Thorough, adversarial security review of API endpoints, UI flows that call those endpoints, and any database-interacting code. Use when the user asks for a security review, permission/authorization audit, red-team style assessment, or vulnerability analysis. Assume access to source code and a running system; perform threat modeling and check current vulnerabilities relevant to the stack.

This skill should be used when the user asks to "apply a layout", "arrange nodes", "organize the graph", "apply hierarchical layout", "use organic layout", "use tree layout", or mentions layout algorithms like "HierarchicalLayout", "OrganicLayout", "TreeLayout", "CircularLayout", "OrthogonalLayout", or "RadialLayout".

Convert an ML PRD into prd.json for ML-Ralph. Use when you have an ML PRD and need prd.json. Triggers on: convert this prd, turn this into ml-ralph format, create prd.json from this, ralph json.

This skill should be used when the user asks to "build a graph from data", "load data into a graph", "import JSON into yFiles", "create nodes from an array", "use GraphBuilder", or mentions "data to graph", "import data", "business data", "GraphBuilder", "TreeBuilder", or "AdjacencyGraphBuilder".

This skill should be used when the user asks to "add tooltips", "add a context menu", "implement graph search", "add an overview", "handle click events", "handle selection changes", or mentions "tooltip", "context menu", "search", "GraphOverviewComponent", "click handler", "selection changed", "hover effects", or "interactive features".

This skill should be used when the user asks to "create a custom node style", "implement NodeStyleBase", "create a custom node visualization", "implement createVisual", "implement updateVisual", "render nodes with SVG", or mentions "custom rendering", "TaggedSvgVisual", or "visual caching".

This skill should be used when the user asks to "implement viewport culling", "implement isVisible", "implement getBounds", "create a group node style", "optimize rendering performance", or mentions "isVisible", "getBounds", "group node style", "folder tab", "viewport culling", or "rendering outside layout bounds".

This skill should be used when the user asks to "make a node style configurable", "bind node data to visuals", "render text in a node style", "use node.tag in a style", or mentions "configurable style", "node.tag", "data binding", "TextRenderSupport", or "text rendering in custom style".

This skill should be used when the user asks to "implement hit testing", "add custom click area", "implement isHit", "implement getOutline", "fix edge cropping", or mentions "hit testing", "isHit", "getOutline", "edge cropping", or "edge connection points" in a node style context.

Standardize issue and pull request triage so incoming work is labeled, prioritized, and routed consistently.

**Prerequisites**: Load `plugins/context/capabilities/events_skills.md` first

Safe cleanup + de-bloat operator for SYSopGPTWSL. Inventories candidates, proposes an action plan, and only deletes after explicit user confirmation. Defaults to repo-scoped, reversible moves into `sysop/out/janitor_trash/`. Use when the user says “clean up”, “cleanup”, “delete”, “remove duplicates”, “free disk space”, “declutter”, or “bloat”.

Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture optimization.

Build the regulation/knowledge update pipeline (official sources -> snapshots -> structured rulesets/templates -> admin approval -> active). Use for keeping visa rules and document requirements up-to-date without code hardcoding. (키워드= 규정 최신화, 공식 정보, 스냅샷, 검수/승인, 룰셋/템플릿 업데이트)

Supabase RLS パフォーマンス最適化。セキュリティ境界と最適化フィルタの区別、および堅牢な関数定義を規定。

GitHub Copilot CLIをサブエージェントとして活用し、コードベースの解析・調査を行う。 以下の場面で使用: (1) /copilot コマンドで明示的に呼び出された場合 (2) コードベースの広範な調査が必要で、別視点からの分析が有用な場合 (3) 特定の実装パターンや設計についてセカンドオピニオンが欲しい場合

Scans codebases and dependencies for known vulnerabilities and security issues

Verifies Definition of Done checks and generates a DoD report.

Use when creating or updating CLAUDE.md files for projects or subdirectories - covers top-level vs domain-level organization, capturing architectural intent and contracts, and mandatory freshness dates

Analyzes and optimizes database queries for performance and efficiency