Structured implementation planning for multi-step development tasks. Use when you have a spec or requirements and need to break work into executable steps.

Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans in current session, when tasks need fresh subagent context to avoid...

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task...

Root cause analysis for debugging. Use when bugs, test failures, or unexpected behavior have non-obvious causes, or after multiple fix attempts have failed.

Assesses and responds to incoming code review feedback on PRs (reviewer comments, requested changes), especially when suggestions are unclear, technically questionable, or scope-expanding. Use...

Disciplined plan execution for implementation tasks. Use when executing a saved implementation plan, following step-by-step instructions from a plan document.

|

Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes',...

Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes',...

>

|

에이전트/스킬 실행 기여도를 분석하고 리포트를 생성합니다. stream.jsonl의 실행 로그를 파싱하여 호출 횟수, 성공률, 순위를 계산합니다. 내장 에이전트(general-purpose, Explore, Plan 등)는 제외하고 커스텀 에이전트/스킬만 분석합니다. "기여도 분석해줘", "이주의 에이전트", "에이전트 통계" 등의 요청 시 사용합니다.

Feature-first init: create or reuse worktree/branch and seed per-feature context. Git-aware and idempotent.

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

Fully autonomous TDD with strict guardrails. Use when you want the AI to drive the entire RED-GREEN-REFACTOR cycle independently while maintaining TDD discipline.

|

|

|

|-

选题系统主控Agent。协调热点采集、选题生成、选题审核三个环节，支持迭代直到产出合格选题。触发方式：(1)"开始今日选题"启动完整流程 (2)"今日AI热点"只采集热点不生成选题 (3)"我有一个选题"进入单个选题分析 (4)"推荐一些好的选题"直接输出推荐。输出保存到Obsidian选题库。