Sub-architect Frontend. Invocado por /architect orchestrator. Lee 01-spec.md + 02-design-ui.md + story YAML. Produce 03-arch-fe.md con: routes, components FSD-Lite, hooks React Query, Zod schemas, types TS, tests Vitest+Playwright, server-first boundaries. Activa cuando /architect spawna o user dice: '/architect-fe', 'arq frontend', 'diseña FE'.

Sub-architect Backend. Invocado por /architect orchestrator. Lee 01-spec.md + (02-design-ui.md si mixed) + story YAML. Produce 03-arch-be.md con: endpoints, DTOs Pydantic, SQLA models, migrations idempotent, services, repositories, tests requeridos, cross-cutting (tenant isolation, currency, master-data, PII). Cross-module audit obligatorio. Activa cuando /architect spawna o user dice: '/architect-be', 'arq backend', 'diseña BE'.

Sub-architect Agentic. Invocado por /architect orchestrator cuando story toca copilot/sales_agent. Lee 01-spec.md + 02-design-agentic.md + story YAML. Produce 03-arch-agentic.md con: tools defs (Pydantic schema), prompt slot architecture, LangGraph state, eval suite path, personas/rubrics asignados, observabilidad (trace + cost), trial policy. Carga sales-agent-expert, copilot-expert, tessl__langgraph, claude-api. Activa cuando /architect spawna o user dice: '/architect-agentic', 'arq del agente', 'diseña agentic'.

Identify Terraform provider support for resources, data sources, actions, list resources, ephemeral resources, and functions. Use when checking provider capabilities, asking "what resources does X provider support", "does provider Y have actions", or querying specific provider features.

Generate, audit, and compress AI-optimized documentation for codebases. This skill applies research-backed principles from three peer-reviewed papers to create documentation that maximizes AI agent performance instead of degrading it. Use this skill whenever the user asks to "write docs", "create a CLAUDE.md", "document a module", "audit documentation", "compress docs", "optimize docs for AI", "write module docs", "create domain documentation", "review doc quality", or mentions documentation bloat, token waste, or AI context efficiency. Also trigger when the user references "ai-docs principles", "telegram style docs", or wants to apply the "Lost in the Middle", "Less is More", or "AGENTS.md" research findings.

Tailwind CSS patterns and conventions for frontend apps. Use when writing component styles, layouts, or working with CSS classes.

Especialista Senior en Frontend (Next.js, React, Tailwind, FSD) para la construcción de interfaces. Úsalo cuando el usuario pida "nueva funcionalidad", "modifica el front", "crea un componente", "actualiza el diseño" o "refactoriza la UI".

Especialista Senior en Python, FastAPI y Domain-Driven Design (DDD) para backend. Úsalo cuando necesites crear endpoints, modificar lógica de negocio, diseñar entidades, actualizar servicios o trabajar con bases de datos.

Simulate high-stakes reasoning by modeling how top experts in the relevant domain would think, disagree, and converge on a decision. Use when users ask to role-play strongest minds, compare elite viewpoints, or ask: what would be a good group of people to explore X, and what would they say. Trigger for prompts like "think like world-class experts", "simulate top domain specialists", "role-play strongest domain people", and "use four-lens dialogue".

意图识别,理解用户输入的真实意图和上下文

Guardian 复盘分析,检测偏差信号和行为模式

基于科学依据的微协议生成,为空闲时段设计行动方案

目标繁荣规划,为用户规划深度心流和高质量连接时段

【强制】复杂任务管理系统。 AI 必须在遇到以下情况时**先读取此 SKILL.md**，再执行任何操作： - 多文件变更、规划设计、新功能开发 - 用户说"帮我想想/重构/升级/实现" 禁止使用内置 agentic_mode 的 artifact 目录处理复杂任务，必须使用项目根目录下的 .taskflow/ 目录。

Predict Animal Crossing New Horizons turnip prices using the game's exact algorithm. Use when a user asks about turnip prices, ACNH turnips, stalk market, turnip predictions, when to sell turnips, or bell profit from turnips.

Builds a Claude Code statusline from scratch or extends an existing one. A statusline is a live status bar that runs a shell script after every Claude response and displays data — security scans, git status, API quotas, build state — directly in the session. Use this skill when the user says "create a statusline", "make a statusline for X", "add X to my statusline", "show Y in the status bar", "build a statusline plugin", or "I want live data in my Claude session". Trigger even if the user just describes wanting live feedback during a Claude session without naming "statusline" explicitly. The skill drives from idea to a working, installed, tested statusline without requiring the user to direct every step.

Creates high-quality agent skills by running the official Claude skill creator plugin and then applying a structured set of enhancement phases covering use-case design, frontmatter completeness, body structure, writing quality, and progressive disclosure architecture. Use this skill when the user wants to create a new skill, improve an existing SKILL.md, or asks "how do I write a good skill", "help me make a skill for X", "review my SKILL.md", or "turn this workflow into a skill". Trigger even if the user just says "let's make a skill" or describes a workflow they want to capture.

Runs Snyk CLI security scans and fixes the vulnerabilities found. Covers four domains: source code (SAST via snyk code test), open-source dependencies (SCA via snyk test), container images (snyk container test), and infrastructure-as-code files such as Terraform, Kubernetes YAML, and CloudFormation (snyk iac test). Use this skill whenever the user wants to scan for vulnerabilities, audit dependencies, secure a Dockerfile or container image, check IaC for misconfigurations, or asks "is my code/app/image/infra secure?". Also trigger for requests like "fix security issues", "run a security scan", "check for CVEs", "find hardcoded secrets", or "review my Terraform for security problems" even if Snyk is not mentioned by name.

Explain why code looks the way it does by tracing the latest change for a file range or pasted snippet through `git blame` and deduplicated `entire explain` lookups. Use when the user asks what happened, says "tell me why" about a code block, is confused about a section of code, asks "wtf is going on", "why is this like this", "why was this changed", or wants provenance for a specific file block.

Troubleshoot Astronomer production deployments with Astro CLI. Use when investigating deployment issues, viewing production logs, analyzing failures, or managing deployment environment variables.