Coding & Development

Generates print-ready A5 Filofax binder coin collection checklists as PDF. ALWAYS activate when the user asks for a printable coin checklist, binder insert, coin collection PDF, A5 coin list, or anything combining "coin" + "print" / "binder" / "checklist" / "PDF". Also activate when iterating on an existing coin checklist PDF — reformatting, adding series, fixing layout. This skill encodes hard-won formatting rules for ReportLab on A5 paper with 6-hole punch margins, grayscale laser printing, and Carlito (Calibri-equivalent) font.

Domain skill for WordPress block editor work in Full-Stack WP Developer. Covers building custom Gutenberg blocks (block.json, static and dynamic rendering, attributes, supports, InnerBlocks, variations, deprecations, block bindings), block patterns, and the Interactivity API (data-wp directives, stores, server-side state), with the @wordpress/scripts build workflow. Use for any custom block, pattern, or front-end interactivity in a plugin or theme.

Crea presentaciones por escenas que cambian en cada paso, al estilo de un explicador visual. A la izquierda va una tarjeta de pasos; a la derecha, una ilustración animada con los objetos del mundo del tema (un tablero, una consola, un documento, un instrumento o una maqueta 3D) o una captura o foto que se acerca y se rotula. Cada presentación tiene una identidad visual propia (paleta, tipografías y piel CSS) diseñada para su tema. El resultado es un único archivo HTML con notas, vista general, pantalla completa, modo edición y exportación a PDF. Úsala cuando la persona pida una presentación, exposición, diapositivas, slides, un explicador visual o "Cerulean" sobre un tema, sobre todo si quiere ilustraciones, animaciones o mostrar capturas de su aplicación. No la uses si pide expresamente un PowerPoint (.pptx), Google Slides o un documento.

Checklist to run before publishing any number, chart or comparison built from public data (official statistics, public contracts, budgets, council records). Catches mismatched years, wrong units, contracts mistaken for spending, small samples, duplicated entities and licence problems. Use whenever an answer or product cites open data. Verificação de dados públicos antes de responder ou publicar.

Research methodology for building complete coin series checklists from a Numista CSV export. ALWAYS activate when the user asks to cross-reference their collection against a series, find gaps in their collection, plan which coins to collect next, suggest new series to pursue, or analyze a Numista export file. Also activate for coin fair shopping lists or series completion planning. This skill covers the full pipeline from CSV parsing through series research to gap analysis and priority ranking.

Use when a page needs an explanatory diagram (process, timeline, flow, structure, before/after) as an SVG React component that draws itself as it scrolls into view, in a minimalist ink-and-grey style, for a Next.js or React site. Also when asked for a "diagramme animé", "schéma qui se dessine".

Teaches current Vitest 5 practices drawn from the official documentation. Use when writing, reviewing or fixing Vitest tests (test, describe, expect, test.for, fixtures with test.extend, hooks, snapshots), mocking with vi (vi.fn, vi.spyOn, vi.mock, vi.when, fake timers, stubGlobal, stubEnv), configuring vitest.config or projects, choosing an environment or pool, filtering and running tests in CI, measuring coverage with v8 or istanbul, debugging slow or flaky suites, testing components in browser mode with Playwright, or migrating from Jest, Mocha or Vitest 4. Triggers on vitest, vi.mock, vi.fn, vitest.config, toMatchSnapshot, expect.poll, coverage thresholds, browser mode, @vitest/browser-playwright, jsdom, happy-dom, migrate Jest to Vitest, upgrade Vitest 5.

Make a Fringe Lines vertical short in the "editorial" style (paper background, speaker that morphs between full-bleed / card / round PiP, explainer graphics, word-by-word serif captions, hook + end card, SFX). Use when asked to make, restyle or fix a short from an episode.

The consumer panel. Spins up a swarm of buyer sub-agents (default 100, --quick for 20) trained on the user's target customer, each with a different income, age, buying behaviour and objection, shows every one the same pitch, and runs the business through 100 buyer scenarios to see who buys, who doesn't, and why. Tallies the answers into buy rates by segment, the reasons people pass in their own words, what would flip a no, and price answers for litmus. Every result is labelled SIMULATED: it finds objections and the questions to ask real buyers, and never counts as demand. Use when the user says "would people buy this", "test it on customers", "run the consumer panel", "simulate buyers", "who is my customer", or "validate demand".

