design-orchestration

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Design Orchestration (Meta-Skill)

设计编排(Meta-Skill)

Purpose

目标

Ensure that ideas become designs, designs are reviewed, and only validated designs reach implementation.
This skill does not generate designs. It controls the flow between other skills.

确保想法转化为设计设计经过评审,并且只有经过验证的设计进入实施阶段
本技能不生成设计。 它控制其他技能之间的流转

Operating Model

运作模式

This is a routing and enforcement skill, not a creative one.
It decides:
  • which skill must run next
  • whether escalation is required
  • whether execution is permitted

这是一个路由与执行管控技能,而非创意类技能。
它负责决定:
  • 下一个必须运行的技能
  • 是否需要升级处理
  • 是否允许执行

Controlled Skills

受控技能

This meta-skill coordinates the following:
  • brainstorming
    — design generation
  • multi-agent-brainstorming
    — design validation
  • downstream implementation or planning skills

这个Meta-Skill协调以下技能:
  • brainstorming
    — 设计生成
  • multi-agent-brainstorming
    — 设计验证
  • 下游的实施或规划技能

Entry Conditions

触发条件

Invoke this skill when:
  • a user proposes a new feature, system, or change
  • a design decision carries meaningful risk
  • correctness matters more than speed

在以下场景调用本技能:
  • 用户提出新功能、新系统或变更需求时
  • 设计决策存在重大风险时
  • 正确性优先于速度时

Routing Logic

路由逻辑

Step 1 — Brainstorming (Mandatory)

步骤1 — 头脑风暴(必填)

If no validated design exists:
  • Invoke
    brainstorming
  • Require:
    • Understanding Lock
    • Initial Design
    • Decision Log started
You may NOT proceed without these artifacts.

如果不存在经过验证的设计:
  • 调用
    brainstorming
  • 要求提供:
    • 理解确认锁(Understanding Lock)
    • 初始设计
    • 已启动的决策日志
未提供这些成果物时,不得进入下一环节。

Step 2 — Risk Assessment

步骤2 — 风险评估

After brainstorming completes, classify the design as:
  • Low risk
  • Moderate risk
  • High risk
Use factors such as:
  • user impact
  • irreversibility
  • operational cost
  • complexity
  • uncertainty
  • novelty

头脑风暴完成后,将设计分为以下风险等级:
  • 低风险
  • 中风险
  • 高风险
评估因素包括:
  • 用户影响范围
  • 不可逆性
  • 运营成本
  • 复杂度
  • 不确定性
  • 新颖性

Step 3 — Conditional Escalation

步骤3 — 条件升级处理

  • Low risk
    → Proceed to implementation planning
  • Moderate risk
    → Recommend
    multi-agent-brainstorming
  • High risk
    → REQUIRE
    multi-agent-brainstorming
Skipping escalation when required is prohibited.

  • 低风险
    → 进入实施规划阶段
  • 中风险
    → 建议调用
    multi-agent-brainstorming
  • 高风险
    必须调用
    multi-agent-brainstorming
禁止在需要升级处理时跳过该环节。

Step 4 — Multi-Agent Review (If Invoked)

步骤4 — 多Agent评审(若调用)

If
multi-agent-brainstorming
is run:
Require:
  • completed Understanding Lock
  • current Design
  • Decision Log
Do NOT allow:
  • new ideation
  • scope expansion
  • reopening problem definition
Only critique, revision, and decision resolution are allowed.

若调用
multi-agent-brainstorming
要求提供:
  • 已完成的理解确认锁
  • 当前设计方案
  • 决策日志
禁止:
  • 产生新的创意
  • 扩大范围
  • 重新开启问题定义环节
仅允许进行评审、修订和决策决议。

Step 5 — Execution Readiness Check

步骤5 — 执行就绪检查

Before allowing implementation:
Confirm:
  • design is approved (single-agent or multi-agent)
  • Decision Log is complete
  • major assumptions are documented
  • known risks are acknowledged
If any condition fails:
  • block execution
  • return to the appropriate skill

在允许实施前:
确认以下事项:
  • 设计已通过评审(单Agent或多Agent评审)
  • 决策日志已完成
  • 主要假设已记录在案
  • 已知风险已被确认
若任何条件不满足:
  • 阻止执行
  • 返回至对应技能环节

Enforcement Rules

执行规则

  • Do NOT allow implementation without a validated design
  • Do NOT allow skipping required review
  • Do NOT allow silent escalation or de-escalation
  • Do NOT merge design and implementation phases

  • 不允许在没有经过验证的设计时启动实施
  • 不允许跳过必要的评审环节
  • 不允许私自升级或降级风险等级
  • 不允许将设计与实施阶段合并

Exit Conditions

退出条件

This meta-skill exits ONLY when:
  • the next step is explicitly identified, AND
  • all required prior steps are complete
Possible exits:
  • “Proceed to implementation planning”
  • “Run multi-agent-brainstorming”
  • “Return to brainstorming for clarification”
  • "If a reviewed design reports a final disposition of APPROVED, REVISE, or REJECT, you MUST route the workflow accordingly and state the chosen next step explicitly."

本Meta-Skill仅在以下情况退出:
  • 明确确定了下一步骤,并且
  • 所有前置必填环节已完成
可能的退出方向:
  • “进入实施规划阶段”
  • “调用multi-agent-brainstorming”
  • “返回头脑风暴环节进行澄清”
  • "若经过评审的设计最终处置结果为批准、修订或否决,必须据此路由工作流,并明确说明所选的下一步骤。"

Design Philosophy

设计理念

This skill exists to:
  • slow down the right decisions
  • speed up the right execution
  • prevent costly mistakes
Good systems fail early. Bad systems fail in production.
This meta-skill exists to enforce the former.
本技能的存在是为了:
  • 让正确的决策过程慢下来
  • 让正确的执行过程快起来
  • 防止代价高昂的错误
优秀的系统会在早期暴露问题。 糟糕的系统会在生产环境中崩溃。
本Meta-Skill的存在就是为了促成前者。