Web & Frontend

tmforum-oda Skill

Given a TM Forum ODA component (TMFCxxx) or Open API (TMFxxx) id and a proposed change (deprecation, breaking version bump, removal), lists every TMFSxxx use case that depends on it, describes specifically how each one uses it, and drafts a maturity-weighted migration/impact report. Use this before deprecating, breaking, or removing a component or API.

tmforum-oda Bundle

⚠ Builds & deploys — the one skill in this plugin with real side effects (builds/pushes Docker images, can `helm install`). Build a complete TM Forum ODA Component implementation from scratch, including Node.js microservice source code, Dockerfiles, and Kubernetes Helm charts. Use this skill whenever the user wants to: - Create, build, scaffold, implement, or generate an ODA Component - Build an implementation for a standard TMForum component (TMFC001 through TMFC062) - Generate source code and/or Helm charts following the ODA Component standard - Ask "how do I build TMFC006?" or "I want to implement Service Catalog Management" Invoke whenever you see: "create ODA component", "build TMForum component", "scaffold TMFC", "implement ODA", "new ODA component", or any mention of TMFCxxx component codes. For a lightweight, language-agnostic scaffold with no side effects instead of this full opinionated Node.js/Helm stack, see generate-implementation-scaffold-from-usecase.

tmforum-oda Skill

Given a TMFCxxx component id, processes every image in its knowledge/components/{ID}/media/ folder in turn -- classifies it, renames it descriptively, reverse-engineers structured diagrams (the component architecture overview, eTOM-SID ABE link diagrams, API/Resource/Operation diagrams) into PlantUML .puml files, and writes a text-description.md for everything else -- updating the component's own {ID}.md body to match. Use this to enrich a component's raw extracted images into agent-friendly formats. Unlike other skills here, this one writes to knowledge/, not just reads it.

tmforum-oda Skill

Given a proposed component or API design that claims to extend or depend on existing ODA components/APIs, checks those claims against the real cached specs and flags drift -- fields, operations, or behavior the design assumes exist but don't. Use this before building against an assumed ODA capability, to confirm the assumption is real.

tmforum-oda Skill

Given a business scenario description, drafts a new TMFSxxx-shaped use-case document matching this corpus's own observed structure, citing real existing component/API ids wherever the scenario matches existing ODA capability and flagging genuine gaps rather than inventing plausible-sounding new ids. Use this when a requirement doesn't match any existing use case or known gap closely enough to just reuse.

tmforum-oda Skill

Given a description of a proposed or existing multi-component architecture (not scoped to one use case or one component), reviews it against the cached ODA corpus for duplicated ownership (a capability the architecture assigns to a new/custom component that an existing TMFCxxx already owns), point-to-point coupling (a direct interaction where an existing cached Open API already mediates that exact interaction type), and component-boundary bypass (a described interaction that reaches into another component's internals instead of its declared coreFunction). Use this for a whole-architecture ODA conformance review; see validate-design-against-oda for checking one design's specific claimed dependencies, and the audit-implementation-against-* skills for auditing one use case or one component already built.

tmforum-oda Skill

Given a TMFCxxx component id (or one identified via decompose-requirement-against-oda/recommend-oda-components-for-requirement) and the APIs it exposes or depends on, drafts published/subscribed event definitions in the same shape every cached component.yaml's eventNotification block already uses -- resource-level create/attributeValueChange/stateChange/delete events tied to real resource names, never invented event types. Use this when a design needs new events and no existing eventNotification entry already covers them.

tmforum-oda Skill

Given a TM Forum ODA use-case id (TMFSxxx), reads its sequence-diagram section and linked component/API frontmatter, then drafts BDD-style (Gherkin) test scenarios grounded in the real component/API IDs and cached OpenAPI schemas in knowledge/apis/ -- never invented ones. Mirrors oda-canvas's write-bdd-feature Gherkin conventions, pointed at real use-case content instead of hand-written scenarios. Use this when asked to generate test cases, BDD scenarios, or acceptance tests for a TMFSxxx use case.

tmforum-oda Skill

Given a TMFSxxx use-case id, reads its Description/Scope/Objective sections and drafts user stories and acceptance criteria, citing the exact component/API ids from frontmatter for any integration touchpoint rather than inventing them. Use this to turn an existing use case into requirements a delivery team can work from.

tmforum-oda Skill

Given a TMFCxxx component id and a description of an existing implementation, checks conformance at Component-boundary granularity, split explicitly the way component.yaml itself is split -- Core Function (does it expose/consume the real exposedAPIs/dependentAPIs) and Supporting Function (does it provide the managementFunction/securityFunction behaviors the spec describes) -- reported as two separate dimensions, never blended into one score. Use this to audit a component's full contract independent of any specific use case; see audit-implementation-against-usecase for flow-level auditing against one use case's narrative instead.

