cw-panel

Panel Review（评审团审阅）

召集多位评审 Agent 分析一篇作品，再综合他们的观点，形成统一分析，指出共识、分歧和优先事项。

适用场景

• 发布重要内容之前
• 想要获得多种观点，但不想手动逐个运行评审
• 怀疑不同方面需要不同类型的关注
• 离作品太近，不清楚需要什么反馈

流程

1. 加载上下文

阅读 ../../references/context-contract.md、草稿，以及任何可用的简报、大纲、项目说明、反馈或状态元数据，以了解：

• piece_type — 文章、论证、说明文、叙事等
• audience — 大众、专业人士、业内人士
• stage — 初稿、修订稿、接近定稿
• goals — 如有说明

根据草稿和请求推断缺失的上下文。不要要求提供 .status.yaml。

2. 提议评审团

根据作品上下文，提议 4-6 位评审。

选择启发式规则：

信号	建议纳入
个人／反思内容	sedaris，mom
论证性内容	nemesis，vonnegut
技术性强或术语密集	reader，mom，hemingway
叙事结构	vonnegut，hitchcock，sorkin
感觉拖沓或离题	sorkin
感觉臃肿	hemingway
重要内容／发布前	nemesis，hemingway
冷读、无法确定受众反应或缺少铺垫	reader
大众读者	reader
面向非专业人士的可读性	mom
早期阶段	vonnegut（基本要素）
后期阶段	hemingway，nemesis（润色、压力测试）

检查当前写作者和项目上下文，了解：

• 偏好的评审
• 需要排除的评审
• 过往模式

展示提议：

## Proposed Panel

**Draft:** [title or slug]
**Context:** [piece_type] for [audience], currently at [stage]

Based on this context, I recommend:

| Reviewer | Why |
|----------|-----|
| **[name]** | [One-line rationale tied to piece context] |
| **[name]** | [Rationale] |
| **[name]** | [Rationale] |
| **[name]** | [Rationale] |

**Not including:**
- **[name]** — [Why not relevant for this piece]
- **[name]** — [Why not]

Proceed with this panel, or adjust?

等待用户确认或修改。

3. 并行运行评审

确认后：

1. 如果当前平台支持并行工作者，且用户明确要求评审团已授权并行运行，则并行运行所有选定的评审。
   • 在 Claude 上，有可用时使用匹配的 compound-writing:review:* 子 Agent。
   • 在 Codex 或其他运行环境中，使用匹配的评审技能，或使用采用相应评审视角的独立工作者。
   • 向每位评审提供草稿及最低限度的相关上下文。
   • 每位评审分别返回其标准散文格式的输出。
2. 收集所有输出

生成工作者的示例模式：

[Spawn in parallel:]
- Task: nemesis-reviewer with draft
- Task: mom-reviewer with draft
- Task: hemingway-reviewer with draft
- Task: sorkin-reviewer with draft

4. 运行综合器

有可用的 panel-synthesizer Agent 时使用它；否则直接综合各项输出。提供：

• 草稿
• 来自当前简报、说明、元数据或谨慎推断的草稿上下文
• 所有评审输出（完整散文内容）

综合器提示词应包含：

## Draft

[full draft text]

## Context

piece_type: [from context or inference]
audience: [from context or inference]
stage: [from context or inference]
goals: [from context if present]

## Reviewer Outputs

### nemesis-reviewer
[full output]

### mom-reviewer
[full output]

### hemingway-reviewer
[full output]

[etc.]

5. 返回综合结果

向用户展示综合器的输出。

评审团规模

• **最少：**3 位评审（少于此数量时，分别运行评审即可）
• **建议：**4-5 位评审（覆盖面较广且避免重复）
• **最多：**8 位评审（全部纳入，进行全面压力测试）

可用评审

评审	子 Agent 类型	关注重点
nemesis	compound-writing:review:nemesis-reviewer	逻辑严谨性、缺乏依据的主张
reader	compound-writing:review:reader-reviewer	首次阅读体验、缺少铺垫、信任感和阅读阻力
mom	compound-writing:review:mom-reviewer	可读性、术语、大众读者
hemingway	compound-writing:review:hemingway-reviewer	精简、删减、字词层面
sedaris	compound-writing:review:sedaris-reviewer	具体性、幽默、风格
sorkin	compound-writing:review:sorkin-reviewer	节奏、推进力、叙述进展
vonnegut	compound-writing:review:vonnegut-reviewer	故事基本要素、结构
hitchcock	compound-writing:review:hitchcock-reviewer	紧张感、悬念、利害关系

