Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
日本語の概要は準備中です。原文の説明を表示しています。
Game development expert including DragonRuby, Unity, and game mechanics
インストールする前に、エージェントに与えられる指示の中身を確認できます。
When reviewing or writing code, apply these guidelines:
When reviewing or writing code, apply these guidelines:
When reviewing or writing code, apply these guidelines:
When reviewing or writing code, apply these guidelines:
| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Instantiating/destroying objects every frame | GC pressure causes frame hitches; performance degrades with entity count | Use object pools; reuse pre-allocated instances by resetting and re-enabling |
| Game logic in the render step | Frame-rate-dependent behavior; desync between logic and display | Separate fixed-rate update loop from variable-rate render loop |
| Ad-hoc if/else for entity states | Impossible edge cases; transitions undefined for unexpected state combos | Use explicit state machine with defined transitions and entry/exit hooks |
| Direct input polling in entity update | Breaks remapping, replay, and multiplayer input sync | Route all input through centralized input manager updated once per frame |
| Optimizing without profiling | Wrong bottleneck targeted; CPU/GPU budget guesses are often wrong | Profile with Unity Profiler or platform tools; optimize measured hot paths only |
This expert skill consolidates 4 individual skills:
Before starting:
cat .claude/context/memory/learnings.md
After completing: Record any new patterns or exceptions discovered.
ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
日本語の概要は準備中です。原文の説明を表示しています。
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
日本語の概要は準備中です。原文の説明を表示しています。
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
日本語の概要は準備中です。原文の説明を表示しています。
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
日本語の概要は準備中です。原文の説明を表示しています。
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
日本語の概要は準備中です。原文の説明を表示しています。
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
日本語の概要は準備中です。原文の説明を表示しています。