Explorar skills

Habilidade do Claude Code para auditorias de segurança estruturadas com planos de remediação acionáveis.

Analisa o perfil de risco de um protocolo DeFi em dimensões de contrato inteligente, off-chain e histórico, útil para avaliar a segurança e os riscos de um projeto.

Full-spectrum security research skill for web servers, REST APIs, web applications, and network/port enumeration. Triggers whenever the user wants to: find vulnerabilities, run a security assessment, scan a target, test an API for security issues, enumerate ports or services, check for OWASP Top 10 vulnerabilities, audit auth/secrets, fuzz endpoints, run recon on a domain or IP, or use tools like

Skill de Relatório de Auditoria de Prontidão para IA: Ajude um consultor de IA a transformar descobertas de auditoria em um relatório profissional para clientes, fazendo perguntas estruturadas em 5 domínios e pontuando cada um.

Audits any project for security, test coverage, and Claude Code automation. 46 checks across 6 layers: secrets, CLAUDE.md, hooks, skills, agents, rules, MCP, CI, memory. Adaptive scoring — auto-detects project maturity (Starter/Growing/Mature/Pro). Diagnoses gaps, prescribes project-specific fixes, applies them. Usage: /doctor — full audit (all 6 layers) /doctor quick — TOP-3 priorities + score (3

A continuously-firing background work runner for Claude Code. Queue real tasks ("/blitz add"), track long-term goals ("/blitz goal add"), and enable per-project audit rotations ("/blitz audit enable"). Blitz fires on a configurable cadence with a per-project idle gate, decomposes goals into increments on a long-lived branch, and persists every fire's output to ~/blitz/runs/<timestamp>/. Includes c

When the user asks for a 4.6 / 4.7 compatibility scan, run this skill rather than improvising the analysis. Covers CLAUDE.md, AGENTS.md, subagents, skill files, settings.json, hooks, package manifests, and Anthropic SDK call sites. Triggers - "compatibility scan", "scan for opus 4.7 migration", "is my project ready for opus 4.7", "my agent is acting weird since I switched to 4.7", "scan for 4.7-on

Skill ROBUSTA de cybersegurança full-spectrum para arquitetar, auditar e responder. Usar SEMPRE que o usuário quiser projetar segurança, auditar projeto, garantir hardening, defender contra invasão, mitigar vulnerabilidades, ou tratar incident. Também aciona quando mencionar 'cybersegurança', 'cyber', 'segurança do projeto', 'hackeado', 'invadido', 'invasão', 'ataque', 'breach', 'vazamento', 'pent

Multi-layered anti-fraud and bot detection system for registration flows. Use when implementing: (1) Registration form security, (2) Bot detection and shadow banning, (3) Behavioral analysis (keystroke, mouse tracking), (4) Risk scoring systems, (5) Honeypot field implementation, (6) Disposable email detection, or any fraud prevention for user registration