Token导航 LogoToken导航TokenDH.com
前端设计需要联网github未标认证来源可访问许可证需确认审计通过

master-architect建筑师大师

Agent Skill

master-architect 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

238

周安装

10

GitHub Stars

2

下载量

83
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:master-architect(建筑师大师)
来源仓库:https://github.com/cycleuser/skills
仓库路径:skills/master-architect
安装命令:
npx skills add https://github.com/cycleuser/skills --skill master-architect
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/cycleuser/skills --skill master-architect

简介

master-architect 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理时使用。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限和维护状态。
  • 使用前建议核实是否会触发联网、命令执行或文件读写操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Master Architect

The supreme architect agent for complex software development projects.

Philosophy

┌─────────────────────────────────────────────────────────────────────────┐
│                        MASTER ARCHITECT                                  │
│                    "Excellence Through Iteration"                        │
├─────────────────────────────────────────────────────────────────────────┤
│                                                                          │
│    ┌──────────┐    ┌──────────┐    ┌──────────┐    ┌──────────┐        │
│    │ ANALYZE  │───▶│  DESIGN  │───▶│ DECOMPOSE │───▶| ITERATE  │        │
│    │          │    │          │    │           │    │          │        │
│    └────┬─────┘    └────┬─────┘    └─────┬─────┘    └────┬─────┘        │
│         │               │                │               │              │
│         │               │                │               │              │
│    ┌────▼─────┐    ┌────▼─────┐    ┌─────▼─────┐    ┌────▼─────┐        │
│    │ QUALITY  │    │ QUALITY  │    │  QUALITY  │    │ QUALITY  │        │
│    │  GATE 1  │    │  GATE 2  │    │   GATE 3  │    │  GATE 4  │        │
│    └────┬─────┘    └────┬─────┘    └─────┬─────┘    └────┬─────┘        │
│         │               │                │               │              │
│         └───────────────┴────────────────┴───────────────┘              │
│                                   │                                      │
│                            ┌──────▼──────┐                               │
│                            │  INTEGRATE  │                               │
│                            │   & DELIVER │                               │
│                            └─────────────┘                               │
│                                                                          │
└─────────────────────────────────────────────────────────────────────────┘

Phase 1: Requirement Analysis

Objective: Achieve deep understanding of the task, its context, constraints, and success criteria.

Process: The requirement analysis phase proceeds through four key activities. First, stakeholder analysis identifies who the users are, what pain points they experience, and what outcomes they expect. Second, constraint mapping documents technical constraints around languages, frameworks, and platforms, along with resource constraints for time, budget, and personnel, plus quality constraints for performance, security, and usability. Third, success criteria definition establishes measurable outcomes, acceptance thresholds, and validation methods. Fourth, risk assessment identifies technical risks, integration risks, and timeline risks.

Quality Gate 1 checks that all user personas are documented, no constraints remain unresolved, all metrics are quantified, and all high risks have mitigation plans. Exit condition: All gate criteria passed. Architecture review approved.

Phase 2: Architecture Design

Objective: Create the system blueprint with clear module boundaries and interfaces.

Process: The architecture design phase creates a comprehensive system blueprint. The system blueprint includes a high-level architecture diagram, component responsibilities, and data flow patterns. Module boundaries are defined with single responsibility per module, clear interface contracts, and a dependency graph. Technology decisions cover language and framework selection with rationale, library choices with alternatives considered, and infrastructure requirements. Non-functional design addresses performance targets, scalability approach, and security model.

Architecture Documentation Template

The architecture document should follow a standard structure. Section 1 provides an overview with one paragraph describing the system's purpose and approach. Section 2 presents the high-level design with an architecture diagram. Section 3 details module decomposition, defining for each module its responsibility and dependencies. For example: Core handles business logic with no dependencies, API provides external interface depending on Core, CLI offers command interface depending on API, and GUI provides graphical interface depending on API. Section 4 documents interface contracts including API interface specifications and data model definitions. Section 5 describes the technology stack with rationale for each layer: Python 3.10+ for backend due to rich ecosystem and rapid development, Flask for web due to being lightweight and flexible, PySide6 for GUI due to cross-platform native feel. Section 6 specifies quality attributes including performance targets (response time under 100ms), scalability targets (handle 10,000 concurrent users), and security requirements (input validation, output sanitization).

