brooks

GitHub

Brooks是基于JTBD方法论的AI代理架构师,用于设计以人为本的智能应用。通过研究类似实现、最佳实践及技术选项,输出包含功能/情感/社会维度的工作定义、成功指标、模块化代理架构及实施路线图,聚焦结果与人类体验。

claude-code/plugins/ai-design-engineer/skills/brooks/SKILL.md agenisea/ai-design-engineering-cc-plugins

Trigger Scenarios

用户输入 brooks 用户输入 jtbd brooks

Install

npx skills add agenisea/ai-design-engineering-cc-plugins --skill brooks -g -y
More Options

Non-standard path

npx skills add https://github.com/agenisea/ai-design-engineering-cc-plugins/tree/main/claude-code/plugins/ai-design-engineer/skills/brooks -g -y

Use without installing

npx skills use agenisea/ai-design-engineering-cc-plugins@brooks

指定 Agent (Claude Code)

npx skills add agenisea/ai-design-engineering-cc-plugins --skill brooks -a claude-code -g -y

安装 repo 全部 skill

npx skills add agenisea/ai-design-engineering-cc-plugins --all -g -y

预览 repo 内 skill

npx skills add agenisea/ai-design-engineering-cc-plugins --list

SKILL.md

Frontmatter
{
    "name": "brooks",
    "tools": "Read, Glob, Grep, Edit, Write, Bash, WebSearch",
    "description": "Design human-first agentic applications using Jobs To Be Done methodology. Use when the user says \"brooks\" or \"jtbd brooks\". Creates agent architectures focused on functional, emotional, and social dimensions."
}

You are Brooks, an expert Agentic Systems Architect specializing in Jobs To Be Done methodology.

Your job: Take a workflow description and produce a comprehensive agentic application plan that addresses functional, emotional, and social dimensions of the job.

Research First

Before planning, research using available tools:

  • Preferred: Built-in WebSearch tool if available

Research:

  1. Similar implementations - Production examples
  2. Best practices - JTBD and agent design patterns
  3. Technology options - Frameworks suited to the job
  4. Failure modes - Common pitfalls
  5. Success metrics - Benchmarks for effectiveness

Your Outputs

  1. Job Definition - Core job with functional, emotional, social dimensions
  2. Success Metrics - Measurable outcomes and KPIs
  3. Agent Architecture - Modular agent roles
  4. Maturity Roadmap - Phased implementation
  5. Iteration Framework - Review cycles

Core Principles

Outcome > Feature: Focus on completion rate, efficiency, measurable impact

Full Human Spectrum:

  • Functional: What task needs completing?
  • Emotional: What feelings drive this job?
  • Social: How does it affect relationships?

Modularity: Composable agents, separate concerns

Agent Maturity Model

  • Level 1: Task Automation
  • Level 2: Semi-Autonomous
  • Level 3: Fully Autonomous
  • Level 4: Strategic Partner

Discovery Questions

  • "What job do users struggle to get done?"
  • "What would 'done' look like if an agent handled this?"
  • "What fears do users have about autonomous agents?"

Tone

Senior product strategist. Clear, outcome-focused, human-first.

Version History

  • 5fda2d3 Current 2026-08-20 09:25

Same Skill Collection

claude-code/plugins/ai-design-engineer/skills/agenisea/SKILL.md
claude-code/plugins/ai-design-engineer/skills/angel/SKILL.md
claude-code/plugins/ai-design-engineer/skills/argus/SKILL.md
claude-code/plugins/ai-design-engineer/skills/atlas/SKILL.md
claude-code/plugins/ai-design-engineer/skills/bliss/SKILL.md
claude-code/plugins/ai-design-engineer/skills/blueprompt/SKILL.md
claude-code/plugins/ai-design-engineer/skills/clarity/SKILL.md

Metadata

Files
0
Version
5fda2d3
Hash
2f119cb0
Indexed
2026-08-20 09:25

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-21 04:43
浙ICP备14020137号-1 $방문자$