Cut a new semver release — bump all version strings via bump-version.ts, open a release PR, and after merge tag main and push. Use when cutting a release, tagging a version, shipping a build, or preparing a deployment. Trigger keywords - cut tag, release tag, new tag, cut release, tag version, ship it.
Checks whether a proposed new task conflicts with the project No-gos list in pitch.md. Automated detection gate to prevent mid-build scope creep and rabbit holes. This is Workflow 2 in the 9 named workflows.
Fluxo de trabalho com IA em 3 fases — Explorar (brainstorm guiado), Planejar (plano com tarefas atômicas) e Executar (passo a passo). Ative esta skill sempre que o usuário digitar `/explorar`, `/planejar` ou `/executar`, ou quando tiver qualquer objetivo que envolva planejamento, criação ou dúvida aberta. Serve tanto para tarefas de código quanto para tarefas do mundo real (escrever, pesquisar, contatar, montar). Idioma pt-BR.
Checks how well a Linear cycle is prepared. Reports per-person load in
working days against available days, tickets with no estimate, tickets
nobody is assigned to, oversized tickets that need splitting, work that
did not finish last cycle, on-call rotation cost, and how groomed the
backlog behind the cycle is. Invoke when the user says "cyclotic",
"cyclotic prep", "cyclotic prep next", "cyclotic review", "cyclotic init",
"cyclotic configure", "cyclotic for" a person's name, "cyclotic show
cards", "cyclotic list tickets", "cyclotic explain" a person's name, or
adds "-v" or "verbose" to any of those. Also invoke when the user asks
whether a cycle or sprint is ready, who is over or under capacity, what
carried over from last cycle, which tickets still need estimates, how the
backlog looks going into planning, what is in the cycle and at what sizes,
or how one person's load adds up. Read-only against Linear.
Review customer, data, security, privacy, and operational risks in External-system Synchronization and Checkpointing. Use when founders, PMs, or engineering managers need prioritized consequences, controls, tests, and release concerns.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
Turn product photos and a minimal brief into verified, platform-adapted e-commerce detail-page systems, including product fact review, visual analysis, localized copy, 6-10 module story planning, policy-aware text-free image generation or real-photo routing, deterministic Pillow typography, platform-sized slices, long-page previews, manifests, and automated validation. Supports 淘宝/天猫/京东/拼多多/抖音/小红书/Amazon/AliExpress/Temu/TikTok Shop/eBay/Etsy/Shopify. Use when a user asks for 电商详情页, 商品详情图, 商详设计, A+ content, listing galleries, or a short-input workflow that turns product photos into ready-to-review commerce assets without inventing unsupported claims.
End-to-end AI design system with 190+ battle-tested styles, AI image generation, and pixel-perfect export. Designs social media posters, carousels, YouTube thumbnails, PDFs, and full websites — entirely from natural language. Includes brand onboarding, self-review quality system, Puppeteer export scripts, and 6 teachable design skills. Built through 300+ real design experiments.
Use this skill when the user asks to: design a poster, create social media content, build a carousel, make a YouTube thumbnail, generate a PDF/report, design a website or landing page, create any visual content, or improve the look of any HTML/CSS.
Best practices and guidelines for bootstrapping, defining modules, using dependency injection, managing server lifecycles, and handling events in the NitroStack SDK.
Product leadership for scaling companies. Product vision, portfolio strategy, product-market fit, and product org design. Use when setting product. Agent skill for Claude Code, Codex CLI, Gemini CLI, OpenClaw.
Search and recall relevant memories from past sessions via MemSearch. Use for past decisions, debugging notes, previous conversations, and project knowledge, especially when the context includes a MemSearch memory hint. Skip purely current-code questions or when the user asks to ignore memory.