數據與 AI

Executa CodeRabbit CLI em modo prompt-only para revisar alterações locais, identificar issues, planejar correções e validar com testes antes do commit

Create Mermaid diagrams (activity, deployment, sequence, architecture) from text descriptions or source code. Use when asked to "create a diagram", "generate mermaid", "document architecture", "code to diagram", "create design doc", or "convert code to diagram". Supports hierarchical on-demand guide loading, Unicode semantic symbols, and Python utilities for diagram extraction and image conversion.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

ARCHIVE REFERENCE ONLY. Superseded by active `campaign-page-copy` skill. Use this as inspiration, not for invocation in the orchestrated flow.

Frappe DocType creation patterns, field types, controller hooks, and data modeling best practices. Use when creating DocTypes, designing data models, adding fields, or setting up document relationships in Frappe/ERPNext.

코드 작성이 필요할 때 coder-agent 활용 가이드. 직접 코드 작성 대신 위임

Use when user requests code review with multiple perspectives, wants parallel review from different models, or uses trigger words: super-review, 超级审查, 并行审查, 全面 review

Validate HTML5 structure and basic syntax. BLOCKING quality gate - stops pipeline if validation fails. Ensures deterministic output quality.

Master-level fullstack software engineering with deep backend expertise. Use when building production-grade APIs, database architectures, authentication systems, microservices, or any backend-heavy application. Triggers on: (1) API design and implementation, (2) Database schema design and optimization, (3) Authentication/authorization systems, (4) System architecture decisions, (5) Performance optimization, (6) Error handling and logging, (7) Testing strategies, (8) DevOps and deployment, (9) Security hardening.

Draft detailed engineering specs from an approved PRD. Use when generating or updating the engineering specification for a feature, before implementation begins.

End-to-end testing for Blazor applications using Playwright for .NET. Use when writing E2E tests, creating test infrastructure, testing MudBlazor components, handling Blazor WebAssembly loading, debugging test failures, or setting up CI/CD test pipelines.

Master MongoDB indexing and query optimization. Learn index types, explain plans, performance tuning, and query analysis. Use when optimizing slow queries, analyzing performance, or designing indexes.

Validate implementation against test cases and acceptance criteria. Use when checking if code works correctly, validating against user-provided test cases, or verifying acceptance criteria are met. Gets test cases from user input or previous workflow stages.

Turn ideas/brain dumps into a structured project brief (problem, goals, scope, milestones, success criteria). Use when starting a project.

Master programming fundamentals, algorithms, data structures, and multiple languages. Covers Python, Java, Go, Rust, C++, Kotlin, Bash, and computer science essentials for every developer.

Generate Kubernetes YAML manifests for deployments, services, ingress, configmaps, and other resources with best practices. Triggers on "create Kubernetes manifest", "generate k8s yaml", "kubernetes deployment for", "k8s config".

Performs intelligent compliance audits for software projects. Automatically detects which regulatory frameworks (GDPR, HIPAA, PCI-DSS, CCPA, SOC 2) apply based on project analysis and user context. Provides tiered reports with executive summaries and detailed technical findings. Use when the user asks about compliance, regulatory requirements, security standards, data protection, or wants to audit their codebase for legal/regulatory adherence.

Generate reactive iOS list screens with RxSwift MVVM Input/Output pattern. Creates complete list features with reactive bindings, pagination (date range/page number), ViewModel, ViewController, Navigator, and tests for iOS reactive projects. Use when "create reactive list", "generate reactive list", "new reactive list screen", "create rxswift list", or "generate list with rxswift".

Expert prompt engineering for LLMs and AI agents. Use when users request help writing, reviewing, or improving prompts for chatbots, AI agents, system prompts, instruction sets, or any LLM-based application. Applies research-backed techniques to minimize hallucinations and maximize reliability.

生成GOAL/SubPlan依赖DAG和关键路径分析，并执行SubPlan划分。当需要分析技术依赖、业务依赖、识别关键路径、发现并行执行机会、执行SubPlan分配时使用。基于GOAL的dependencies字段和业务逻辑分析生成Mermaid依赖图和SubPlan划分方案。