Quality Gate 2 verifies that each module has single responsibility (module cohesion), no circular dependencies exist (coupling analysis), all interfaces are documented (interface clarity), and all technology choices are justified (technology rationale). Exit condition: Architecture review approved by stakeholder simulation.

Phase 3: Task Decomposition

Objective: Break architecture into granular, actionable sub-tasks with clear dependencies.

Process: The task decomposition phase transforms the architecture into actionable work items. Feature extraction lists all features from requirements, prioritizes them by value and risk, and maps features to modules. Task breakdown converts each feature into multiple tasks, with each task targeting under 4 hours of work and clear completion criteria. Dependency graph builds a task dependency tree, identifies the critical path, and plans parallel execution opportunities. Iteration planning assigns iteration targets, defines iteration scope, and sets quality targets per iteration.

Task Decomposition Template: For each module and feature, define the priority (High/Medium/Low), dependencies (list of prerequisite features), and estimated complexity (Simple/Medium/Complex). Then break into sub-tasks with ID, description, time estimate, and completion criteria. Finally, create an iteration plan grouping tasks into logical iterations.

Quality Gate 3 verifies all tasks are under 4 hours (task granularity), no ambiguous dependencies exist (dependency clarity), all features are mapped to tasks (coverage), and the critical path is identified and documented. Exit condition: Task breakdown reviewed and approved.

Phase 4: Iterative Development

Objective: Develop each module through rigorous iteration until excellence.

Iteration Cycle:

┌─────────────────────────────────────────────────────────────────────┐
│                    SINGLE MODULE ITERATION                           │
├─────────────────────────────────────────────────────────────────────┤
│                                                                      │
│    ┌──────────┐    ┌──────────┐    ┌──────────┐    ┌──────────┐   │
│    │  BUILD   │───▶│  TEST    │───▶│ EVALUATE │───▶│ REFINE   │   │
│    │          │    │          │    │          │    │          │   │
│    └──────────┘    └──────────┘    └──────────┘    └──────────┘   │
│         │               │               │               │          │
│         │               │               │               │          │
│         │               │               ┌───────┐       │          │
│         │               │               │SCORE  │       │          │
│         │               │               │≥ 90?  │       │          │
│         │               │               └───┬───┘       │          │
│         │               │              YES  │  NO        │          │
│         │               │               ┌───┴───┐       │          │
│         │               │               ▼       ▼       │          │
│         │               │          [DONE]  [NEXT       │          │
│         │               │                   ITERATION] │          │
│                                                                      │
└─────────────────────────────────────────────────────────────────────┘

Iteration Scoring: The iteration uses a weighted scoring system across four metrics. Test coverage carries 30% weight with a target of 80% or higher. Code quality carries 25% weight targeting a lint score of zero. Functionality carries 25% weight requiring all tests to pass. Documentation carries 20% weight requiring completeness. Minimum score to proceed: 90/100.

Iteration Report Template: Each iteration report documents build summary (files created, modified, lines added), test results (tests run, passed, coverage percentage), quality metrics (lint errors, type errors, complexity score), the overall score, improvements applied, and next iteration focus areas.

Quality Gate 4 requires module score of 90 or higher, test coverage of 80% or higher, 100% tests passing, and complete documentation. Exit condition: Module achieves excellence score. Proceed to next module.

Phase 5: Integration & Validation

Objective: Ensure all modules work together coherently.

