utility-pm-critic

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

PM Critic (Dispatch Skill)

PM Critic（调度技能）

This skill is a cross-client dispatch wrapper for the

pm-critic

sub-agent. It exists so that users on non-Claude clients can run adversarial review with the same intent as Claude Code users, without depending on native plugin sub-agent infrastructure.

Per master plan D11 (amended) + D30, sub-agents are a Claude Code plugin feature. Non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) cannot natively load

subagents/pm-critic.md

. This skill bridges the gap.

本技能是

pm-critic

子代理的跨客户端调度包装器。它的存在是为了让非Claude客户端的用户能够以与Claude Code用户相同的意图运行对抗性审查，而无需依赖原生插件子代理基础设施。

根据修订后的主计划D11 + D30，子代理是Claude Code的插件功能。非Claude客户端（Codex CLI、Cursor、Windsurf、Copilot、Gemini CLI）无法原生加载

subagents/pm-critic.md

。本技能填补了这一空白。

When to Use

使用场景

You want adversarial review of a PM artifact (PRD, OKR set, persona, lean canvas, meeting recap, interview synthesis, problem statement, hypothesis, edge case catalog, retrospective, etc.)
You are running on a non-Claude AI client and the
```
pm-critic
```
sub-agent is not natively available
You are running on Claude Code and prefer skill-invocation semantics over sub-agent semantics (e.g., for consistency across a multi-step workflow that mixes skills and sub-agent intents)

你需要对PM工件（PRD、OKR集合、用户画像、精益画布、会议纪要、访谈总结、问题陈述、假设、边缘案例目录、回顾文档等）进行对抗性审查
你正在使用非Claude AI客户端，且
```
pm-critic
```
子代理无法原生使用
你正在使用Claude Code，但相比子代理语义，更倾向于使用技能调用语义（例如，为了在混合技能和子代理意图的多步骤工作流中保持一致性）

When NOT to Use

不适用场景

You want a structural lint / repo-level audit -> use
```
utility-pm-skill-auditor
```
(audits skills + repo state) instead
You want to author an artifact (this skill only reviews) -> use the appropriate phase skill (deliver-prd, foundation-okr-writer, etc.)
You want code review -> use a code-review-specific tool (this skill is for PM artifacts)
You want to enforce style rules like em-dash sweep -> that is
```
pm-release-conductor
```
's G0 gate, not this skill

你需要进行结构检查/仓库级审计 -> 请改用
```
utility-pm-skill-auditor
```
（审查技能+仓库状态）
你需要创作工件（本技能仅用于审查）-> 请使用对应阶段的技能（deliver-prd、foundation-okr-writer等）
你需要代码审查 -> 请使用专门的代码审查工具（本技能仅针对PM工件）
你需要强制执行如破折号规范之类的样式规则 -> 这是
```
pm-release-conductor
```
的G0关卡功能，不属于本技能

Instructions

操作说明

Runtime detection step. Determine which AI client is invoking this skill.

运行时检测步骤。确定调用本技能的AI客户端类型。

If you are running in Claude Code with the pm-skills plugin installed

若在安装了pm-skills插件的Claude Code中运行

Invoke

@agent-pm-critic

on the target artifact. Pass the artifact path as argument (or the most recent artifact in session context if no argument is provided). Return the sub-agent's findings to the user. No further action needed from this skill - the sub-agent handles the review natively in its own context window.

在目标工件上调用

@agent-pm-critic

。将工件路径作为参数传递（如果未提供参数，则使用会话上下文中最新的工件）。将子代理的审查结果返回给用户。本技能无需进一步操作——子代理会在其自身的上下文窗口中原生处理审查工作。

If you are running in any other AI client

若在其他任何AI客户端中运行

Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI, ChatGPT, or any other client without native pm-skills plugin sub-agent support:

