GitHub
react-best-practices
Vercel React/Next.jsパフォーマンス最適化 - 45ルール8カテゴリ、ウォーターフォール排除からバンドル最適化まで
☆ 0View skill
Blockchain AI Skills
Discover Blockchain skills, compare source repositories and read the instructions for each workflow.
Categories: Blockchain
Blockchain Clear filters
Browse skills
GitHub
load-guidelines
ガイドライン自動読み込み - プロジェクトの技術スタックを検出し、必要なガイドラインのみをセッションに適用。トークン節約。
☆ 0View skill
GitHub
ui-skills
UI Skills - Tailwind CSS/motion/react特化のエージェント向けUI構築制約
☆ 0View skill
GitHub
session-mode
セッションモード切替 - strict/normal/fast でGuard関手の動作を変更。Serena Memoryで状態永続化。
☆ 0View skill
GitHub
terraform
Terraform IaC設計 - モジュール設計、状態管理、セキュリティベストプラクティス
☆ 0View skill
GitHub
microservices-monorepo
マイクロサービス・モノレポ設計 - サービス分割、通信パターン、モノレポ構成
☆ 0View skill
GitHub
api-design
API設計 - REST/GraphQL設計原則、バージョニング、エラーハンドリング、ドキュメント
☆ 0View skill
GitHub
grpc-protobuf
gRPC/Protobuf開発 - proto定義、コード生成、バックエンド実装のワークフロー
☆ 0View skill
GitHub
uiux-review
UI/UXレビュー - Material Design 3 + WCAG 2.2 AA + Nielsen 10原則で実装に直結するレビュー
☆ 0View skill
GitHub
docs-test-review
ドキュメント・テスト品質レビュー - コメント品質、API仕様、テストの意味、カバレッジを統合評価
☆ 0View skill
GitHub
docker-troubleshoot
Dockerトラブルシュート - lima/Docker Desktop接続エラー、コンテナ起動失敗の診断・解決
☆ 0View skill
GitHub
guideline-maintenance
ガイドラインメンテナンス - 最新ドキュメントからClaude向け実践的レシピへ変換・更新
☆ 0View skill
GitHub
mcp-setup-guide
MCP設定ガイド - Claude Code向けMCPサーバーのセットアップ・トラブルシュート
☆ 0View skill
GitHub
github-issues
Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, or mana...
☆ 0View skill
GitHub
weekly-report
MLシステム開発共同研究プロジェクトの週報を自動作成するスキル。先週の週報をベースにNotionから今週の更新情報を収集し、差分を反映して新しい週報をNotionに発行する。Use when: (1) 週報を作成したい、(2) weekly report...
☆ 0View skill
GitHub
skill-improve
Improve existing skills. Triggers include "improve this skill", "skill feels shallow", "upgrade skill", or when self-evaluating skill quality. Codifies the self-eval → research → rewrite → validate pattern.
☆ 0View skill
GitHub
fanout
This skill should be used for multi-perspective analysis through parallel copilot sessions. Triggers include "analyze from multiple angles", "what are the gaps/patterns/friction", "explore before deciding", pre...
☆ 0View skill
GitHub
context
Context preservation across sessions, checkpoint monitoring, and agent handoffs. Triggers include "save context", "checkpoint", "hand off", "relay context", or when transitioning between sessions.
☆ 0View skill
GitHub
auto
This skill should be used for autonomous single-repo orchestration. Triggers include "use auto", "autonomous mode", "work on this repo", or when starting a deep work session. LLM ideation discovers work, copilo...
☆ 0View skill
GitHub
skill-compose
This skill should be used when orchestrating multiple skills together for complex workflows. Triggers include "chain these skills", "use X then Y skill", "multi-skill workflow", "which skills", "suggest skills"...
☆ 0View skill
GitHub
issue-context
Enrich issues with intelligent codebase context, architecture diagrams, and agent-ready prompts. Use for preparing issues for implementation or transforming vague tickets into rich specifications.
☆ 0View skill
GitHub
skill-improve
This skill should be used when improving existing Claude Code skills. Triggers include "improve this skill", "skill feels shallow", "upgrade skill", or when self-evaluating skill quality. Codifies the self-eval...
☆ 0View skill
GitHub
emil-kowalski
Design philosophy for UI components, animations, and interactions. Triggers include "make it feel Linear", "emil style", "tasteful animation", or when designing interactive components that need craft and restra...
☆ 0View skill
GitHub
loop
This skill should be used for autonomous work on complex tasks with ZERO context required. Triggers include "start a loop", "work autonomously", "before I sleep", "take this and run with it", or when claude det...
☆ 0View skill
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.