Explorar skills

Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

Use this skill when working with Proofpoint forensics and threat response - auto-pull, search and destroy, message trace, evidence collection, and remediation workflows. Covers post-delivery remediation, message investigation, and incident response procedures for email-borne threats.

Database conventions and patterns. Use when working on database schemas, migrations, or data modeling.

Use this skill when working with the SuperOps.ai GraphQL API - authentication, query building, mutations, pagination, rate limiting, and error handling. Covers Bearer token auth, cursor pagination, variable usage, and best practices for GraphQL integration with SuperOps.ai.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Use this skill when working with Liongard detections, change monitoring, alerts, metrics, or timeline events. Covers automated change detection, anomaly alerts, alert rules, custom metrics, metric evaluation, and timeline audit trails for compliance and monitoring workflows.

Use this skill when working with Huntress incidents - querying incidents by organization and status, reviewing SOC-recommended remediation details, approving or rejecting remediations individually or in bulk, checking remediation execution status, and resolving incidents after all remediations are processed.

Use this skill when working with the Domotz MCP tools -- available tools, authentication via API key, API structure, pagination, rate limiting, region selection, error handling, and best practices.

Use this skill when the user asks about Worktrunk (wt), git worktree management, running parallel AI agents with worktrees, setting up wt hooks, configuring wt.toml, using `wt switch`, `wt list`, `wt merge`, `wt remove`, `wt step`, LLM commit messages, or integrating Worktrunk with your AI agent. Also trigger when the user wants to run multiple AI agent sessions in parallel across isolated git bra

Multi-agent code review with parallel specialized reviewers, architecture validation, and challenge validation. Use `rq` to request a review of diffs (defaults to main branch), `rs` to respond to review findings. Triggers on "review this", "review my code", "code review", "check for bugs", "audit this", when examining PRs, pull requests, branches, or diffs. Always asks user before applying fixes.

Esta skill aborda o uso das ferramentas Huntress MCP, incluindo ferramentas disponíveis, autenticação HTTP Basic Auth, estrutura da API, paginação com tokens, limite de taxa (60 req/min), tratamento de erros e melhores práticas.

Use this skill when working with Proofpoint threat intelligence - campaign tracking, threat families, indicators of compromise (IOCs), forensic evidence, and threat landscape analysis. Covers campaign details, actor attribution, threat indicators, and how to investigate and track threat campaigns across the organization.