Comprehensive system check for Mastra AI agent projects. Validates configuration, agents, workflows, memory, tools, prompts, and security across 66 rules organized by priority. Use when setting up new projects, debugging issues, reviewing code, or preparing for production deployment.
Unit + E2E testing + quality gate para Next.js con Claude Code. Combina TDD workflow, Vitest patterns, Playwright E2E, validacion de build, env vars, y security check en una sola skill. Se activa al crear/modificar route.ts, page.tsx, o archivos de test. Para cualquier proyecto Next.js con App Router.
Execute Codex CLI for code analysis, refactoring, and automated code changes. Use when you need to delegate complex code tasks to Codex AI with file references (@syntax) and structured output.
Expert in agsync, the Git-native CLI that syncs skills, commands, and MCP tools across AI coding agents. You MUST use this skill when working on agent skills, commands, MCP configurations or agsync (agsync.yaml) directly.
Personal Knowledge Management documentation system based on Zettelkasten principles. Use when documenting conversations, decisions, development work, learnings, or any knowledge that should persist. Triggers on new projects, technical decisions, completed tasks, lessons learned, meeting notes, or when the user says…
PROHIBITS placeholder code, default values that mask missing data, and silent failures. Enforces fail-fast with loud errors. Use when implementing ANY function or data structure.
Review code for security vulnerabilities, performance issues, and coding best practices. Activate when the user asks to review code, check code quality, give feedback on code changes, or audit a file.
Remove signs of AI-generated writing from text. Use after drafting to make copy sound more natural and human-written. Based on Wikipedia's "Signs of AI writing" guide.
Auditoria automatizada da conta de Meta Ads em 4 frentes (estrutura, criativo, público, LP). Devolve lista priorizada de ações em markdown salva no vault.
Quick read-only health check — session context, workspace mounts, tool availability, and task snapshot. Use when the user asks for system status or runs /status.
Use when you write an HTML document, plan, spec, design, report, or similar deliverable for the user to READ AND GIVE FEEDBACK ON. Wraps the HTML as a self-contained Noteback feedback canvas so the user can highlight text, leave comments (including whole-document notes) in their browser with NO extension, and copy the…
Dial in an espresso shot by steering the dose–yield–time triangle from taste. Use when an espresso tastes sour, bitter, or hollow, when switching beans or roast, or when a shot runs too fast or too slow and you need a concrete grind/dose/yield adjustment.
A Chinese-language research mentor for PhD students working in deep learning and artificial intelligence. It covers research from choosing a topic and designing experiments through writing papers and responding to reviews.
Detect silent agent failures and memory degradation. Use when asked for an agent health check, when agent behavior seems off or output quality drops, after long unattended runs, or as part of a scheduled maintenance pass.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: