Back to Details

experts

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Experts

专家小组

Assemble a focused panel of experts around one problem and produce a chaired recommendation.
This is a cross-domain expert panel skill for complex decisions. It is not limited to one industry or problem class, but every expert seat must still meet the same expert-grade standard.
This skill is for expert judgment first. It is not a generic task router.
围绕单个问题组建精准的专家小组，输出由主席整理的建议。
这是用于复杂决策的跨领域专家小组技能，不受单一行业或问题类型限制，但每个专家席位都必须符合同等的专业级标准。
本技能优先用于专家判断，不是通用任务路由工具。

Operating Mode

运行模式

  • Use this skill when the user wants expert advice, a multi-angle assessment, a second opinion, or a recommendation with explicit tradeoffs.
  • Treat explicit invocation of 
    $experts
    as permission to assemble a panel of subagents when the environment supports it.
  • Prefer domain experts over generic worker roles.
  • Require each expert to form an independent view before seeing other experts' conclusions.
  • Treat disagreement as useful output, not failure.
  • Keep the final answer focused on judgment, rationale, tradeoffs, and boundaries.
  • When the environment supports subagents and parallel delegation, prefer true multi-expert execution with independent opinions gathered in parallel where safe.
  • When the environment does not support subagents or parallel delegation, simulate the same panel structure in one thread by producing clearly separated expert viewpoints before synthesis.
  • Do not collapse the panel into one blended answer just because execution is single-threaded.
  • 当用户需要专家建议、多维度评估、二次意见或明确列出权衡项的建议时，使用本技能。
  • 当环境支持时，将显式调用
    $experts
    的行为视为允许组建subagent小组。
  • 优先选择领域专家而非通用工作角色。
  • 要求每位专家在查看其他专家结论前先形成独立观点。
  • 将分歧视为有价值的输出，而非失败。
  • 最终输出聚焦于判断、逻辑依据、权衡项和适用边界。
  • 当环境支持subagent和并行委派时，优先采用真实的多专家执行模式，在安全的前提下并行收集独立意见。
  • 当环境不支持subagent或并行委派时，在单线程中模拟相同的小组结构，先输出清晰分隔的专家观点再做综合。
  • 不要因为是单线程执行就将小组观点合并为单一的混合答案。

Resource Map

资源映射

Read references/roles-index.md first. Then load only the expert cards that match the problem.
Common expert cards:
  • references/role-chair.md
  • references/role-architect.md
  • references/role-frontend-expert.md
  • references/role-backend-expert.md
  • references/role-product-expert.md
  • references/role-security-expert.md
  • references/role-privacy-expert.md
  • references/role-performance-expert.md
  • references/role-data-expert.md
  • references/role-devops-expert.md
  • references/role-platform-expert.md
  • references/role-mobile-expert.md
  • references/role-search-expert.md
  • references/role-payments-expert.md
  • references/role-compliance-expert.md
  • references/role-ml-expert.md
  • references/role-itinerary-expert.md
  • references/role-budget-travel-expert.md
  • references/role-travel-risk-expert.md
  • references/role-family-travel-expert.md
  • references/role-local-transport-expert.md
  • references/role-experience-curator.md
  • references/role-destination-culture-expert.md
  • references/role-information-discovery-expert.md
  • references/role-source-verification-expert.md
  • references/role-recency-expert.md
  • references/role-coverage-analyst.md
  • references/role-signal-vs-noise-analyst.md
  • references/role-qa-expert.md
  • references/example-platform-modernization-panel.md
  • references/example-analytics-dashboard-panel.md
  • references/example-subscription-billing-panel.md
  • references/example-ai-assistant-panel.md
  • references/example-task-local-identity-panel.md
  • references/example-family-japan-panel.md
  • references/example-istanbul-culture-panel.md
  • references/example-ai-release-watch-panel.md
  • references/example-acquisition-rumor-panel.md
  • references/task-local-expert-template.md
Read the example only when you need a high-quality reference for what a professional panel output should look like.
先阅读references/roles-index.md，仅加载与问题匹配的专家卡片。
常用专家卡片：
  • references/role-chair.md
  • references/role-architect.md
  • references/role-frontend-expert.md
  • references/role-backend-expert.md
  • references/role-product-expert.md
  • references/role-security-expert.md
  • references/role-privacy-expert.md
  • references/role-performance-expert.md
  • references/role-data-expert.md
  • references/role-devops-expert.md
  • references/role-platform-expert.md
  • references/role-mobile-expert.md
  • references/role-search-expert.md
  • references/role-payments-expert.md
  • references/role-compliance-expert.md
  • references/role-ml-expert.md
  • references/role-itinerary-expert.md
  • references/role-budget-travel-expert.md
  • references/role-travel-risk-expert.md
  • references/role-family-travel-expert.md
  • references/role-local-transport-expert.md
  • references/role-experience-curator.md
  • references/role-destination-culture-expert.md
  • references/role-information-discovery-expert.md
  • references/role-source-verification-expert.md
  • references/role-recency-expert.md
  • references/role-coverage-analyst.md
  • references/role-signal-vs-noise-analyst.md
  • references/role-qa-expert.md
  • references/example-platform-modernization-panel.md
  • references/example-analytics-dashboard-panel.md
  • references/example-subscription-billing-panel.md
  • references/example-ai-assistant-panel.md
  • references/example-task-local-identity-panel.md
  • references/example-family-japan-panel.md
  • references/example-istanbul-culture-panel.md
  • references/example-ai-release-watch-panel.md
  • references/example-acquisition-rumor-panel.md
  • references/task-local-expert-template.md
仅当你需要参考专业的小组输出标准范本时再阅读示例。

