全部能力

Use when analyzing Rspack/Webpack bundles from local `rsdoctor-data.json` and producing evidence-based optimization recommendations.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word…

当用户提供一段梦境文字素材、日记片段、或口述梦境内容，并希望生成视频时触发。触发词包括："梦到"、"梦见"、"做了个梦"、"梦境素材"、"帮我生成视频"、"转成视频"、"dream to video"。也适用于用户直接粘贴一段梦境描述并期望获得视频文件的场景。此技能会将文字转化为视频提示词，自动提交到即梦平台生成，并下…

What-if scenario analyzer for sports. Play-calling recommendations, clock management, substitution patterns, risk/reward calculations.

Implement proven methodologies and tool workflows from top security researchers for effective reconnaissance, vulnerability discovery, and bug bounty hunting.…

Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.

Create, edit, deploy, and interact with agents on TerminalUse. Use when user mentions "tu", "terminaluse", "deploy agent", "create agent", "edit agent",…

Guidelines for using modern Dart features (v3.0 - v3.10) such as Records, Pattern Matching, Switch Expressions, Extension Types, Class Modifiers, Wildcards, Null-Aware Elements, and Dot Shorthands.

Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in…

Experimental NotebookLM harness for listing notebooks, managing sources, asking questions, generating artifacts, and downloading outputs through an installed…

Turn a cleanup packet into one behavior-preserving refactor brief. Use when the user needs to simplify a messy function, component, service, script, or module; split an oversized diff into safer cleanup slices; freeze behavior before touching fragile legacy code; or plan a repeated migration / codemod without changing intended behavior. Route diagnosis to `debugging`, review judgment to `code-review`, validation-program design to `testing-strategies`, bottleneck-led tuning to `performance-optimization`, and pure symbol inventory or impact mapping to `codebase-search`.

bmad-editorial-review-structure — an installable skill for AI agents, published by bmad-code-org/bmad-method.

Create project-context.md with AI rules. Use when the user says "generate project context" or "create project context"

Clinic-architecture-aligned iOS animation craft guidelines for SwiftUI (iOS 26 / Swift 6.2) covering motion tokens, spring physics, gesture continuity, spatial…

Generate CLAUDE.md and AGENTS.md by exploring the codebase

Java 21 language and runtime patterns for modern, safe code. Trigger: When writing Java 21 code using records, sealed types, or virtual threads.

Identify storage buckets that are publicly accessible and may contain sensitive data.

Implements drag-and-drop and sortable interfaces with React/TypeScript including kanban boards, sortable lists, file uploads, and reorderable grids. Use when…

Detect if a web application uses Supabase by analyzing client-side code, network patterns, and API endpoints.

List all storage buckets and their configuration to identify the storage attack surface.