$ skills --list
瀏覽並探索 AI 代理技能
瀏覽並探索 AI 代理技能
Showing 44241-44260 of 44357 skills
Use PROACTIVELY when debugging React Native apps. Reads console logs and executes JavaScript in running apps via Metro bundler. Invoke for: app crashes, state inspection, API debugging, error investigation, or running diagnostic code. Requires Metro running (port 8081).
Extracts and writes project constitutional information from documents (PDF, MD, TXT). Focuses exclusively on identifying principles, values, governance structures, and formatting them into a proper project constitution.
Auto-invoked compositional project analysis using φ = ∫(structure × semantics × memory). Analyzes codebase using three integrated layers - structure, semantics, and memory - for understanding project layout, architecture, and accumulated insights.
Installs and manages KASM Workspaces, a container-based VDI platform for streaming desktops to browsers.Supports Ubuntu ARM64, desktop streaming, isolated browser sessions, and remote workspace access.Use when: installing KASM on Ubuntu ARM64, setting up VDI, configuring browser-based desktops, deploying on OCI instances.Keywords: kasm workspaces, VDI, virtual desktop, browser streaming, ARM64, kasm port 8443, container desktop
Playwright E2E testing patterns with chrome-devtools MCP integration.Reference for integration tests, A11y validation, and visual regression.
Use this skill when creating new skills via forced conceptual collision of existing patterns. Duct-tapes jank-builder to super-collider for autopoietic meta-skill generation.
Icon usage patterns using Material Symbols v3. Use when adding icons to buttons, navigation, or status indicators. Covers sizing, accessibility, animations, and color integration with project tokens.
Generate 50-question interactive quizzes using the Quiz component with randomized batching.Use when creating end-of-chapter assessments. Displays 15-20 questions per session withimmediate feedback. NOT for static markdown quizzes.
Generate conventional commit messages based on git diff analysis. Use when you need to create well-structured commit messages following conventional commit format.
Review test cases for Authorization Endpoint. Covers response_type=code, request parameters (scope, client_id, redirect_uri, state, nonce, prompt, display, max_age), and authorization response per OIDC Core 1.0 Section 3.1.2.
Attack and enumerate Active Directory environments using Kerberos attacks (Kerberoasting, ASREPRoasting), credential dumping (DCSync, Mimikatz), lateral movement (PtH, PtT), and BloodHound analysis. Use when pentesting Windows domains or exploiting AD misconfigurations.
Comprehensive guide for AI agents on proactive documentation capture using /docent:tell
Expert in EqualizerAPO configuration file format, parsing, and generation. Use when implementing EAPO config import/export, adding support for new filter types, or debugging config file issues.
MongoDB CLI 工具。直接執行 MongoDB 查詢語法,支援 CRUD、聚合、索引管理。輸出格式:table/json/csv/yaml。預設唯讀模式保護生產環境。
input/ 폴더의 미디어 파일들을 분석하여 YouTube Shorts (9:16, 60~90s)를 자동 생성한다.
Guide for creating effective prompts and instructions for LiveKit voice agents. Use when building conversational AI agents with the LiveKit Agents framework, including (1) Creating new voice agent prompts from scratch, (2) Improving existing agent instructions, (3) Optimizing prompts for text-to-speech output, (4) Integrating tool/function calling capabilities, (5) Building multi-agent systems with handoffs, (6) Ensuring voice-friendly formatting and brevity for natural conversations, (7) Iteratively improving prompts based on testing and feedback, (8) Building industry-specific agents (debt collection, healthcare, banking, customer service, front desk).
Automatically applies when engineering prompts for LLMs. Ensures proper prompt structure, templates, few-shot examples, context management, and injection prevention.
Security audit worker (L3). Scans codebase for hardcoded secrets, SQL injection, XSS, insecure dependencies, missing input validation. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.
Use when user requests to save conversation summary to Obsidian, mentions "总结", "保存笔记", "卡片笔记", or Zettelkasten - creates atomic, well-structured notes following Zettelkasten principles without guessing paths or formats
PostgreSQL MCPでスキーマ確認とread-only分析を行う。集計・意思決定資料が必要な時に使う。