Process: The integration and validation phase verifies cross-module coherence. Interface validation verifies all contracts are honored, tests inter-module communication, and validates data flow. Integration testing covers end-to-end test scenarios, edge case coverage, and error handling verification. Performance validation includes load testing, stress testing, and resource usage profiling. User acceptance involves scenario walkthroughs, usability assessment, and documentation review.

Quality Gate 5 requires all integration tests to pass, performance targets to be met, user scenarios to be validated, and error handling to be complete.

Phase 6: Documentation Generation

Objective: Produce documentation compliant with all skill standards.

Documentation Checklist: Code-level documentation includes README.md in English, README_CN.md in Chinese, API documentation, code comments, and type hints. Architecture-level documentation includes system architecture document, module dependency diagram, interface specifications, and data model definitions. User-level documentation includes installation guide, user manual, troubleshooting guide, and FAQ. Development-level documentation includes CONTRIBUTING.md, development setup guide, testing guide, and release notes template.

Skill Compliance Matrix: Different skills have different documentation requirements. The python-project-developer skill requires ToolResult pattern documentation, CLI flags, and tests. The software-planner skill requires README sections and sample data. The academic-writer skill is needed only if paper documentation is required. |

Commands Reference

/architect design

Execute complete architecture design workflow.

/architect design "Build a text classification system with CLI and GUI"

→ Phase 1: Requirement Analysis
  - Analyzing stakeholders...
  - Mapping constraints...
  - Defining success criteria...
  ✓ Gate 1 passed

→ Phase 2: Architecture Design
  - Creating system blueprint...
  - Defining module boundaries...
  ✓ Gate 2 passed

→ Phase 3: Task Decomposition
  - Breaking into 15 tasks...
  - Building dependency graph...
  ✓ Gate 3 passed

→ Ready for iterative development
  Use /architect iterate <module> to begin

/architect phase

Execute a specific phase.

/architect phase 2

→ Executing Architecture Design phase
  - Creating system blueprint...
  - Defining module boundaries...
  - Documenting interfaces...
  ✓ Phase 2 complete

/architect iterate

Iterate on a specific module.

/architect iterate core

→ Iteration 1/?
  - Building...
  - Testing...
  - Score: 75/100
  → Improvements needed, continuing...

→ Iteration 2/?
  - Building...
  - Testing...
  - Score: 88/100
  → Improvements needed, continuing...

→ Iteration 3/?
  - Building...
  - Testing...
  - Score: 92/100
  ✓ Module complete!

/architect status

Show current architecture status.

Project: Text Classification System
Status: Phase 4 - Iterative Development

Modules:
  ├── core        [██████████] 92% ✓
  ├── api         [████████░░] 80% → iterating
  ├── cli         [░░░░░░░░░░] 0%  pending
  └── gui         [░░░░░░░░░░] 0%  pending

Current Iteration: api - Iteration 2
Next Module: cli

Overall Progress: 43%

/architect review

Review and validate current architecture.

→ Architecture Review

✓ Module cohesion: Good
✓ Interface contracts: Clear
✓ Test coverage: 85%
✓ Documentation: Complete

⚠ Warnings:
  - API module has 2 TODOs
  - Performance not yet validated

→ Recommendation: Address warnings before integration phase

Rules

Integration with Other Skills

The master-architect skill integrates with other skills at specific points. The python-project-developer skill provides code structure and the ToolResult pattern. The software-planner skill defines documentation format and project structure. The iteration-manager skill manages per-module iteration cycles. The academic-writer skill is consulted if paper documentation is needed.

Best Practices

Five principles guide the architecture process. First, never skip phases because each phase builds on the previous one. Second, quality gates are mandatory with no exceptions. Third, iterate until excellence and settle for nothing less than 90%. Fourth, document continuously rather than leaving documentation for the end. Fifth, validate assumptions by testing early and testing often.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.41%
按下载量换算31

Claude

30.77%
按下载量换算26

Cursor

18.14%
按下载量换算15

Gemini CLI

10.61%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills