Explore skills

MAGI 1號機 - 科學家視角分析 (Claude Opus 4.5)。作為 MAGI 三機平行討論的一員，從架構、可行性、技術深度角度分析任務。觸發條件：MAGI 系統啟動時自動平行調用。

Task management agent. Auto-invoked for task creation, status tracking, and kanban board operations using Markdown files across lane directories. V2 enforces Kanban Sovereignty constraints preventing manual task file edits.

Use when a task is complete and ready for review, when reviewing a PR, when validating an implementation against its contract, when checking quality before merging, or when a five-axis quality gate is needed before approving code.

(Industry standard: Sequential Agent / Agent as a Tool) Primary Use Case: Delegating a well-defined task to a worker agent, verifying its execution, and repeating if necessary. Inner/outer agent delegation pattern. Use when: work needs to be delegated from a strategic controller (Outer Loop) to a tactical executor (Inner Loop) via strategy packets, with verification and correction loops.

(Industry standard: Parallel Agent) Primary Use Case: Work that can be partitioned into independent sub-tasks running concurrently across multiple agents. Parallel multi-agent execution pattern. Use when: work can be partitioned into independent tasks that N agents can execute simultaneously across worktrees. Includes routing (sequential vs parallel), merge verification, and correction loops.

Audit a file for TODO comments, pending work items, or technical debt markers. Useful for checking code readiness before a commit or reviewing task status. Trigger with "check for todos", "audit for debt", "list pending work", or "scan for TODOs".

This skill helps users organize important life matters: last wishes, post-mortem instructions, account passwords, and messages for loved ones. It's ideal for death preparation, digital legacy management, and leaving messages for family and friends.

三機(Claude/Gemini/Codex)平行分析創意，評估可行性、維護性、安全風險後投票共識

三機(Claude/Gemini/Codex)平行審查代碼，評估邏輯、品質、安全漏洞後投票共識

Automate Todoist task management, projects, sections, filtering, and bulk operations via Rube MCP (Composio). Always search tools first for current schemas.

Organize a MindTracer vault, an append-only voice/AI conversation log produced by the MindTracer CLI. Use this skill when the user asks to summarize, cluster, or extract topics from their vault.

Protocol for @feedback annotations in source code. Use when the user mentions @feedback, addresses feedback, provides inline feedback, or encounters @feedback markers during any task.