GitHub
godot-architect
专业的Godot游戏架构设计师，专注于游戏系统架构设计、场景结构规划和状态机架构设计。当用户需要设计新游戏功能、规划场景结构、设计状态机架构或进行系统模块划分时触发此技能。
Skills IA Données et IA
Découvrez les skills Données et IA, comparez leurs dépôts et consultez leurs instructions.
Catégories: Données et IA
Données et IA Effacer les filtres
Explorer
GitHub
create-claude-rules
Claude Rulesファイルを.claude/rules/ディレクトリに作成・管理する。プロジェクト固有のルール、コーディング規約、ワークフロー設定を追加したい場合に使用。
GitHub
pr-review
PRをレビューする。変更されたコードに対してmacOS/Swift/SwiftUI固有の問題を検出し、日本語でフィードバックを提供する。
GitHub
project-conventions
AI 가계부 프로젝트의 코딩 컨벤션 가이드라인. 코드 작성, 리뷰, 리팩토링 시 일관된 스타일을 보장하기 위해 사용. 새 파일 생성, 함수 작성, 타입 정의, 커밋 작성 시 트리거됨.
GitHub
vercel-react-best-practices
Vercel 엔지니어링 팀의 React 및 Next.js 성능 최적화 가이드라인. React/Next.js 코드를 작성, 리뷰, 리팩토링할 때 최적의 성능 패턴을 보장하기 위해 사용. React 컴포넌트, Next.js 페이지, 데이터 페칭, 번들 최적화, 성...
GitHub
web-design-guidelines
웹 인터페이스 가이드라인 준수 여부를 검토하는 UI 코드 리뷰 도구. "UI 리뷰해줘", "접근성 확인해줘", "디자인 감사해줘", "UX 리뷰해줘", "베스트 프랙티스에 맞는지 확인해줘" 등의 요청 시 사용.
GitHub
egenskriven-workflows
Workflow modes and agent behaviors for EgenSkriven task management. Use when configuring strict/light/minimal workflow modes, understanding autonomous/collaborative/supervised agent behaviors, or using the prim...
GitHub
egenskriven
Local-first kanban task manager for AI agent workflows. Use when managing tasks, tracking work, creating issues, or when user mentions tasks, kanban, boards, backlog, or egenskriven.
GitHub
conventional-commit
Create properly formatted conventional commits with type prefixes and optional scope
GitHub
conventional-commit
Create properly formatted conventional commits with type prefixes and optional scope
GitHub
ui-test
Run UI tests using the ui-test-engineer agent with Playwright. Use when testing web UIs, verifying UI functionality, debugging UI issues, or when the user mentions UI testing, browser testing, or end-to-end tes...
GitHub
egenskriven-advanced
Advanced EgenSkriven features including epics, task dependencies, sub-tasks, batch operations, and views. Use when working with blocked tasks, epic management, sub-tasks, batch imports, or complex filtering.
GitHub
python-lint
Validate and auto-fix Python linting, formatting, and type issues using ruff and ty
GitHub
markmap-render
Render markmap (.mm.md) files to HTML for committing. Finds all .mm.md files in the project and runs npx markmap to generate interactive HTML mind maps.
GitHub
skill-creator
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 AI Agent's capabilities with specialized knowledge, workflows, or...
GitHub
discord-gd
Complete Discord.gd knowledge base for creating Discord bots in Godot. Use for Discord API integration, handling messages, buttons, select menus, slash commands, embeds, and Discord interactions in GDScript.
GitHub
dongshan-next-map-development
Expert guide for developing the Dongshan Next Map LBS game, covering 3-layer architecture, Zustand state management, custom Systems (LBS, Save, Quest), and HUD development.
GitHub
plan-mode-arc-gsm8k-improvement
AEGISモデルのARC-Challenge評価改善とGSM8K健全性チェックのためのPlanモード。タイムアウト率・抽出失敗率分析、頑健な回答抽出、データ汚染検査、複数seed評価を実行。
GitHub
plan-mode-aegis-v25-development
AEGIS v2.5開発の包括的Planモード。数学データ収集、形式証明環境構築、GRPO訓練パイプライン、MCP/A2Aエージェント開発、進捗監視を実装。SO(8)四重推論再現のための完全開発ワークフロー。
GitHub
plan-mode
AEGISモデルのARC-Challenge改善、GSM8K健全性検証、GRPO報酬多目的化のための包括的Planモード。頑健な回答抽出、タイムアウト最適化、データ汚染チェック、複数seed評価、汎化性能向上を実装。
GitHub
plan-mode-creation
Planモードの設計・作成・設定を自動化するスキル。AI開発ワークフローのPlanモードを効率的に構築し、チェックポイント管理・進捗監視・エラー回復機能を統合。SO8Tプロジェクト専用に最適化。
GitHub
plan-mode-official-leaderboard-abctest
公式リーダーボード準拠のA/B/Cテストを実行するPlanモードスキル。Phi-3.5-mini-instruct、Borea-phi3.5-instinct-jp、AEGIS-Phi3.5mini-jpv2.4を標準化ベンチマークで比較評価し、統計的有意性を検証。
GitHub
plan-mode-advanced
Create and execute advanced execution plans for complex AI model development incorporating 2024-2026 cutting-edge techniques (DeepSeek GRPO, manifold-constrained architectures, geometric scaling). Use when plan...
GitHub
mathematical-theorem-prover
Implement comprehensive mathematical theorem proving capabilities with SFT+GRPO training, MCP/A2A agent integration, and imatrix quantization protection to surpass Boreas-phi3.5-instinct-jp in formal proof gene...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.