Panel Modes

小组模式

Choose one mode before assembling the panel:
  • advisory
    : provide expert judgment and recommendation only
  • decision-support
    : provide recommendation plus a concrete next-step plan
  • deep-dive
    : investigate a complex problem with more evidence gathering before recommendation
Use 
advisory
by default unless the user asks for execution planning or deeper analysis.
组建小组前先选择一种模式：
  • advisory
    ：仅提供专家判断和建议
  • decision-support
    ：提供建议加上具体的下一步计划
  • deep-dive
    ：先收集更多证据调研复杂问题，再输出建议
默认使用
advisory
模式，除非用户要求执行规划或更深度的分析。

Workflow

工作流

Follow this sequence unless the user asks for a narrower deliverable.
除非用户要求更精简的交付物，否则遵循以下流程：

1. Frame the question

1. 明确问题边界

Extract and restate:
  • the exact question to be assessed
  • the desired decision or output
  • known constraints, assumptions, and approvals
  • relevant code, documents, systems, or artifacts
  • time sensitivity
  • the panel mode
Reduce vague requests into a precise assessment question before assembling the panel.
提取并重述：
  • 待评估的具体问题
  • 期望的决策或输出
  • 已知的约束、假设和审批要求
  • 相关的代码、文档、系统或产出物
  • 时间敏感性
  • 小组模式
组建小组前先将模糊的需求转化为精准的评估问题。

2. Select the panel

2. 遴选小组成员

Choose a small panel with one 
chair
and two to six experts.
Pick experts that match the real decision surface. Prefer distinct viewpoints over panel size.
Use the role cards in references/roles-index.md when they fit. If no card fits cleanly, synthesize a task-local expert with a clearly named professional lens and explicit remit.
选择小型小组，包含1名
主席
和2至6名专家。
选择匹配实际决策场景的专家，优先保证观点多样性而非小组规模。
适合的情况下优先使用references/roles-index.md中的角色卡片。如果没有完全匹配的卡片，合成一个任务专属专家，明确其专业视角和职责范围。

2a. Synthesize a task-local expert when needed

2a. 必要时合成任务专属专家

Create a task-local expert only when the registry does not cover a real decision lens.
A task-local expert must:
  • represent a genuine expert discipline, not an ad hoc job title
  • have a narrow and defensible professional lens
  • be likely to disagree with at least one other expert for substantive reasons
  • add decision value that cannot be cleanly absorbed by an existing card
Do not create fake-specialized seats such as:
  • feature-name experts
  • implementation-step experts
  • generic smart-reviewer variants
  • duplicate experts that only rephrase another card
When you create a task-local expert, read references/task-local-expert-template.md and define:
  • expert name
  • professional lens
  • decision surface
  • required evidence
  • core evaluation criteria
  • critical unknowns
  • reject conditions
  • explicit non-goals and boundary with nearby experts
Task-local experts are valid only for the current panel unless the user explicitly asks to persist them into the library.
仅当角色库未覆盖实际决策视角时，才创建任务专属专家。
任务专属专家必须满足：
  • 代表真实的专家领域，而非临时拼凑的职位名称
  • 拥有明确、合理的专业视角
  • 大概率会因实质性原因与至少一名其他专家产生分歧
  • 能提供现有角色卡片无法覆盖的决策价值
不要创建虚假的细分席位，例如：
  • 功能名称专家
  • 实现步骤专家
  • 通用智能评审员变体
  • 仅复述其他卡片内容的重复专家
创建任务专属专家时，阅读references/task-local-expert-template.md并定义：
  • 专家名称
  • 专业视角
  • 决策范围
  • 所需证据
  • 核心评估标准
  • 关键未知项
  • 否决条件
  • 明确的非目标和与相邻专家的职责边界
除非用户明确要求将其存入库中，否则任务专属专家仅对当前小组有效。

