Instructions for any AI coding agent working on this project.
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Instructions for any AI coding agent working on this project.
Horizontal Gene Transfer protocol for skills. Synchronizes best practices and architectural patterns across the skill library.
Find and install agent skills with `npx playbooks find skill` and `npx playbooks add skill`. Use whenever a skill needs to be discovered or installed.
>
This directory contains documentation and resources for the autogenlib subsystem.
'Concurrent investigation of independent failures. Use when multiple unrelated issues need parallel resolution.'
Disable autonomous loop mode immediately. TRIGGERS - ru stop, stop autonomous, disable loop, end autonomous mode.
Isolate root causes and propose targeted fixes with clear validation steps.
TAKT ピースエンジン。Agent Team を使ったマルチエージェントオーケストレーション。ピースYAMLワークフローに従ってマルチエージェントを実行する。
实现离散点Hough变换算法，输入包含浮点数的坐标点，输出检测到的直线斜率和截距，不使用MATLAB自带函数
Compare two competing PRs implementing the same feature, identify strengths of each, and combine the best parts into a single branch. Use when comparing PRs, combining implementations, cherry-picking between PRs, or resolving competing approaches.
>
Async agents in tmux sessions with optional git worktree isolation.
Repo guardrail check and repair.
Autonomously diagnose Magento 2 bugs from a symptom or error — reads logs, checks system state, identifies root cause, and produces a concrete fix plan.
Autonomous diagnose-research-fix-verify loop — up to 5 attempts before human escalation
URDF/Xacro 创建技能 - URDF 语法、宏定义、传输配置、ROS2 控制器
模型-based 强化学习技能 - World Models、MPC、PlaNet、MuZero 实现
人形机器人 SDF/XACRO 模型开发技能 - 双足机器人模型、全身关节配置、平衡控制、环境交互
地瓜机器人旭日系列 - X3M X5 BPU 机器人开发
机器人 SDF 建模技能 - SDF 模型结构、链接关节、摩擦阻尼、ROS2 gazebo_ros
系统架构设计 — 模块划分、接口定义、状态机设计、故障诊断树，适用于 ROS2 机器人应用架构
Mujoco 建模技能 - MJCF 模型、关节驱动、接触参数、ROS2 Mujoco 桥接
> **版本演進**：
强化学习 ROS2 集成技能 - Gazebo/Isaac Gym 训练环境、ROS2 消息、行动服务器
See CLAUDE.md for project architecture, commands, and conventions.
本文介绍了一篇名为《XSKILL: Continual Learning from Experience and Skills in Multimodal Agents》的论文。该论文提出了一种名为**XSKILL**的双流框架，旨在解决多模态智能体在开放环境中工具使用效率低和编排灵活性差的问题。XSKILL通过从过去的执行轨迹中持续学习两种互补的可重用知识——**经验（Experiences）*
> **Definition**: a person who acts on behalf of another person or group
When `/color-mining` is invoked with depth > 4, spawn parallel Task agents for maximum throughput.
Job descriptions, interview scorecards, take-home assignments, and evaluation rubrics.
>-
Embed claude-sub-proxy as an internal service within another project. Minimal footprint — 4 JS files + config, running on localhost with no external exposure.
Distribute your agent's native token to Bankr Club NFT holders daily, proportional to how many NFTs each holder owns. Holders with more NFTs get more of your token.
Smart notification routing for AI agents across multiple channels with urgency-based escalation and timezone awareness.
Master 智能命令中心等效规则 - 实现与 /master 相同的效果和功能，支持意图解析、智能路由、规则/技能/脚本调用、21种AI人格
Spawn claude, codex, or gemini CLI workers in tmux panes for parallel task execution
<!--
Manually write response back to Claude. Use if read-task did not auto-complete or to finalize response.
Read and execute task delegated from Claude. Use when user says read task, get task, or pick up claude task.
User flow design, micro-interactions, and interface behavior patterns with state management for all interaction conditions. Use when designing natural interactions, feedback systems, or handling error states.
Product vision, roadmap development, and go-to-market execution with structured prioritization frameworks. Use when evaluating features, planning product direction, or assessing market fit.
Instructions for AI agents working with this dotfiles repository.
Task and Event objects: polymorphic WhatId/WhoId, Activity object model, ActivityHistory vs OpenActivity, activity timeline customization, bulk task creation, Einstein Activity Capture boundaries. NOT for Calendar sharing (use calendar-sharing-setup). NOT for Email-to-Case (use case-management-setup).
Configure and manage Field Service Lightning work orders: work types, work order line items, service appointments, status flow, and auto-creation via maintenance plans. NOT for case management, resource scheduling optimization, or dispatcher console configuration.
<!-- FOR AI AGENTS - Human readability is a side effect, not a goal -->
Add or refine depth through elevation systems, raised and inset surfaces, layered overlap, and meaningful shadow behavior so interfaces feel structured instead of flat. Use when the user mentions depth, elevation, shadows, layering, flat cards, pressed states, drag feedback, or inset controls.
Brand strategist AI — identity, archetype, positioning, voice, brand book สำหรับธุรกิจไทย
ที่ปรึกษาธุรกิจ SME + startup ทำ SWOT, Business Canvas, Porter 5 Forces, pitch deck, และ 3-year forecast
เขียนประกาศขาย/เช่า, virtual tour script, neighborhood analysis, CMA สำหรับบ้าน/คอนโด/ที่ดินในไทย
Self-help mental wellness coach — daily journaling prompts + gratitude practice + emotional regulation tools + thought reframing สำหรับคนทั่วไป (ไม่ใช่ clinical therapy)