工具

Generates clear commit messages from git diffs. Use when writing commit messages or reviewing staged changes.

Use when the user asks to "refactor shell script", "fix bash style", "apply Google style guide to shell", "review shell script style", "format bash script", or when writing, reviewing, or refactoring shell/bash scripts. Provides Google Shell Style Guide rules for formatting, quoting, naming, control flow, and common anti-patterns.

Build OpenCode plugins, agents, hooks, and tools. Use when creating, reviewing, or debugging OpenCode extensions. Covers plugin architecture, agent configuration, lifecycle hooks, custom tools, and distribution. Invoke PROACTIVELY when user mentions OpenCode plugins, agents, hooks, or wants to extend OpenCode functionality.

Builds full-stack applications with Payload CMS, the Next.js-native headless CMS. Use when creating content-driven apps with TypeScript, code-first configuration, and full control over your backend.

Processo e template para auditoria técnica + estratégica da plataforma. TRIGGERS: 'auditoria', 'platform audit', 'análise completa', 'health check'. Use para executar análises periódicas de saúde técnica, arquitetura, ROI e sustentabilidade.

Use when generating PDFs from markdown with Pandoc - covers differences from Python-Markdown, blank line rules, fix scripts for labels/anchors/metadata, and visual testing workflow

This skill should be used for thorough AI review via Codex CLI (gpt-5.2-max). Triggers include architectural decisions, blocking issues, final review before done, or when consult-light escalates due to low confidence.

Create CrewAI workflows as NestJS applications under apps/crewai/. FUTURE: Same pattern as LangGraph - NestJS app, same webhook pattern as n8n, receive same parameters, wrap as API agents. CRITICAL: Status webhook URL must read from environment variables.

This skill should be used when the user asks to "find past conversation", "search session history", "where did we discuss X", "find when I worked on Y", or "search old sessions by keyword". Searches Claude Code session files in ~/.claude/projects/ by topic, keyword, or date.

Enforce comprehensive deployment verification after deploying code, scripts, or configurations. Use after any deployment, build, or installation operation. Prevents deployment verification failures (FP-9).

A clear description of when this skill should activate and what it does

Incremental migration from legacy systems. Run old and new in parallel, gradually shift traffic, rollback at any point. Zero downtime, production-validated.

MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows

Fast type checking for single files. Never hangs, always answers in <5s.

Comprehensive plugin development toolkit for creating, testing, and managing plugins across multiple platforms with scaffolding, validation, and deployment utilities.

Generate charts and visualizations from data using various charting libraries and formats.

Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.

Proteomics analysis toolkit for label-free quantitative proteomics. Invokes R scripts for normalization, visualization (volcano, heatmap, PCA, LOPIT), pathway analysis (KEGG, ConsensusPathDB), and protein list cross-referencing (MISEV2018, SASP, Matrisome). USE WHEN user says 'analyze proteomics', 'volcano plot', 'normalize protein data', 'pathway enrichment', 'check EV markers', 'SASP analysis', 'matrisome', OR mentions q-value, fold-change, or protein quantification.

MUST INVOKE this skill when creating focused prompts in .prompts/prompts/ and multi-stage chains in .prompts/metaprompt/. Create, audit, and maintain all types of prompts including standalone prompts and meta-prompts for AI-to-AI workflows.

Zustand state management for React Native. Use when implementing client-side state.