Explorar skills

Translate natural-language requests about modifying an AI coding agent, its skills, MCP tools, MCP servers, prompts, routing, tool descriptions, context loading, memory, portability, or other agentic behavior into the concrete mechanics of the target system. Use when a request is underspecified, phrased in human terms instead of runtime terms, or risks making the wrong change because the agent mus

Gera um sistema de marca de nível de diretor criativo e um brand board HTML autônomo e polido para diversas entidades como startups, produtos e agências. Utilize esta skill para branding, identidade visual, direção de arte ou um concept board pronto para apresentação.

Auditoria de segurança para servidores MCP (Model Context Protocol). Detecta riscos de exfiltração de dados, injeção de comandos, escalonamento de permissões e vulnerabilidades na cadeia de suprimentos antes de adicionar servidores MCP ao seu agente.

Apple Search Ads (ASA) deep analysis for mobile app advertisers. Evaluates campaign structure, bid health, Creative Sets, MMP attribution, budget pacing, TAP coverage (Today/Search/Product Pages), and goal CPA benchmarks by country. Use when user says "Apple Search Ads", "ASA", "App Store ads", "Apple ads", "Search Ads", or is advertising a mobile app on iOS.

Camada de execução para o skill-dispatcher que executa cadeias de agentes multifásicas de ponta a ponta com telemetria por etapa e correlação de ID da cadeia.

Fix "untracked working tree files would be overwritten by merge" errors when pulling after a squash merge. Use when: (1) `git pull` fails listing files that should already be on main, (2) you just squash-merged a PR and can't pull on another branch, (3) files from a merged branch appear as "untracked" blocking checkout or pull. The root cause is that squash merge creates new commits — the original

Ponte de contexto multiagente — alterne facilmente entre agentes de codificação de IA sem perder o contexto.

Construa agentes de IA com estado e fluxos de trabalho agênticos usando LangGraph em Python. Abrange agentes que utilizam ferramentas com loops LLM-ferramenta, fluxos de trabalho com ramificações, memória de conversação, supervisão humana e monitoramento de produção.

Full-spectrum web application Vulnerability Assessment and Penetration Testing (VAPT). Automates reconnaissance, scanning, injection testing, authentication analysis, and report generation. Supports --mode pro (terse) and --mode dev (educational). Enforces authorization gate before any active testing.

Adversarial test hardening — domain-lens behavioral attacks on contracts before implementation

Analyze session history to identify inefficiency patterns and workflow gaps. Two modes: lightweight end-of-session reflection from conversation context, or comprehensive periodic analysis across multiple sessions via jq-extracted JSONL summaries. Produces structured reports with copy-paste-ready improvement proposals for CLAUDE.md, skills, commands, and automation.

Use when facing a task too large to hold in one piece — decompose into atomic subtasks. Divide-and-conquer in chengyu form. Pairs naturally with subagent dispatch (each part becomes one subagent's job) and with the dispatching-parallel-agents superpower. The decomposition itself is the skill — the parts should each have one clear purpose and a well-defined interface to the others.