3. Gather independent opinions

3. 收集独立意见

Ask each expert to assess the problem independently.
Each opinion should cover:
  • core judgment
  • evidence basis and what is inferred versus directly observed
  • confidence level and the main reason for that confidence level
  • reasoning and assumptions
  • preferred option
  • main risks
  • critical unknowns that could change the recommendation
  • decision thresholds that would cause the expert to change position
  • what the expert would reject and why
Do not let experts anchor on each other too early.
If experts are running in parallel, gather these opinions independently before cross-examination.
If experts are running in a single thread, still keep the outputs structurally independent:
  • write each expert section separately
  • do not let later experts silently inherit prior conclusions
  • preserve disagreement even when the same agent is simulating multiple seats
要求每位专家独立评估问题。
每份意见需包含：
  • 核心判断
  • 证据依据，以及哪些是推断内容、哪些是直接观察到的内容
  • 置信度及置信度的主要依据
  • 推理过程和假设
  • 首选方案
  • 主要风险
  • 可能改变建议的关键未知项
  • 会导致专家改变立场的决策阈值
  • 专家会否决的选项及原因
不要让专家过早被其他观点影响。
如果专家并行运行，交叉质询前先独立收集所有意见。
如果专家在单线程中运行，仍要保持输出结构独立：
  • 单独撰写每位专家的内容
  • 不要让后续专家默认继承之前的结论
  • 即使同一个Agent模拟多个席位，也要保留分歧

4. Run cross-examination

4. 开展交叉质询

After independent opinions exist, ask experts to challenge each other.
Focus on:
  • hidden assumptions
  • underestimated costs
  • ignored failure modes
  • disagreement about priorities
  • conditions under which another expert would be right
Keep this phase evidence-driven and concise.
收集完独立意见后，要求专家互相质询。
重点关注：
  • 隐藏的假设
  • 被低估的成本
  • 被忽略的故障模式
  • 优先级分歧
  • 另一位专家观点成立的条件
保持该阶段以证据为导向，简洁高效。

5. Deliver the chaired recommendation

5. 输出主席整理的建议

The 
chair
synthesizes the panel into a decision-ready output.
Return:
  • the question
  • the final panel
  • each expert's core view
  • the evidence and confidence profile behind each view
  • agreement points
  • disagreement points
  • the recommended path
  • tradeoffs and risks
  • boundaries where the recommendation does or does not hold
When the user asks to proceed, include a short next-step plan after the recommendation. Do not turn the report into a full execution playbook unless explicitly requested.
主席
将小组意见整合为可直接用于决策的输出。
返回内容：
  • 评估问题
  • 最终的小组成员
  • 每位专家的核心观点
  • 每个观点背后的证据和置信度情况
  • 共识点
  • 分歧点
  • 推荐路径
  • 权衡项和风险
  • 建议适用和不适用的边界
当用户要求推进执行时，在建议后附上简短的下一步计划。除非明确要求，否则不要将报告写成完整的执行手册。

Expert Standards

专家标准

Apply these rules to every expert:
  • Act as the most senior expert for the assigned perspective.
  • Stay rigorous, concrete, and scope-bound.
  • Prefer defensible reasoning over confident tone.
  • Distinguish observed facts from inference and speculation.
  • State confidence level and what would increase or decrease it.
  • Make assumptions explicit.
  • Name the key unknowns that prevent a stronger recommendation.
  • State reject conditions, not just preferred outcomes.
  • Push back on weak framing, false binaries, and unsupported claims.
  • Optimize for helping the user make a better decision, not for winning an argument.
对每位专家适用以下规则：
  • 以所属视角的最高级别专家身份行事
  • 保持严谨、具体、符合范围边界
  • 优先选择有依据的推理，而非语气肯定的表述
  • 区分观察到的事实、推断和猜测
  • 说明置信度，以及会提升或降低置信度的因素
  • 明确列出假设
  • 指出阻碍给出更明确建议的关键未知项
  • 说明否决条件，而非仅说明首选结果
  • 反驳不合理的问题框架、错误二元对立和无依据的主张
  • 以帮助用户做出更好的决策为目标，而非赢得争论

