Explorar skills

Update Cabal project index-state to the latest timestamp. Use when it needs to bump the cabal index-state.

Standalone agentic architecture skill. Designs complete multi-agent AI systems from scratch — no other vibe-* skills required. Deep knowledge of LangGraph, LangChain, CrewAI, AutoGen, Vercel AI SDK, and custom implementations. Produces AGENT_ARCH.md covering pattern selection, agent roles, tool mapping, state design, HITL checkpoints, VerifierAgent rubrics, implementation order, stack recommendati

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Create and manage temporary/disposable email inboxes via tempmail.lol API (no dependencies, just curl). Use whenever the user needs a throwaway email — E2E testing, account registration, email verification, OTP confirmation, or any disposable inbox scenario. Triggers on: "temp email", "temporary email", "disposable email", "docasny email", "docasna schranka", "throwaway email", "fake email for tes

Generate marketing images using DALL-E 3 or ComfyUI (Stable Diffusion XL). Batch generation, optimization, cost estimation. Requires image-generation extension. Triggers on: /creo image-generation, generate images, DALL-E, ComfyUI.

Use this skill when the user asks "where am I", "what's the current task", "what's blocking me", "show status", "what needs sign-off", or "what's next". Prints a snapshot of the active plan, gate, sign-off progress, and next action. Reads only — writes nothing.

Generates a DESIGN.md file for any website URL or fetches a pre-built one from the awesome-design-md collection (55+ sites). DESIGN.md captures the complete design system of a real product — exact hex/oklch values, font families, spacing scales, shadow formulas, component states, do's and don'ts — in a format vibe-design reads to produce pixel-accurate matching UI. Two modes: fetch a pre-built DES

Ponto de entrada do construtor de mundos, focado em diagnosticar onde o usuário está travado na fase inicial (-1 a 0) e encaminhá-lo para a sub-skill correta. Ajusta o tom e escreve regras de roteamento no CLAUDE.md na primeira execução.

Generate a single canonical AGENTS.md context file plus minimal CLI-specific shim files that @-import it for coding agents that do not read AGENTS.md natively (Claude Code, Gemini CLI, Qwen Code). Based on "Evaluating AGENTS.md" (ETH Zurich, Feb 2026) which found auto-generated context files DECREASE performance by ~3% and increase costs by 20-23%, while minimal human-written files improve perform

Content-focused SEO audit for Next.js apps. Deep dive into E-E-A-T, AI-generated content detection (26 phrases + 24 vague quantifiers), humanity/specificity/structure scoring, search intent detection, opportunity scoring, internal linking audit, and citability-ready rewrite priorities. Complements creo-seo (which covers technical, build, live, schema) by focusing exclusively on content quality. Tr

Algoritmo de Dijkstra: Caminhos Mais Curtos em Grafos Ponderados

三機(Claude/Gemini/Codex)平行審查測試，評估覆蓋率、邊界條件、異常處理後投票共識