LoRAIro

Maintain an agent-created LoRAIro pull request after creation or after draft-to-ready transition: mark reviewable draft PRs ready, poll CI and review comments with gh, repair failures in the same worktree/session, reply in Japanese, escalate design loops, and squash merge when safe. Use after creating PRs or when asked to continue PR maintenance automation.

Run LoRAIro PR maintenance to completion automatically after an agent creates a PR or a draft PR becomes ready for review: keep polling CI and bot review with gh, repair failures and reply in Japanese in the same worktree, escalate design loops, and squash merge when safe, without waiting for a human to restart each poll cycle. Use right after an agent-created PR exists or transitions draft-to-ready. Do NOT use for human-authored PRs, and do NOT redefine repair/merge/escalation policy here (that lives in agent-pr-maintainer).

Capture LoRAIro design from the wireframes operation prototype or claude.ai/design recreations correctly. Use when syncing/mirroring design, reconciling Qt (.ui) or the DS AppShell with the design, or when nav/tab order, layout, or grouping looks off between the app and the prototype. The prototype's effective state is produced by render-time JS (e.g. restructureNav), so static-HTML grep alone misses it.

Use this skill to generate well-branded interfaces and assets for LoRAIro (a Japanese desktop tool for preparing image datasets for LoRA / fine-tune training), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

PySide6 widget technical implementation for LoRAIro GUI. Covers Signal/Slot patterns, Direct Widget Communication, Qt Designer integration, and async workers. For design intent and aesthetics, use interface-design skill first.

Interface design skill for dashboards, admin panels, apps, and tools. NOT for marketing design. Provides design intent, domain exploration, craft principles, and component-driven design-tool↔code sync. For PySide6/Qt technical implementation, use lorairo-qt-widget skill.

Maintain a directory of markdown docs as an Open Knowledge Format (OKF) bundle in any project: ensure each concept file has valid OKF frontmatter (required `type`, plus optional title/description/tags/timestamp), keep frontmatter the single source of truth, and regenerate the derived index.md (and an optional human-readable table) from it. Use when adding/editing concept docs (ADRs, knowledge bases, glossaries) or when a bundle's index looks stale. Project-specific drift detection stays in the project.

Before implementing a feature in LoRAIro, hear out the requirement, then research existing libraries / tools / local_packages that already solve it. Use when scoping a new feature, evaluating build-vs-reuse, or asked to find existing solutions before writing code.

Library research via web search and long-term memory via OpenClaw LTM. OpenClaw may enrich stored content using Context7/Perplexity.

LoRAIro long-term memory via OpenClaw webhook (/hooks/lorairo-memory). Store, de-duplicate, and retrieve project memories from Notion DB "LoRAIro-Long-Term Memory (Shared)".

SQLAlchemy repository pattern for LoRAIro: type-safe transactions, session management, ORM best practices. Use when creating repositories or implementing data persistence patterns.

Generate pytest unit, integration, and GUI tests for LoRAIro with fixtures, mocks, 75%+ coverage, and pytest-qt for PySide6. Use when creating test suites or ensuring code quality.

Optimize CLAUDE.md files using progressive disclosure: reduce bloat, move details to references, extract reusable patterns into skills, improve context efficiency. Use when CLAUDE.md is too long or needs restructuring.

GitHub operations via gh CLI and GitHub API: create/view/merge PRs, manage issues, query API endpoints, handle workflows in enterprise or public GitHub environments.

Establish QA testing processes: test strategies, Google Testing Standards, P0-P4 bug tracking, OWASP security, quality metrics, 90% coverage targets. Includes master prompts for autonomous execution and third-party QA team handoff documentation.

Refactor module-level imports of heavy native dependencies (torch, tensorflow, jax) to function-internal lazy imports. Use when a library import triggers SIGSEGV or slow startup in environments where the native dep cannot fully initialize (e.g., CUDA driver absent, triton C-extension segfault, missing GPU). Predicts test-side effects from removed module attributes.

Transform vague prompts into precise specifications using EARS (Easy Approach to Requirements Syntax) methodology. Use when requirements are loose, ambiguous, or need enhancement for AI-generated code, products, or documents.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

SQLAlchemy の効率的なクエリパターン集。N+1回避、サブクエリ、バルク操作、インデックス活用、EXPLAIN解析など、LoRAIroのSQLiteデータベースに特化したクエリ最適化ガイド。Use when writing new queries, optimizing slow queries, or reviewing database access patterns.