Organize and run matters for a New Jersey business-law practice — open a new matter from intake notes (with NJ ethics checks — conflicts, entity-as-client, written fee terms), pick the right NJ forum (Special Civil Part, Law Division, Complex Business Litigation Program, Chancery General Equity, D.N.J.), build matter summaries and phased task plans for business sales, entity formation, contract disputes, and owner disputes, keep sourced chronologies, review the caseload by urgency, and draft client status updates. Use this skill whenever an attorney or paralegal mentions a new client or matter, intake, conflicts, "where are we on the X matter", next steps, a closing checklist, a case timeline, a docket/caseload review, a matter tracker, or wants emails, notes, or documents turned into an organized matter file — even if they don't say "case management".

Primus-Turbo handoff to the autonomous kernel-optimize loop — collect the prerequisites (kernel path, focused test/bench commands, scoring metric, execution mode, quick-validation harness) a kernel campaign needs and pass them on. Use when pushing a Primus-Turbo kernel toward the hardware limit, not just spot-checking perf.

Timekeeper and scribe for the user's own timeboxed build session, default 90 min, also 1h / 1.5h / 2h (Orient, Build, Verify, Harden, Close, scaled to the block). Use when the user says "start a session", "deep work", "90 min block", "work block", or invokes /deep-work. Subcommands: status, park <note>, close, abort.

把故事、小说、剧本、大纲或人物设定转成可直接投喂 MiniMax H3（Ref2VA / R2V 参考工作流 + MiniMaxH3AddGuide 接段）的分镜与视频提示词交付文件，包含分段、资产表与生图提示词、连接清单、六段提示词和质检。只要用户给出叙事文本并想“做成视频 / 出分镜 / 出提示词”，或提到 H3、Ref2VA、R2V、ComfyUI 视频、AddGuide、接段、尾帧引导、资产图、镜头表，就使用本 skill，即使没有明确说“提示词”或“skill”；单段多镜、跨段接段、中文正文全部由本 skill 负责。

Gives current guidance from the official Rust standard library docs (std 1.99.1 stable) on pitfalls, panics, platform differences, discouraged APIs and newer stable replacements. Use when writing, reviewing or refactoring Rust code that uses std, especially collections (Vec, HashMap, BTreeMap, BinaryHeap, entry, extract_if, sort), Option/Result/error handling (expect, ?, Error, ExitCode, panic), iterators (collect, flatten, Peekable, try_fold), Box/Rc/RefCell/Cow/Pin/mem::take, Arc/Mutex/RwLock/OnceLock/LazyLock/thread::scope/mpsc/Condvar/atomics, String/str/fmt/format!/OsString/CString, io/fs/path (BufWriter, OpenOptions, PathBuf::join), process/env/net/time (Command, set_var, TcpStream, Instant, Duration), From/TryFrom/AsRef/Ord/Drop/Deref/Clone, and unsafe raw pointers, MaybeUninit, transmute, NonNull or integer overflow and float ordering.

Gives current guidance from the official tokio documentation (tokio 1.54.1) on async Rust pitfalls, cancel safety, blocking code, surprising defaults and deprecated APIs. Use when writing, reviewing or debugging async Rust code that uses tokio, especially the runtime (#[tokio::main], #[tokio::test], Builder, enable_all, block_on, current_thread, LocalRuntime, shutdown, feature flags), tasks (spawn, JoinHandle, JoinSet, abort, spawn_blocking, block_in_place, LocalSet, spawn_local, task_local), select!, join!, try_join!, cancellation and graceful shutdown, sync primitives (Mutex across .await, RwLock, Semaphore, Notify, OnceCell), channels (mpsc backpressure, oneshot, broadcast lag, watch), time (sleep, interval, MissedTickBehavior, timeout, paused time, start_paused), I/O and networking (AsyncReadExt, BufWriter flush, split, io::copy, framing, TcpListener, TcpStream, UdpSocket), tokio::fs, process (Command, kill_on_drop, Child), signals (ctrl_c, Windows console events) and Windows named pipes.

Generate a customer "Technical Impact Presentation" (TIP / POV / POV-summary deck) from a Dynatrace PowerPoint template plus an optional example deck and a success-criteria table, populated with LIVE tenant data pulled via dtctl, with deep-links to specific tenant views where screenshots should be pasted. Runs MANDATORY dtctl + Dynatrace MCP preflight validation, auto-detects dark vs light slide layouts to prevent invisible text, and finishes with a visibility/link/brand QA pass. Use when someone asks to build a "Technical Impact Presentation", "TIP deck", "POV summary", "technical impact review", or "impact deck for <customer>". Requires dtctl authenticated to the customer's Gen3 tenant and (recommended) the Dynatrace MCP server connected.

