Generate comprehensive Functional Specification Documents (FSDs) that translate PRD requirements into implementation-ready specifications. Use when the user needs to create an FSD, functional spec, system specification, or detailed feature specification. Triggers on requests like "create an FSD", "write functional specifications", "translate this PRD into specs", or any request to define system behaviors, data requirements, business rules, and acceptance criteria from a PRD or feature description.
Wenn es um Notariat 014 Ehevertrag Scheidungsfolgenvereinbarung Belehrung in Notariat im Alltag geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und Gegenposition; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Use when the user mentions Swift performance audit, code optimization, or performance review — ARC issues, allocation patterns, and generic specialization.
Next.js 16+ and Turbopack guidance — incremental Rust bundling, file-system caching, faster dev startup and HMR, Turbopack vs webpack tradeoffs, and the middleware.ts to proxy.ts filename change. Use when developing or debugging Next.js 16+ apps, diagnosing slow dev startup or hot reload, choosing between bundlers, or reviewing middleware/proxy file naming.
Audit a project's theme, design tokens, and colour accessibility — WCAG contrast across every theme, focus indicators, and design-system hygiene (hardcoded colours bypassing tokens, orphan/unwired tokens, theme parity drift, diluted text utilities) — then fix what's broken and prove it with a rendered-DOM sweep. Use this whenever the user mentions a theme audit, design tokens, colour contrast, WCAG or a11y for colour, dark mode parity, "is my palette accessible", CSS variables organization, hardcoded colours, or asks to review/clean up/reorganize a design system's colours — and also when they ask to check accessibility of a site's look, fix unreadable or washed-out text, make focus states visible, or audit a theme they just built, even if they never say "tokens" or "contrast".
Scaffold a new DEC-### decision record with a valid ID, filename, frontmatter, required sections, and README index entry, and wire it into any PRD or context that references it. Use only when explicitly asked to create a decision record; do not use for repository structure, tooling, agent workflow, or CI policy choices.
Use this skill whenever writing any audio cue, haptic signal, Web Audio API initialisation, or interaction feedback code in the Myelin simulator. This defines the complete audio event map, frequency values, Web Audio API implementation pattern, haptic signal contract, and the accessibility fallback requirements. Load this skill before writing any audio or haptic code.
Use this skill for every task in this project. It provides the tech stack, constraints, naming conventions, and non-negotiable rules that must be respected at all times when writing or modifying code.
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and scope, or when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a capability map of modules before specifying.
Structured logging guidance for .NET applications. Use when adding log
statements, choosing levels, defining message templates, correlation, scopes,
or reviewing logging quality and sensitive-data exposure.
Comprehensive codebase survey and understanding system that forces Claude to fully understand a project before making any changes. Use this skill BEFORE starting work on any new or existing project. Triggers on phrases like "start working on", "help me build", "continue the project", "fix my code", "add a feature", or when encountering an unfamiliar codebase. Employs parallel subagent analysis to survey all aspects of a project - architecture, connections, integrations, operations - and creates a living SOURCE-OF-TRUTH.md that becomes the canonical reference. PREVENTS assumptions and guessing. Claude must KNOW before it can DO.
Use when an AI agent needs to manage Traefik Route Manager routes through its HTTP API, including authenticating, listing routes, and creating, updating, or deleting managed route entries that map domains to backend services.
Clean up AI-generated writing by removing slop (generic tone, filler, inflated claims, vague attributions, list spam) while keeping meaning the same. Use when asked to "humanize" text, remove AI-sounding writing, or align prose with local/author voice.
Find the laziest solution that works: question whether the task needs to exist (YAGNI), prefer stdlib over custom code, one line over fifty. Use when user says "ponytail", "lazy mode", "simplest solution", "minimal", "yagni", or complains about over-engineering, bloat, or unnecessary dependencies.
Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests.