Explorar skills

Gere Documentos de Requisitos de Produto abrangentes com as melhores práticas de PM de IA para novos recursos e produtos.

Verifica a integridade de CLAUDE.md em relação à estrutura real do projeto. Use quando CLAUDE.md pode estar dessincronizado com os arquivos mox.lua, conanfile.py, build.lua, README.md ou LICENSE.

This skill should be used when the user asks to "detect workspaces", "find packages", "list monorepo packages", "workspace structure", "monorepo analysis", or needs to identify workspace/package boundaries in a codebase for focused security analysis.

This skill should be used when the user asks about "logging failures", "log injection", "insufficient logging", "audit logging", "security logging", "CWE-117", or needs to find logging-related vulnerabilities during whitebox security review.

This skill should be used when the user asks about "compliance mapping", "PCI-DSS", "HIPAA", "SOC 2", "NIST CSF", "regulatory requirements", "compliance report", or needs to map security findings to compliance framework requirements.

Interact with Slack workspaces — send messages, react, pin/unpin, read history, manage threads, search, upload files, and look up members. Use when the user asks to send a Slack message, react to something, read a channel, or manage Slack content.

Detect postMessage handlers that trust unvalidated origins or write attacker-controlled data to dangerous DOM sinks.

Use when writing or reviewing error handling, floating-point math, concurrent code, remote calls, singletons/globals, hot-path data structures, or high-volume log statements

Use when writing or reviewing tests, designing test data, naming a test, choosing what to assert, or writing test helpers/mocks/fixtures

Send WhatsApp messages programmatically via the Baileys library (WhatsApp Web multi-device protocol). Use when the user asks to send a WhatsApp message or interact with WhatsApp.

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

This skill should be used when the user asks about "vulnerability chains", "chained exploits", "multi-step attacks", "SSRF to RCE", "pivot attacks", or needs to identify how vulnerabilities in different components can be combined during whitebox security review.