Planning stage of Full-Stack WP Developer. Classifies the work (new plugin, new theme, update to an existing plugin or theme, add-on for another product, or WordPress Core patch), triages existing code with a bundled detection script, asks one round of essential questions, does competitive research, and produces one reviewable PRD or change brief with a single approval gate. Also covers Migration mode and multi-session handoff docs. Invoked by fswp-developer before any code is written; consult directly for PRD, change-brief, or handoff-doc questions.

Review, mark up, and summarize business contracts for a New Jersey business-law practice — identify risky or missing clauses, apply NJ law overlays (Atalese arbitration waivers, bulk-sale notice in asset purchases, non-compete reasonableness, LAD/NDA limits, Franchise Practices Act, Consumer Fraud Act/TCCWNA), rate each issue, propose replacement language, and produce a client-ready review memo or issues list. Use this skill whenever a user shares or pastes an agreement (asset or equity purchase, operating/shareholder agreement, NDA, MSA, services, SaaS/license, employment or contractor, commercial lease, distribution/franchise, loan/guaranty, settlement, amendment) and wants it reviewed, redlined, compared to a playbook, summarized, negotiated, or checked for problems — even if they only say "can you look at this contract", "anything I should worry about here?", or "what does this clause mean".

Use antes de criar, entrar ou remover um git worktree (git worktree add, EnterWorktree, subagente com isolation "worktree", worktree pedido por outra skill) e quando o usuário quiser listar os worktrees abertos ou saber quais pode apagar. Apresenta o plano e espera aprovação antes de criar, gera um relatório com veredito por worktree e propõe a limpeza ao final da tarefa.

Build and open bibliometric network visualizations in VOSviewer (desktop or VOSviewer Online) from bibliographic data. Use this skill whenever the user wants to visualize co-authorship, co-citation, keyword co-occurrence, bibliographic coupling, or term maps from PubMed, Crossref, Scopus, Web of Science, RIS exports, NotebookLM sources, or any list of papers. Also trigger on phrases like "mapa bibliométrico", "rede de coautoria", "análise bibliométrica", "VOSviewer", "co-citation", "term map", "keyword map".

Desplegar una app Node (con dependencias nativas o Chromium) en un servidor Docker que ya aloja otras aplicaciones, sin tumbar nada ajeno. Cubre: liberar disco antes de construir, límites de memoria por servicio, healthcheck solo en servicios HTTP, versión de módulos nativos según el Node, publicar detrás de un Caddy compartido con basic auth, y validar/reload del proxy sin downtime. Usar cuando se despliega sobre un servidor existente con otros stacks corriendo, cuando el build falla por espacio en disco, cuando un módulo nativo aborta el proceso, o cuando hay que exponer un servicio nuevo por el proxy que ya existe.

Build or change Gutenberg blocks in the Nextora parent theme or a Nextora child theme — block.json registration, typed attributes, native visual editing with RichText and media, InspectorControls settings panels, repeatable list editors with modal item editing, render.php output, view scripts, block style variations, and the esbuild block pipeline. Use when a request mentions a block, block.json, edit.tsx, index.tsx, render.php, ServerSideRender, InnerBlocks, a repeater or list editor, a modal item form, an inspector panel, a block category, or "add/restyle a section block" for Nextora.

Teaches current next-intl 4 practices for internationalizing Next.js apps, drawn from the official documentation. Use when setting up next-intl with the App Router, writing i18n/request.ts, adding a [locale] segment with defineRouting, createMiddleware in proxy.ts (formerly middleware.ts), building locale switchers with createNavigation, translating with useTranslations or getTranslations, passing messages to NextIntlClientProvider, writing ICU messages (plurals, select, rich text), formatting dates, numbers and lists with useFormatter, translating metadata, Server Actions, Route Handlers, localized 404 and error pages, static rendering with next/root-params, type-safe messages through AppConfig, testing with Jest, Vitest, Storybook, or extracting inline messages with useExtracted. Triggers on next-intl, useTranslations, getTranslations, NextIntlClientProvider, getRequestConfig, i18n routing, locale prefix, localePrefix, NEXT_LOCALE, hreflang, setRequestLocale, ICU messages, App Router internationalization.

Turns a vague project idea into a verifiable Definition of Done (GOAL.md) before any code is written, amends it when scope changes, and checks whether the project meets it. Use at project kickoff ("I want to build…", "new project", "help me scope this"), when goals or scope change ("we're dropping X", "add Y to the scope", "change the requirements"), or when asked whether the project is done ("are we done?", "does this meet the goal?", "verify against GOAL.md").