Plugin Claude Code
Say what you want to build in one sentence. Fifteen superforge skills take it from idea to release gate with model tiering and file persistence, plus five Claude Code workflows that enforce the parts prose cannot.
Skill Claude CodeCodex
Audit and fix accessibility against WCAG 2.2, ARIA, Apple, and Material guidance — a seven-pass run (automated, keyboard, screen reader, zoom and reflow, colour, motion and time, forms and errors) that produces a criterion-by-criterion verdict instead of a scanner dump. Covers Web, iOS, and Android, and the legal…
Skill Claude CodeCodex
Decide whether a market is worth entering, then architect the business model on top of it. Opens with a GO/NO-GO gate: TAM/SAM/SOM computed both ways, confidence tiers on every input, and the reverse calculation asking how many customers this needs and whether you can reach that many. Then monetization archetype…
Skill Claude CodeCodex
Run the BreakBias engine — an exhaustive, machine-checkable idea sweep — or, when the stakes don't call for it, a lighter classic method (SCAMPER, Six Hats, Crazy 8s, How Might We). For a full sweep: decompose the problem across five lenses, name the hidden bias on every element, ban the obvious three, then push each…
Skill Claude CodeCodex
Define brand identity systems (naming, tone, visual tokens, VVA Matrix coordinates) and produce AI-generated visual and motion assets through prompt engineering for generateimage, Kie.ai, and Higgsfield — with the generation cost, the consistency recipe that makes a twelfth image match the first, and commercial…
Skill Claude CodeCodex
Root-cause-first debugging with FailForward learning memory, which recalls past failures before diagnosing and records new ones after, in a committed docs/failforward.md that survives the session. Forbids trial-and-error patching and dummy fallbacks that mask symptoms. Covers the bugs the protocol cannot start on …
Skill Claude CodeCodex
Build multi-component features by decomposing the work and dispatching subagents, assigning a model tier per subtask. Splits work into tasks with one outcome, a proof line, and a listed set of files — so parallel safety is decidable rather than hoped for — and proposes Subagents versus Agent Teams versus a scripted…
Skill Claude CodeCodex
Write the session state to a structured capsule in .handoff/ so any AI model or tool (Claude Code, Codex, Gemini CLI, Antigravity, Cursor) can resume the work with zero context loss. Use before clearing a long thread or switching tools. Also packages work for an async cloud agent such as Devin — deciding whether a…
Skill Claude CodeCodex
Deliver an unsparing, compliment-free critique of a design, PRD, plan, architecture, copy, or UI to expose flaws before they ship. Strips AI politeness and names the weakest point first. Use when the user says "roast", "be brutal", "tear this apart", "what's wrong with", "honest feedback", "critique", "poke holes"…
Skill Claude CodeCodex
Build a scroll-scrubbed cinematic landing page where scroll drives a camera continuously through a generated world, with no cuts between scenes. Plans the camera before generating anything — floor plan or world map, room adjacency, a shot list with camera position, heading, lens and eye height per leg, a seam…
Skill Claude CodeCodex
Security review for products built by small teams — seven passes (secrets, authentication, authorization, input handling, data at rest and in transit, dependencies, exposed surface) producing a finding-by-finding ledger instead of a scanner dump. Ranks by what an attacker actually gets, not by a generic score. Covers…
Skill Claude CodeCodex
Decide whether a product may be released, a different question from whether it works. Runs the release gate: which legal obligations the product's own data handling triggered and where a lawyer becomes mandatory, what will actually get it rejected from the App Store or Google Play, the measurement that must exist…
Skill Claude CodeCodex
Decide what earns a test, then drive implementation through Red-Green-Refactor TDD across Web (Jest, Vitest, Playwright), iOS (Swift Testing, XCTest), and Android (JUnit, Compose Test), verifying each red and green state by actually running the suite. Covers test granularity (unit / integration / E2E), where the…
Skill Claude CodeCodex
Design and build interfaces across Web, iOS (SwiftUI), and Android (Jetpack Compose), covering layout, visual hierarchy, typography, responsive behaviour, state specification, and micro-interactions. Opens by sourcing the visual direction from references or a design made in another tool, and extracting the system…
Skill Claude CodeCodex
Gate that blocks any completion claim until there is empirical runtime evidence — the test suite actually run, both mobile and desktop viewports checked, and native iOS or Android simulator runs confirmed. Grades every piece of evidence (reproducible / observed / derived / asserted) and forbids a report that rests on…
Skill Claude CodeCodex
Concierge and router for the whole making process, from idea to shipped product. Reads intent, hands the work to the right superforge- skill (brain, biz, brand, ui, dev, test, debug, roast, verify, handoff), and assigns a model tier per subtask before any agent is dispatched, applying per-model prompting deltas. Also…