review-standard
reviewca が review.md を Must/Should/Nit で書き、OK判定条件を付けるための標準。
Discover Data & AI skills, compare source repositories and read the instructions for each workflow.
reviewca が review.md を Must/Should/Nit で書き、OK判定条件を付けるための標準。
1作業=1ディレクトリ(docs//)で、implementedplan.md と tasks.md を作る手順とテンプレ。
Debug canvas layout issues, grid positioning problems, and component overlap. Use when troubleshooting Konva canvas rendering, grid constraints, snap-to-grid behavior, or visual layout mismatches. Includes Canv...
Review code for Visual Layout Builder quality standards including TypeScript patterns, React 2025 best practices, accessibility, and performance. Use when reviewing PRs, checking code quality, or ensuring compl...
Develop and optimize AI prompt strategies for code generation. Use when creating new AI model strategies, optimizing prompts for Claude/GPT/Gemini/DeepSeek/Grok, or improving prompt quality. Includes model-spec...
Write comprehensive unit tests for Visual Layout Builder using Vitest. Use when creating tests for lib/ functions, schema validation, canvas utilities, or any business logic. Follows AAA pattern and project tes...
Create and modify Visual Layout Builder schema components, breakpoints, and layouts. Use when working with types/schema.ts, creating new components, adding breakpoints, or modifying layout configurations. Helps...
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
Generate and maintain the root CHANGELOG.md in a beginner-friendly, analogy-rich format from git state or a commit range.
Codex pickup checklist when starting on a task.
Codex handoff checklist for agents.
Land one PR end-to-end (changelog + thanks, lint, merge, back to main).
Use the screenshot workflow to pick, verify, replace, and verify CI.
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Automate Ghostty terminal sessions via MCP. Use when you need to send commands to terminals, read terminal output, capture screenshots, resize windows, open new tabs/windows, or interact with TUI apps like Neov...
Dapr (Distributed Application Runtime) integration patterns for microservices. Covers Pub/Sub, State Store, Jobs API, Secrets Management, and Service Invocation with HTTP APIs. Full Dapr implementation with all...
Microservices architecture patterns for event-driven systems. Covers service-to-service communication, idempotency, user isolation, event-driven design, and service discovery.
Event-driven architecture patterns with Apache Kafka. Covers event schemas, producer/consumer patterns, partitioning strategies, dead letter queues, and retry mechanisms. Works with Dapr Pub/Sub abstraction.
Build AI agents with OpenAI Agents SDK + Model Context Protocol (MCP) for tool orchestration. Supports multi-provider backends (OpenAI, Gemini, Groq, OpenRouter) with MCPServerStdio. Use this skill for conversa...
RRULE pattern parsing and next occurrence calculation for recurring tasks. Uses python-dateutil for RFC 5545 RRULE support, simplified patterns (daily, weekly, monthly, yearly), and UTC-only time handling.
Infrastructure as Code with Terraform for cloud Kubernetes clusters. Covers OKE (Oracle), AKS (Azure), GKE (Google) provisioning, multi-cloud patterns, and state management.
Kubernetes deployment patterns with Helm charts. Covers deployments, services, ConfigMaps, Secrets, Dapr sidecar injection, health probes, and resource management.
Domain-Driven Design and Clean Architecture implementation guide
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.