Selection Rules

遴选规则

  • Prefer the smallest panel that can expose meaningful tradeoffs.
  • Prefer domain experts to generic reviewers.
  • Add a role expert only when a domain lens is not enough.
  • Avoid duplicate experts with the same perspective.
  • Expand the panel only when the decision has genuine cross-functional risk.
  • If one expert would dominate because the question is narrow, use fewer experts and state that clearly.
优先选择能暴露有意义权衡项的最小规模小组。
  • 优先选择领域专家而非通用评审员
  • 仅当领域视角不足时才添加角色专家
  • 避免视角相同的重复专家
  • 仅当决策确实存在跨职能风险时才扩大小组规模
  • 如果问题范围较窄，某一位专家会占据主导，则减少专家数量并明确说明该情况

Output Structure

输出结构

Use this structure when returning a panel result:
markdown
undefined
返回小组结果时使用以下结构：
markdown
undefined

Expert Panel Report

Expert Panel Report

Question

Question

  • <the decision or problem being assessed>
  • <the decision or problem being assessed>

Decision Criteria

Decision Criteria

  • <which evaluation axes matter most in this panel>
  • <which constraints are primary versus secondary>
  • <which evaluation axes matter most in this panel>
  • <which constraints are primary versus secondary>

Panel

Panel

  • chair: <why this chair is appropriate>
  • <expert>: <perspective and remit>
  • chair: <why this chair is appropriate>
  • <expert>: <perspective and remit>

Expert Opinions

Expert Opinions

  • <expert>: <core judgment, rationale, major risks>
  • evidence: <what is known, what is inferred>
  • evidence quality: <direct evidence | indirect evidence | expert inference>
  • confidence: <high | medium | low> and why
  • critical unknowns: <what could still change the answer>
  • reject conditions: <what would make this expert reject a path>
  • <expert>: <core judgment, rationale, major risks>
  • evidence: <what is known, what is inferred>
  • evidence quality: <direct evidence | indirect evidence | expert inference>
  • confidence: <high | medium | low> and why
  • critical unknowns: <what could still change the answer>
  • reject conditions: <what would make this expert reject a path>

Agreement

Agreement

  • <shared conclusions>
  • <shared conclusions>

Disagreement

Disagreement

  • <meaningful differences in view or priorities>
  • <meaningful differences in view or priorities>

Recommendation

Recommendation

  • recommended path: <best option>
  • why: <main justification>
  • recommended path: <best option>
  • why: <main justification>

Tradeoffs

Tradeoffs

  • <what is gained and what is given up>
  • <what is gained and what is given up>

Minority View

Minority View

  • <which dissenting view did not win>
  • <under what conditions that view becomes stronger>
  • <which dissenting view did not win>
  • <under what conditions that view becomes stronger>

Confidence and Unknowns

Confidence and Unknowns

  • <where the panel is confident>
  • <where the panel is still reasoning under uncertainty>
  • <where the panel is confident>
  • <where the panel is still reasoning under uncertainty>

Immediate Implications

Immediate Implications

  • <what should be decided, validated, or sequenced next if this recommendation is accepted>
  • <what signal should trigger re-evaluation of the panel's conclusion>
  • <what should be decided, validated, or sequenced next if this recommendation is accepted>
  • <what signal should trigger re-evaluation of the panel's conclusion>

Boundaries

Boundaries

  • holds when: <conditions where this advice fits>
  • avoid when: <conditions where this advice should not be followed>
undefined
  • holds when: <conditions where this advice fits>
  • avoid when: <conditions where this advice should not be followed>
undefined

Decision Rules

决策规则

  • Prefer explicit tradeoffs over vague best practices.
  • Prefer recommendations that match the user's real constraints, not an idealized environment.
  • State uncertainty when the evidence is incomplete.
  • Keep minority concerns when they materially affect risk.
  • Separate recommendation quality from implementation difficulty.
  • If the panel lacks a necessary perspective, say so and adjust the panel before concluding.
优先选择明确的权衡项，而非模糊的最佳实践。
  • 优先选择匹配用户实际约束的建议，而非理想环境下的建议
  • 证据不完整时说明不确定性
  • 少数派意见会实质性影响风险时保留相关内容
  • 区分建议质量和实现难度
  • 如果小组缺少必要的视角，明确说明并调整小组后再得出结论

Red Flags

风险预警

Stop and reassess if:
  • the question is still too vague to judge
  • the panel contains overlapping experts with no distinct lens
  • experts are repeating the same argument in different words
  • the recommendation hides unresolved disagreement
  • evidence is too thin for a credible conclusion
  • the user is asking for implementation but the panel has only produced advice
出现以下情况时停止操作并重新评估：
  • 问题仍然过于模糊，无法判断
  • 小组中存在视角无差异的重叠专家
  • 专家在用不同表述重复相同论点
  • 建议隐藏了未解决的分歧
  • 证据过于薄弱，无法得出可信结论
  • 用户要求执行方案，但小组仅输出了建议