Mobile

帮助用户在 macOS 上安装软件，自动处理 Homebrew 依赖。Use when user wants to install, 安装, 下载软件, 装一个, 帮我装, 我想安装, 如何安装 apps on macOS.

Penetration testing for Android/PC applications. Authorized security testing using Metasploit, Drozer, Burp Suite, and custom exploits. Requires explicit authorization. Triggers on: pentest, penetration test, exploit, attack simulation, red team, security assessment, vulnerability exploitation, authorized testing.

Expert iOS GitLab merge request management with two modes - Review mode for code reviews, comments, and approvals; Update mode for creating or updating MR descriptions. Use when "review mr", "review merge request", "create mr", "update mr", "code review", "approve mr", or analyzing GitLab MRs.

Intelligent routing layer that analyzes requests and directs them to the most appropriate Skills, Agents, or Commands

Generate app icons (SVG/PNG) and launcher icons for Android Flutter apps. Use when creating UI icons, launcher icons, or platform-ready icon assets. Handles sizing, formats, and flutter_launcher_icons integration.

Use this at session start to discover what CodeCompass can do. Read .ai/capabilities.json for module map (5 domains, 21+ modules) instead of manual Grep/Glob. Apply when: (1) planning tasks, (2) user asks 'What can CodeCompass do?', (3) before implementing features

Local storage, data sync, and conflict resolution for offline-capable apps.

Create multi-stage Azure Pipelines with deployment gates and approvals. Use when implementing complex deployment pipelines with multiple environments.

Lists files contained in a work-day folder while delegating formatting to the list-files skill. Uses the work-day skill to locate the appropriate folder structure (YYYY-MM Work/YYYY-MM-DD) in Google Drive, then passes the target folder to list-files for table generation. Accepts dates in various formats and automatically detects the correct folder level.

Use this skill if /track:init is called OR you notice the project contains tracking files (CLAUDE_SOURCES.md or CLAUDE_PROMPTS.md). Automatically tracks research sources and major prompts when enabled. Checks ./.claude/.ref-autotrack marker file for activation status and ./.claude/.ref-config for verbosity settings. Appends to CLAUDE_SOURCES.md (WebSearch/WebFetch) and CLAUDE_PROMPTS.md (major requests) using [User]/[Claude] attribution.

Validate Dapr component configs, sidecar annotations, and mTLS settings. Use when: (1) Creating Dapr Component manifests, (2) Adding Dapr annotations to deployments, (3) Configuring pub/sub, state stores, or bindings, (4) Before deploying Dapr-enabled applications, (5) Generating new Dapr components. Validates secrets management (secretKeyRef), scopes, mTLS, sidecar resource limits, and namespace configuration.

Master design patterns and SOLID principles. Learn creational, structural, behavioral patterns, and their real-world applications.

Interacts with Bear note-taking app on macOS via X-Callback-URL. Use when user asks to create Bear notes, search notes, add text to notes, manage tags, capture web pages to Bear, or perform any other Bear note management tasks. Supports note creation, text appending, tag management, note search, and web page capture.

Use this skill after a code PR is merged to integrate approved specs into the source-of-truth, update the retrospective with learnings, and clean up branches. Triggers include "integrate change", "post-merge cleanup", or completing a feature implementation.

Applies project-specific coding conventions and patterns. Use when writing, reviewing, or modifying code to maintain consistency with the codebase style.

Get a second opinion from OpenAI Codex CLI for plan reviews, code reviews, architecture decisions, and hard problems. Use when you need external validation, want to compare approaches, or are stuck on a difficult problem.

Apply professional typography principles to create readable, hierarchical, and aesthetically refined interfaces. Use when setting type scales, choosing fonts, adjusting spacing, designing text-heavy layouts, or when the user asks about readability, font pairing, line height, measure, or typographic hierarchy.

Minimal example skill that turns a natural-language procedure description into a structured list of steps. Serves as the reference pattern for other MOVA skills in this lab.

Get a summary of vault activity over a period. Triggers on "activity summary", "vault activity", "what happened this week", "editing patterns".

Assist with grading by applying rubrics to student work, generating criterion-level feedback, and maintaining consistency across submissions. Use when grading assignments, applying rubrics, or providing feedback. Activates on "grade this", "apply rubric", "provide feedback", or "score student work".