发现 研究与调研 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Complete theming guide for the e-commerce storefront. Documents all styled components and provides instructions for applying new themes. Use when customizing store appearance, changing color schemes, or restyli...
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
Complete D365 Finance & Operations debugging framework. Routes symptoms to correct playbook (Finance, SCM, WMS, Batch, Security, Integration, Performance, Reporting). Activates for D365, Dynamics, AX, voucher,...
Retrieve official library documentation and API references. Use when the user asks for "docs", "API signature", "usage examples", or "how to use" a specific package.
Inspect Supabase database schemas and data. Use when the user asks to "check table", "list columns", or "query data" in Supabase. READ-ONLY.
Build and debug Flutter/Dart apps with Riverpod (codegen), Freezed, and GoRouter. Use when implementing Flutter features, running apps, hot reload/restart, or debugging UI.
Interact with GitHub repositories, PRs, and issues using the `gh` CLI. Use when the user asks to "list PRs", "check out PR", "view issue", or "create release".
Plan and execute complex features using markdown checklists. Use when the user asks to "plan a feature", "create a checklist", or "break down a task".
Use fl_lib stores, widgets, utils, and extensions in Flutter apps. Use when requests mention fl_lib APIs or integration.
Provide accurate, evidence-based answers by referencing sources from documents, textbooks, or research papers. Use when user asks for factual or source-backed responses.
Extract and explain formulas used in Physical AI and Humanoid Robotics from text, lecture notes, or papers. Use when user asks to identify or understand relevant formulas.
Summarize robotics-related text, research papers, or lecture notes into concise, clear, and structured summaries. Use when user asks to condense or simplify robotics content.
Generate clear, measurable, and curriculum-aligned learning objectives for any topic. Use when user asks to define goals, outcomes, or objectives for a lesson or course.
Complete Kitty terminal awareness + control for coding agents: list panes/tabs, read scrollback, map ports→processes, parse per-pane git/last-command metadata (from shell hooks), and send commands/focus panes....
Claude Code operates purely as a manager/architect. It reads, plans, verifies, and reviews code, but NEVER writes or edits files itself. All implementation, fixes, and command execution are delegated to Codex C...
Vertical Slice Architecture (VSA) 向け UI 強化スキル。 Phase 1（spec-kit + カタログ）で生成されたプレーンな .razor ファイルを、 Phase 2 で MudBlazor ベースのリッチな UI に変換する。 アーキテクチャには一切手を触...
Blazor VSA アーキテクチャの実装ミス防止ガード。Handler、Validator、 BoundaryService、Entity などの C# コードを生成・修正する際に自動的に 適用される知識。SaveChangesAsync の禁止、BoundaryService での業務ロジック...
Blazor VSA における Boundary パターンのモデリング支援。UI を持つ機能で Entity.CanXxx() メソッドの設計、Intent 定義、BoundaryService の責務分離を 支援する。AI の学習バイアス（古典 DDD は UI を対象外とする）によ...
Blazor VSA パターンカタログからの適切なパターン選択支援。新機能追加、 CRUD 操作、クエリ実装、状態遷移、バウンダリー設計などの文脈で、 catalog/index.json の ai_decision_matrix に基づいて最適なパターンを 提案する...
Archive completed implementation plans after PR merge. Use when a plan's implementation has been merged to main, or after plan-execute completes on main branch.
Create detailed implementation plans with diagrams and dependency graphs. Use when planning features, refactoring, or multi-step development work before writing code.
Create new Agent Skills with proper structure, templates, and best practices. Use when building custom skills for Claude Code, GitHub Copilot, or other Agent Skills-compatible tools.
Review implementation work at checkpoints during plan execution. Use when verifying phase completion, validating code changes, or performing final plan review.
Generate project documentation including CONTENTS.md navigation files and AGENTS.md instructions. Use when creating documentation structure, project indexes, or AI agent configuration files.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。