Explorar skills

规划并执行产品发布，包含质量检查和沟通。当用户需要规划发布、创建发布检查清单、管理上线，或说"规划发布"、"上线检查清单"、"发布管理"时使用。即使没有明确说"发布管理"，当用户正在准备发布功能或部署到生产环境时也应激活。

Gerar, revisar e validar metadados da Apple App Store (nome do aplicativo, subtítulo, palavras-chave, descrição, texto promocional, notas de lançamento) conforme os limites de caracteres da Apple e as melhores práticas de ASO 2025-2026. Acionar quando o usuário mencionar metadados da App Store, ASO, App Store Connect, pesquisa de palavras-chave para iOS, legendas de capturas de tela ou notas de lançamento para um aplicativo iOS / iPadOS / macOS / visionOS / tvOS / watchOS.

Use this skill whenever the user wants to configure their AI workspace, set up agents, create a config for their AI coding assistant, organize development agents, set up their project for AI-assisted development, define quality rules, create slash commands, or prepare their AI team to work on any project. Triggers include: 'configure my workspace', 'setup my AI team', 'create my config', 'set up a

Gere GIFs de demonstração de CLI usando vhs (Charmbracelet). Use ao criar gravações de terminal para arquivos README ou documentação.

Meta-orchestrator that classifies tasks and routes to the right combination of installed skills across caveman (output compression), superpowers (dev workflow), and claude-skills (domain expertise). 23 routing categories including whole-codebase analysis via repomix-pack and LLM/AI app dev. Invoke with /agent-master. Use as default entry point for ambiguous or multi-domain requests.

Expert guidance on Apple Human Interface Guidelines (HIG). Covers iOS, macOS, and visionOS with 2026 Liquid Glass aesthetics and accessibility-first design.

Usado para configurar, instalar, auditar, atualizar, reparar ou sincronizar um 'AI harness' local do projeto para o repositório atual. A ferramenta inspeciona o repositório, realiza uma breve entrevista para definir padrões e guardrails, e então cria ou atualiza os arquivos AGENTS.md, CLAUDE.md, GEMINI.md, PROJECT_HARNESS.md, harness-contract.json e harness-runtime.json.

Modelo de ameaça quântica e arquitetura de defesa. Ativa-se ao discutir a vulnerabilidade do secp256k1, limiares de qubits lógicos, fortalezas criptográficas 2D vs 6D, defesa dimensional, ativos dormentes ou teses temporais.

Agile product ownership for backlog management and sprint execution. Covers user story writing, acceptance criteria, sprint planning, and velocity tracking. Use for writing user stories, creating acceptance criteria, planning sprints, estimating story points, breaking down epics, or prioritizing backlog.

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Za

Always-on multi-agent AI workstation for Claude Code. 142 specialist agents (ML, security, K8s, backend, frontend) · 366 curated skills · 200+ prompt templates · auto prompt-matcher · auto skill-matcher · MCP support · token router cuts Anthropic bill 6x via Kimi/Haiku/Ollama. LiteLLM · BYOK · MIT + Apache. One-line install.

Per-session cost and token budget tracking for AI coding agents. Monitors cumulative spend, warns at thresholds, and enforces limits with three modes: reject (stop work), alert (warn and continue), downgrade (suggest cheaper approach). Ported from the LOCO-Agent BudgetManager. Trigger phrases: "set a budget", "track my spend", "cost limit", "how much have I spent", "token budget", "spending cap".