Coding & Development

Verification stage of Full-Stack WP Developer. Runs the mechanical gate for plugins and themes (house-rule scripts, PHP lint, PHPCS with WordPress standards, PHP compatibility, PHPStan with WordPress stubs), the manual checklist, PRD or change-brief scenario tests, and the pre-release check. Reports PASS, FAIL, or NOT RUN and never implies a skipped check passed. Invoked by fswp-developer after a build and again before delivery; consult directly to audit any plugin or theme folder.

Builds an offer too good to refuse. Lists every problem the buyer hits on the way to the result they want, turns each into a solution, trims to what is cheap to deliver and valuable to the buyer, and stacks it with honest bonuses, a guarantee the CFO can afford, real urgency and a clear name. Scores it on the value equation (outcome, likelihood, time, effort) and re-tests it on a quick buyer panel. Use when the user says "make my offer better", "why won't people buy", "what should I include", "guarantee", "bonuses", "grand slam offer", or after the panel shows people passing.

Run a deliberate teaching session that makes the human deeply understand a specific piece of code — usually code an agent just wrote, an unfamiliar module, or a diff they're about to approve. Trigger when the human explicitly asks to be taught or walked through something for understanding: "teach me this", "make me understand this before I approve/commit", "walk me through what just got written". Also trigger when the human accepts an offer to walk through a change before approving it. Use this even when phrased casually, as long as the intent is comprehension rather than just getting an answer. Do NOT trigger for routine coding help, quick "how do I / what does this" lookups, or ambiently on every question — this is a mode the human steps into on purpose.

Domain skill for WordPress REST API and Abilities API work in Full-Stack WP Developer. Covers registering routes with schemas, argument validation and sanitization, permission callbacks, controller classes, exposing post types and meta, authentication (cookie nonce, application passwords), pagination and errors, and registering abilities with input and output schemas and safety annotations. Use for any custom endpoint or machine-readable capability in a plugin or theme.

Build a SaaS renewal negotiation brief from user-supplied invoices, usage stats, and contract excerpts. Use when the user faces a renewal, wants leverage points, alternative cost ranges, must-have clauses, or a walk-away line. Always states this is not legal advice.

Create and maintain a per-project Asset List (models, textures, sprites, audio, fonts, shaders, images, icons, vendored libraries, datasets) with source, license, credit, status and verification for each asset. Use when adding, replacing, renaming, removing or auditing project assets, when the user asks for an asset list, asset inventory, credits or license check, or before shipping. Safe for several AI agents, Git branches and worktrees. Works for games, VR/XR, web apps and general software.

Your CFO. Builds the unit economics of a business before money is spent: what one unit earns after its direct costs, the real profit margin at the planned volume, the break-even point in units a day, year 1 month by month, the cash needed before it pays for itself, how long the startup spend takes to earn back, and what happens if the price drops, sales come in low or costs rise. Every number traces to an input the user can check. Use when the user says "find the profit margins", "do the numbers", "is this profitable", "break-even", "unit economics", "how much do I need to start", or "run the CFO".

Matches how much you build and how much caution you take to what a change can actually break, instead of doing whatever looks diligent. Always consult it BEFORE running any command or writing any code that touches production or shared state — a database migration, dropping or altering a table, a bulk delete or update, a deploy, a force-push, rotating secrets — and before changing anything others depend on: a public API or GraphQL schema, a function signature, a CLI flag, a response shape. Also use it when sizing effort (how many tests, comments, or abstractions a change deserves), when choosing between upgrading a dependency and vendoring a custom patch, and when a small fix is tempting to expand into a bigger one. Use it even when the request sounds routine or says "just do it" — the failure mode is acting on a destructive or breaking request without pausing, while over-building trivial code and under-protecting risky changes. Defers to the `right-sized-code` skill for how much to build.

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.

Your board of directors, built to disagree with you. Puts a business idea in front of a four-member board, each a sub-agent reading the idea through one published framework: the Offers lens (from Alex Hormozi's $100M Offers), the Monopoly lens (from Peter Thiel's Zero to One), the Product lens (from Walter Isaacson's biography of Steve Jobs) and the Evidence lens (from Rob Fitzpatrick's The Mom Test), which scores only what real people have done. Each member scores the idea, names what would kill it and the cheapest test that would prove it, and votes fund, fund with conditions, or pass. Use when the user says "test my business idea", "would this work", "pressure-test this", "what would a board say", "is this a good business", or starts the Shark Tank Proof pack on a new idea.

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.

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.

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.

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".

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".

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.

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.

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。

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.

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".

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.

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.