, optimistic updates, and infinite queries. Triggers on: useQuery, useMutation, QueryClient, invalidateQueries, TanStack Query, React Query, @tanstack/react-query.
- ▌ Swiftui Liquid Glass · ultroncore bundleImplement, review, or improve SwiftUI features using the iOS 26+ Liquid Glass API. Use when asked to adopt Liquid Glass in new SwiftUI UI, refactor an existing feature to Liquid Glass, or review Liquid Glass usage for correctness, performance, and design alignment.
- ▌
- ▌ Structured Generation · ultroncoreExtract structured data from LLMs using JSON mode, function calling, constrained decoding (outlines, guidance), and validation. Covers OpenAI, Anthropic, and local model approaches.
- ▌ Agents Md · ultroncore bundleCreates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update AGENTS.md, maintain agent docs, set up CLAUDE.md, document repository agent conventions, or keep coding-agent instructions minimal and reference-backed.
- ▌ New Website Repo · ultroncore bundleComplete workflow for spinning up a new client website from the local-service-site-template. Creates a private GitHub repo, copies the template, customises for the client, ensures the "Example User" footer credit is present, runs QA to 100%, and pushes — then updates the auto-push skill table and creates a project memory file.
- ▌ Ecommerce Patterns · ultroncore bundleE-commerce implementation patterns: product catalog, cart state, checkout flow, inventory, and order management. Triggers on: shopping cart, checkout, product catalog, inventory, add to cart, order management, ecommerce.
- ▌ Free Tool Strategy · ultroncoreWhen the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," "free resource," "ROI calculator," "grader tool," "audit tool," "should I build a free tool," or "tools for lead gen." Use this whenever someone wants to build something useful and give it away to attract leads or earn links. For downloadable content lead magnets (ebooks, checklists, templates), see lead-magnets.
- ▌ Delta Lake · ultroncoreBuild reliable data lakes with Delta Lake — an open-source storage layer that brings ACID transactions, scalable metadata handling, and time travel to Apache Spark and other engines. Use this skill whenever the user mentions Delta Lake, Delta tables, ACID transactions on a data lake, or wants reliable streaming + batch on the same dataset. Trigger for "delta lake", "delta table", "deltalake python", "delta format", or "databricks delta".
- ▌ Database Design · ultroncore bundleDatabase design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.
- ▌ XLSX · ultroncore bundleComprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
- ▌ Mise Runtime Manager · ultroncoreManage polyglot runtime versions with mise (formerly rtx), a fast drop-in replacement for asdf
- ▌
- ▌ Nextjs Performance · ultroncoreOptimize Next.js applications for Core Web Vitals, bundle size, and runtime performance. Covers Image optimization, font loading, dynamic imports, Partial Prerendering, React Server Components, caching strategies, and measuring with Lighthouse and Vercel Analytics.
- ▌ App Store Connect · ultroncore bundleApp Store submission, TestFlight distribution, App Store Connect API automation, and release management workflows. Triggers on: App Store Connect, TestFlight, archive, upload, App Store review, ASC API, altool, xcrun notarytool, xcodebuild archive, fastlane deliver.
- ▌ Swiftui Data Flow · ultroncoreMaster SwiftUI data flow patterns — @State, @Binding, @ObservableObject, @EnvironmentObject, the Observation framework (@Observable), and reactive UI updates. Covers ownership rules, performance optimization, and migration from ObservableObject to Observable.
- ▌ Site Architecture · ultroncore bundleWhen the user wants to plan, map, or restructure their website's page hierarchy, navigation, URL structure, or internal linking. Also use when the user mentions "sitemap," "site map," "visual sitemap," "site structure," "page hierarchy," "information architecture," "IA," "navigation design," "URL structure," "breadcrumbs," "internal linking strategy," "website planning," "what pages do I need," "how should I organize my site," or "site navigation." Use this whenever someone is planning what pages a website should have and how they connect. NOT for XML sitemaps (that's technical SEO — see seo-audit). For SEO audits, see seo-audit. For structured data, see schema-markup.