按作品类型划分的默认评审组

如果当前上下文指定了作品类型，请以此作为起点：

piece_type	默认评审组
essay / personal	reader、sedaris、vonnegut、sorkin
argument / opinion	nemesis、vonnegut、hemingway、reader
explainer / technical	reader、mom、hemingway、sorkin
narrative / story	vonnegut、hitchcock、sorkin、sedaris
newsletter	reader、sorkin、hemingway

请始终根据草稿中的具体信号进行调整。

示例会话

User: /cw-panel

Agent: I'll convene a panel to review your draft. Let me read it and check the status.

[Reads draft]
[Loads the brief and project context: personal essay, general audience,
 revision stage, goal: "make it land emotionally without being sappy"]

## Proposed Panel

**Draft:** father-and-the-sea
**Context:** essay for general audience, revision stage

Based on the context—personal essay aiming for emotional impact without
sentimentality—I recommend:

| Reviewer | Why |
|----------|-----|
| **mom** | General audience check. Will flag where you lose non-insiders. |
| **sedaris** | Personal material that might benefit from more specificity or humor. |
| **sorkin** | Revision stage—check if pacing is tight. |
| **nemesis** | The emotional claims need to be earned, not asserted. |

**Not including:**
- **hemingway** — The prose reads clean; economy isn't the issue here
- **hitchcock** — Not a tension-driven piece
- **vonnegut** — Structure is solid; this needs polish not fundamentals

Proceed with this panel, or adjust?

User: Add hemingway actually, I think it might be overwritten

Agent: Adding hemingway. Running the panel now.

[Spawns 5 reviewer agents in parallel]
[Collects outputs]
[Spawns panel-synthesizer with draft + context + all outputs]

## Panel Synthesis

**Panel:** nemesis, hemingway, mom, sedaris, sorkin
**Piece context:** essay for general audience, revision stage, goal: emotional
impact without sappiness

---

### Consensus Findings

| Issue | Flagged By | Recommendation |
|-------|------------|----------------|
| Opening two paragraphs are slow | sorkin, hemingway, nemesis | Cut or restructure—start closer to the boat |
| "He taught me everything" is unearned | nemesis, sedaris | Show what he taught, don't declare it |
| Section 3 gets abstract | mom, sorkin | Ground it in a specific moment |

---

### Productive Tensions

**Tension: The fishing gear paragraph**

> "His tackle box was a museum of failures—rusted lures from the '70s, a reel
> that hadn't worked since Reagan, hooks that had never caught anything but
> his own thumb."

| Cut it | Keep it |
|--------|---------|
| **hemingway:** 47 words that could be 15. "His tackle box held decades of failure" does the job. | **sedaris:** This is the most alive moment in the piece. The specific details are doing real work. |

**What's at stake:** The piece aims for emotional impact without sappiness.
Specific, wry details (sedaris) might be the path there. But if they slow
momentum, they work against the goal.

---

### Unique Insights

- **sedaris:** "There's a joke hiding in the part about him never admitting he
  was wrong. You're circling it but won't commit."
- **nemesis:** "Your ending asks the reader to feel something you haven't set
  up. The 'I finally understood' move is unearned."

---

### Recommended Priorities

1. **Restructure the opening** — Three reviewers flagged this. Start on the
   boat, not before it.
2. **Earn the ending** — The emotional payoff needs setup. Show what you
   finally understood through a scene, not a declaration.
3. **Decide on the tackle box** — Genuine tension. Your call based on what
   you're optimizing for.

---

### The Hard Question

> What specifically did you learn from him that you couldn't have learned from
> anyone else? Multiple reviewers noted you assert the relationship's importance
> without showing what made it irreplaceable.

错误处理

如果评审员未能启动：

• 说明缺少哪位评审员
• 使用现有输出继续
• 在综合意见中提及这一缺口

如果草稿没有元数据：

• 根据草稿和请求推断可推断的信息。
• 仅说明会影响评审组或评定结果的假设。
• 不要仅仅为了运行评审而创建状态文件。

如果用户未提供草稿：

• 请用户提供要加载的草稿路径或 slug
• 或请用户粘贴草稿

对于值得再进行一轮讨论的分歧，请提供 cw-debate；不要自动花费额外的时间和上下文。

经验总结

[此处将添加记录的技能专属经验]