Explorar skills

Acione quando o usuário solicitar trabalho de implementação, exploração de repositório, inspeção de dados/logs, busca na base de código, análise de impacto, trabalho de shell com muita verificação, ou mencionar explicitamente 'Codex'. Também acione para subtarefas internas pesadas que o Claude Code normalmente delegaria a um modelo leve/Haiku.

Communicate systems and flows visually using Mermaid (flowchart, sequence, state, ER, class), the C4 model, and diagram-as-code. Use when the user asks to draw a flow, sequence diagram, state machine, ER diagram, C4 model, architecture diagram, or wants Mermaid code for a system, wants to pick a diagram type, or wants to visualize a process as a flowchart. NOT for UI/UX mockups or visual design (u

PPTX 演示文稿创建、编辑与分析。支持：(1) 从零创建演示文稿 (2) 编辑现有内容 (3) 使用模板创建 (4) 添加评论或演讲者备注。Presentation creation, editing, and analysis using html2pptx and OOXML.

Create individual user personas and customer archetypes — with demographics, goals, pain points, behaviors, and empathy maps — to represent the humans a product or system is built for. Use when the user asks to define personas, create user archetypes, describe target users, build empathy maps, or characterize the audience for a product or design decision. NOT for mapping stakeholders across an org

Transform research papers into professional visual schemas. Analyzes paper logic, selects optimal layout patterns, and generates detailed prompts for AI image generation.

Use when the user has a proposal, position, or design and wants it adversarially pressure-tested before committing.

Helps design and implement Model Context Protocol (MCP) server integrations for AI agents.

Funnel workflow for going from "I want an agent that does X" to a deployed, evaluated, cost-monitored agent. Runs through nine phases starting with the is-this-task-agent-appropriate check (agent-project-development), then prompt design with eval criteria first (prompt-engineering), tool design and consolidation (tool-design), architecture selection for multi-step work (multi-agent-patterns), pers

Create and evolve production-ready skills with reusable scripts, references, and validation. Use for new skill creation, skill upgrades, and enforcing consistent metadata and structure.

Systematically test authorized targets for SQL, XSS, SSTI, XXE, command, and request-smuggling injection classes.

Use when verifying that a cross-service change was applied correctly. Checks for stale references, contract mismatches, uncommitted changes, and broken imports across all services.

Generates a professional, comprehensive README.md for any project from its codebase or description.