Full-Stack & DevOps

To Spec workflow and prompt instructions for Claude and AI coding agents.

Writing Adrs workflow and prompt instructions for Claude and AI coding agents.

Vercel AI SDK: generateText, streamText, tool calling og useChat.

Diagnose why an agent harness misbehaved by reading the local flight-recorder ledger (.vigiles/runs.jsonl) — which skills fired or got hijacked, which hooks blocked or wrongly allowed, which subagent tool-contract violations happened, and how a skill's trigger rate moved. Use ...

Får en Next.js-rute til øjeblikkelig navigation under Cache Components/PPR ved at skrive en fejlende Playwright-test og arbejde den grøn, så testen bliver stående som regressionsværn.

Show real token usage and estimated savings for the current session.

Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.

Leverandøruafhængigt observability-framework til at generere og indsamle traces, metrics og logs.

E-mail-API til udviklere til programmatisk afsendelse af transaktions- og marketingmails.

Web typography from choosing fonts to spacing, wrapping and accessibility. Use when picking or pairing typefaces, configuring variable fonts or OpenType features, setting up a type scale, checking heading hierarchy, styling text in components, truncating text, styling underlin...

A relentless interview to sharpen a plan or design.

Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementati...

Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, che...

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Udfører struktureret kodereview med specialiserede personas, konfidensvurdering af fund og verificerede rettelser før merge.

Redis-baseret distribueret job- og beskedkø til Node.js med workers, schedulers og flows.

Open source-observability-platform til logs, metrics, traces, dashboards, alarmer og real user monitoring.

Slår Cache Components til i en eksisterende Next.js-app og arbejder de blokerende rutefejl igennem, inklusive codemod og valget om opt-out per rute.

TypeScript-first skemavalidering og statisk typeinferens til parsing, transformering og validering af data.

Applikationsovervågning til fejlsporing, performanceovervågning, session replay og profilering.

Automatiserer browserinteraktioner til webtest, udfyldning af formularer, screenshots og dataudtræk.

Platform til holdbar workflow-orkestrering af langvarige processer, retries og pålidelig baggrundsafvikling.

End-to-end typesikre API'er til TypeScript uden schemas eller kodegenerering.

Deploy Next.js-apps til Vercel med korrekt konfiguration og opsætning af miljøvariabler.

Playwright-mønstre: selectors, fixtures, parallelisering og CI-integration.

Styr en live browser via Playwright CLI for at optage, inspicere og afspille interaktioner.

Accessibility engineering for product interfaces, from focus states and keyboard support to ARIA, forms, and screen readers. Use when building or reviewing UI components, modals, menus, forms, custom widgets, or when the user says "make this accessible" or reports keyboard or ...

Testmønstre til webapps på tværs af unit-, integrations- og end-to-end-tilgange.