Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.

Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). In Codex, honor explicit requests for the Codex Chrome plugin/@chrome by using the Chrome Extension workflow; otherwise use Chrome Computer Use when available and fall back to real Chrome CDP scripts only when allowed. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".

End-to-end smoke test for the `tessl launch skill --cloud` pipeline. Reads one Linear issue (read-only) via the Linear API to prove `LINEAR_TOKEN` is wired into the sandbox, appends a single run-marker line to a log file, then opens a GitHub pull request with that one-line change to prove `GITHUB_TOKEN` and the publish path work. Use whenever you need to verify a cloud launch can reach Linear and GitHub and open a PR end to end -- dogfooding the launch pipeline, checking that credentials forward into the sandbox, or as a minimal known-good skill to launch when debugging the launch flow itself. Self-contained: driven by launcher-supplied inputs plus `LINEAR_TOKEN` and `gh` credentials in the environment. Makes no Linear writes; its only change is the one appended log line in the PR it opens.

Hardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a login flow is safe against the OWASP Top Ten. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services. Use when auditing dependencies for known vulnerabilities, triaging package-manager audit findings, or assessing supply-chain risk in a new package. Use when personal data or privacy compliance (GDPR, CCPA) is involved.

Reviews and plans UX for web and React Native (Expo) UIs: walks the user's real path through the code, checks what each control actually does, then goes deep on accessibility (WCAG 2.2) and microcopy. Never recommends a dark pattern. Triggers on "ux review", "ux audit", "check accessibility", "is this accessible", "plan the X flow", "improve copy", "/ux".

Use when the user wants any spec-driven development action — exploring before speccing, deriving specs from code or translating specs from another system, proposing a change, applying or implementing, verifying, syncing delta specs, or archiving. Triggers: 'spec this out', 'create a change', 'apply tasks', 'verify implementation', 'sync specs', 'archive change', or any mention of 'specs' or 'sdd'.

Configures Amazon Route 53 to route traffic to a CloudFront distribution using a custom domain. Use when setting up DNS alias records, alternate domain names (CNAMEs), ACM certificates for HTTPS, and IPv6 support for CloudFront.

Performs code upgrades, migrations, and transformations using the AWS Transform (ATX) CLI. Use when upgrading language versions, migrating AWS SDKs, migrating frameworks (Angular, Vue.js, Spring Boot, React), upgrading libraries, optimizing performance, migrating x86 to Graviton, analyzing codebases / generating documentation, or defining custom transformations with natural language. Runs locally on a few repositories or at scale across hundreds via AWS Batch/Fargate.

Pesquisa mercado e define estrategia e publico de campanha. Trigger em: "pesquisa de campanha", "base estratégica do anúncio", "research de concorrentes para campanha", "pesquisa concorrentes para a campanha", "voz do consumidor", "evidence ledger de marketing", "ângulos de campanha com evidência", "angulos de campanha", "estratégia antes da copy".

Planeja estrategia, producao e distribuicao de conteudo para crescimento. Trigger em: "plano de conteudo", "estrategia de conteudo", "content marketing", "growth de conteudo", "pauta", "calendario editorial", "organizar o blog em clusters", "cluster de conteudo", "topic cluster", "intencao de busca", "intencao comercial", "fundo de funil", "pagina de servico", "pagina de precos", "comparativo X vs Y", "estudo de caso", "link interno", "linkagem interna", "atualizar conteudo antigo", "content refresh", "share of voice", "citacao em IA", "o chatgpt cita os concorrentes", "como medir se a marca aparece nas respostas de IA", "chatgpt recomenda", "lead magnet", "trafego nao converte", "objecoes de venda", "crescimento organico", "growth sem ads", "crescer sem anuncio", "agente recomendar o app", "pagina for-ai", "swarm de paginas", "qr code de divulgacao", "build in public", "apostas de distribuicao".

Corrige interfaces responsivas e problemas de viewport mobile. Trigger em: "responsivo", "mobile", "nao pega 100%", "cortando na tela", "quebrou no celular", "scroll horizontal", "viewport", "safe area", "notch", "bottom sheet", "modal no mobile", "confirmacao de exclusao", "modal de confirmar", "undo", "grid quebrado", "overflow", "converter para mobile", "adaptar layout".

Extrai e aplica convencoes existentes do repositorio. Trigger em: "segue o padrao do projeto", "coda igual ao resto", "nao reinventa padrao", "detecta padroes do codebase", "code style do projeto", "padrao do projeto", "convencao do projeto", "coda consistente", "mesma convencao", "sem reinventar roda", "padrao de codigo", "patterns do codebase", "pattern enforcement", "conformidade de padrao", "convencoes de naming", "padrao de tratamento de erro", "mesma estrutura do projeto", "detecta as convencoes", "extrai padroes de coding", "como o projeto estrutura".

Reconstrói especificacoes e regras de sistemas existentes. Trigger em: "legado", "engenharia reversa", "extrair spec", "documentar codigo existente", "vibe coding sem doc", "detective", "reverse spec", "o que esse codigo faz", "spec a partir do codigo".

Skill para integrar geracao e manipulacao de video em aplicacoes. Trigger em: "text-to-video", "image-to-video", "video generativo", "avatar video", "motion explainer", "clip promocional", "gerar video", "fal video", "Sora", "Veo", "Runway video", "video AI".

Manage a stateful, run-directory-based proof project with Codex: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional DeepSeek second opinion as additional evidence only. Use when the user asks for proof-run orchestration, a GPT Pro handoff, or cross-run proof continuation — use /proof-writer for ordinary proof drafting and /proof-checker for rigorous verification or submission acceptance.

Research and library synthesis from the docs/PDF corpus, mapped to joelclaw system philosophy and concrete operational actions (especially k8s reliability). Trigger on: 'research this', 'from the library', 'from the books', 'pdf brain', 'correlate this', 'synthesize', or any request to derive practical architecture/ops guidance from the docs corpus. This skill is analysis-only; for ingestion/backfill workflows use pdf-brain-ingest.

Execute provider-neutral DevOps operations across AWS, GCP, Cloudflare, and Vercel. Standardizes MCP preflight, identity and authorization, effect-based release gating, and outward verification for setup, deploy, verify, monitor, diagnose, and recover. Use when managing cloud infrastructure, deploying releases, or diagnosing operational issues. (triggers: devops operations, cloud deployment, hosting verification, deployment diagnosis, cloud monitoring, deployment recovery)

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.

UnoCSS instant atomic CSS engine, superset of Tailwind CSS. Use when configuring UnoCSS, writing utility rules, shortcuts, or working with presets like Wind, Icons, Attributify.

Redis LangCache guidance for semantic caching of LLM responses on Redis Cloud — calling search/set via the SDK or REST API, tuning the similarity threshold, separating caches per task type, and filtering with custom attributes. Use when caching LLM completions or RAG answers to cut API cost and latency, building a cache-aside layer in front of OpenAI / Anthropic / etc., tuning hit rate vs precision, or splitting one app's LLM workloads into multiple LangCache caches.