tmforum-oda Skill

Given a TMFSxxx use-case id, reads its sequence-diagram images and linked component/API frontmatter, and emits a Mermaid sequence or architecture diagram as a design-doc-ready artifact, citing only real component/API ids. Use this when asked for an architecture diagram, sequence diagram, or component interaction diagram for a use case.

tmforum-oda Skill

Given a plain-language business requirement (not yet a TMFSxxx id), finds the closest-matching existing use case(s) by name and component/API overlap, and proposes a starting architecture grounded in real component/API ids -- never invented ones. Use this at the start of a design, before a requirement has been mapped to a specific ODA use case.

tmforum-oda Skill

Given a TMFSxxx use-case id (or an explicit component/API set from recommend-oda-components-for-requirement/decompose-requirement-against-oda), generates typed request/response models and route/handler stubs directly from its linked APIs' cached OpenAPI schemas, in a language of the caller's choosing -- with a TODO marker at every point real domain logic belongs. Also handles the case where a non-ODA legacy interface needs an anti-corruption adapter layer into the chosen ODA contract. Use this when a design needs implementation scaffolding, not implemented business logic, and does not want TM Forum's own opinionated Node.js/Helm reference stack (see implement-oda-component for that alternative).

stacksjs Skill

Use when working with browser/frontend functionality in Stacks — the useAuth composable (login, register, logout, token management), Stripe billing utilities (loadCardElement, confirmPayment), the API fetch client, browser model loading, or auto-imported browser utilities. Covers @stacksjs/browser.

gracefullight Bundle

Quality assurance specialist for security, performance, accessibility, comprehensive testing, and quality standard alignment. Use for test, review, security audit, OWASP, coverage, lint work, and ISO/IEC 25010 or ISO/IEC 29119-aligned QA recommendations.

aze333sun Skill

Use when designing or implementing frontend UI/UX without design mockups, crafting visual interfaces, applying aesthetic guidelines, or building production-grade layouts.

stacksjs Bundle

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle diagrams for Stacks applications as explorable standalone HTML with inline SVG, dark/light themes, four visual presets, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accepts plain-language requirements or pasted Mermaid; reads repository evidence when the diagram must reflect real code; compares two architecture snapshots as a Before/Delta/After review. Use for system or cloud architecture, security boundaries, network topology, technical workflows, CI/CD, runbooks, API call sequences, request lifecycles, data pipelines, lineage, PII boundaries, state machines, status transitions, or converting Mermaid into a purpose-built diagram.

idexal Bundle

Develop features, fix bugs, and refactor the Idexal IDE — a professional multi-agent AI-powered desktop IDE built with React, TypeScript, Vite, Electron, TailwindCSS, Zustand, Monaco Editor, and xterm.js. Use this skill whenever working on this codebase: adding panels, services, stores, AI provider integrations, editor features, terminal functionality, or any code inside idexal-ide/.

kirchberg Bundle

Prepare a set of real application screenshots and a local HTML gallery for viewing specified screens and UI states. Use when the user explicitly asks to capture application UI states or prepare them for design review.

kirchberg Bundle

Use when designing, implementing, refactoring, reviewing, debugging, or profiling Swift media playback for iOS, iPadOS, tvOS, visionOS, macOS, or Mac Catalyst with AVFoundation, AVKit, SwiftUI, or UIKit/AppKit. Trigger for AVPlayer, AVQueuePlayer, AVPlayerItem, audio or video players, HLS/VOD/live/offline playback, loading or seeking, buffering and stalls, playback state, player lifetime, observation teardown, inline/full-screen/Picture in Picture transitions, background audio, interruptions and route changes, Now Playing or remote commands, subtitles and accessibility, multiple synchronized players, AirPlay, FairPlay or resource loading, playback metrics, memory, and playback tests.

kirchberg Bundle

Use when designing, auditing, implementing, migrating, reviewing, debugging, profiling, or testing Liquid Glass interfaces for iOS and iPadOS in SwiftUI, UIKit, or hybrid code. Trigger for iOS 26+ design adoption, latest-SDK visual regressions, glassEffect, GlassEffectContainer, glassEffectID, glassEffectUnion, glassEffectTransition, glass or glassProminent button styles, UIGlassEffect, UIGlassContainerEffect, UIBackgroundExtensionView, system bars, sheets, search, custom blur removal, availability fallbacks, accessibility settings, or glass-related hitches. Do not use for visionOS glassBackgroundEffect, artistic glass simulations or backports, app-icon-only work, or broad interface design with no Liquid Glass concern.

maeenseed Skill

Owns website usability and interface design. Use for user flows, navigation, information architecture, accessibility, responsive UX, and interaction review.

maeenseed Skill

Diagnoses broken or conflicting Elementor behavior. Use for responsive defects, CSS conflicts, editor/frontend mismatches, rendering, and plugin issues.

is-noname Bundle

Bündelt viele Entscheidungsfragen in ein Dokument, das der User ausserhalb der CLI in einem HTML-Renderer beantwortet und als Antwort-Datei zurückgibt. Statt zehn AskUserQuestion-Runden ein Sheet. Dieser Skill sollte verwendet werden, wenn mehr als drei Entscheidungen offen sind, wenn der User sie am Stück oder in Ruhe beantworten will (Fragenkatalog, Entscheidungsliste, Sheet, Fragebogen), oder wenn eine exportierte .answers.json eingelesen werden soll.

is-noname Skill

Generisches CSS-Skin für selbstständige HTML-Reports (Dark Mode, Desktop-first) auf Basis der globalen Design Tokens. Kein Struktur-Skeleton — nur Variablen und Basis-Komponenten (Cards, Tabellen, Tags, Stat-Grid), die jeder Report-Skill frei anordnet. Use when ein HTML-Report/Dashboard/Analyse-Output erstellt wird und dabei konsistent zu anderen Reports aussehen soll statt eigene Farben/Abstände zu erfinden.

is-noname Bundle

Identifiziert Tokenfresser, Redundanzen und ineffiziente Ablaeufe in Skills, Workflows und Skripten, belegt sie mit Messdaten aus den Transcripts und praesentiert sie als HTML-Report.

is-noname Bundle

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

koach08 Skill

Scaffold a new SaaS/app from scratch. Auto-generates a Next.js 16 + Supabase + Stripe + Tailwind CSS 4 boilerplate. Use when starting a new app or SaaS project from scratch.

koach08 Skill

Generate rich HTML articles for the WordPress Classic Editor with inline CSS. Produces visually appealing content using gradients, cards, grids, color-coded boxes, and code blocks. Plain text-only articles are not allowed. Use when writing WordPress articles that need professional visual design.

koach08 Skill

Stripe payment integration setup. Checkout Session, Webhook, Subscription management, Customer Portal, and env var separation — all at once. Use when adding Stripe payments to a Next.js + Supabase project.

koach08 Skill

Supabase Auth + RLS + Middleware setup. Client/server helpers, middleware, RLS policies, and role-based access (user/teacher/admin). Use when adding authentication to a Next.js + Supabase project.

zenithjuno Bundle

Use as the final read-only gate before publishing or sharing an educational ("สื่อการเรียนรู้") HTML/JS browser game made by a solo non-developer. It answers one question: "is this safe to put in front of learners yet?" Three parts: (1) a static scan script (scripts/ship_static_scan.py, stdlib only) that flags ship-blockers in the HTML/JS — dev leftovers, insecure/localhost URLs, missing mobile/charset/lang meta, external network dependencies that break offline use; (2) a functional dry-run — the AI plays the game live if a browser/preview tool is available, otherwise a static review plus a manual dry-run checklist the user runs; (3) a readiness checklist that confirms the other skills are green (content audited, playtested, objective deliverable, player data works). Produces a PASS / CONCERNS / FAIL verdict and never edits game files.

zenithjuno Bundle

Use when the user is unsure what to do next on their educational ("สื่อการเรียนรู้") HTML/JS browser game, or is starting out and wants orientation. This is the map for the learning-game toolset. It is READ-ONLY: it inspects the project (design spec, game files, playtests, reports), figures out which lifecycle stage the project is in, and recommends ONE concrete next action and the skill to run for it. Designed for a solo non-developer — plain language, no jargon, never more than one main recommendation. Use on phrases like "what now", "where am I", "ทำอะไรต่อดี", "เริ่มยังไง", "next step".

zenithjuno Bundle

Use to audit the content and data of an educational ("สื่อการเรียนรู้") browser game BEFORE shipping or after changing the engine. Two targets: (1) the HTML/JS question-generator code — reviewed by reading it for coverage, difficulty spread, and especially answer-correctness; and (2) data files — a sample of generated questions and the player-stat table (e.g. exported from Google Sheet) — checked mechanically by the bundled Python script (scripts/audit_game_content.py, stdlib only, no node). This skill is READ-ONLY: it produces a PASS / CONCERNS / FAIL report and never edits game files. Anything it cannot verify it flags as MANUAL CHECK NEEDED rather than assuming pass.

zenithjuno Bundle

Use when designing an educational ("สื่อการเรียนรู้") game through a discussion-first, lightweight design workflow. The user is a non-developer teacher/author building a browser game (HTML/JS front-end, optional Google Sheet for player stats). This skill helps think through the design in chat — learning objective, target learner, core loop, content architecture, minimal tech, and how success will be judged — then writes ONE lean design spec only after explicit approval. It is deliberately lightweight: not a full Game Design Document, no studio pipeline. Bias every decision toward minimal dependencies, low spec, and something a solo non-dev can maintain.

iberi22 Bundle

Astro Static Site Generator