Read the canonical sub-agent definition at
```
subagents/pm-critic.md
```
Execute the system prompt body in that file as your operating instructions for this turn
Read the target PM artifact specified by the user (path from
```
$ARGUMENTS
```
, or most recently produced artifact in session)
Read the canonical standards docs referenced by the pm-critic system prompt for the artifact type (e.g.,
```
skills/foundation-okr-writer/SKILL.md
```
for OKR sets,
```
skills/deliver-prd/SKILL.md
```
for PRDs)
Produce findings graded P0/P1/P2/P3 with concrete fix suggestions, formatted per the output structure documented in
```
docs/guides/adversarial-review.md
```
End the output with the layered structure per master plan D26:
- Section (1): full human-readable findings (the P0/P1/P2/P3 report)
- Section (2):
```
## Status Summary
```
  in prose, summarizing what was found and what the user should do next
- Section (3):
```
## Status
```
  YAML block with machine-readable fields

Codex CLI、Cursor、Windsurf、Copilot、Gemini CLI、ChatGPT或任何其他不支持原生pm-skills插件子代理的客户端：

读取
```
subagents/pm-critic.md
```
中的标准子代理定义
将该文件中的系统提示正文作为当前轮次的操作指令执行
读取用户指定的目标PM工件（来自
```
$ARGUMENTS
```
的路径，或会话中最近生成的工件）
读取pm-critic系统提示针对该工件类型引用的标准文档（例如，针对OKR集合读取
```
skills/foundation-okr-writer/SKILL.md
```
，针对PRD读取
```
skills/deliver-prd/SKILL.md
```
）
生成按P0/P1/P2/P3分级的审查结果，附带具体修复建议，格式遵循
```
docs/guides/adversarial-review.md
```
中记录的输出结构
按照主计划D26的分层结构结束输出：
- 第(1)部分：完整的人类可读审查结果（P0/P1/P2/P3报告）
- 第(2)部分：
```
## Status Summary
```
  （状态摘要）文本部分，总结发现的问题以及用户下一步应采取的行动
- 第(3)部分：
```
## Status
```
  YAML块，包含机器可读字段

Output Format

输出格式

See

references/TEMPLATE.md

for the canonical output structure (with the layered Status envelope per D26). See

references/EXAMPLE.md

for a worked example showing a real cross-client dispatch run against a PRD.

有关标准输出结构（包含符合D26的分层状态信封），请参阅

references/TEMPLATE.md

。有关针对PRD进行跨客户端调度运行的实际示例，请参阅

references/EXAMPLE.md

。

Composition

组合关系

Skills: This dispatch skill composes with all PM-artifact-producing skills (deliver-prd, foundation-okr-writer, foundation-meeting-recap, foundation-persona, foundation-lean-canvas, discover-interview-synthesis, etc.). Run any of those, then run this skill on the produced artifact.
Sub-agents: On Claude Code, this skill dispatches to
```
pm-critic
```
sub-agent. On non-Claude, this skill IS the inline execution; no further dispatch.
Workflows: Once
```
pm-workflow-orchestrator
```
(v2.17) ships, workflows can invoke this skill at quality-gate steps for cross-client compatibility.

技能：本调度技能可与所有生成PM工件的技能组合使用（deliver-prd、foundation-okr-writer、foundation-meeting-recap、foundation-persona、foundation-lean-canvas、discover-interview-synthesis等）。先运行任意上述技能，再对生成的工件运行本技能。
子代理：在Claude Code上，本技能会调度至
```
pm-critic
```
子代理。在非Claude客户端上，本技能直接内联执行；无需进一步调度。
工作流：一旦
```
pm-workflow-orchestrator
```
（v2.17）发布，工作流可在质量关卡步骤中调用本技能以实现跨客户端兼容性。

Cross-Client Notes

跨客户端注意事项

See Sub-Agent Compatibility Matrix for the canonical cross-client status of all 4 sub-agents + dispatch skills. Summary for this skill as of v2.16.0: PRODUCTION on Claude Code + Codex CLI; EXPERIMENTAL on Cursor / Windsurf / Copilot CLI / Gemini CLI. Maintainers wanting cross-client confidence on a non-Claude client can re-run the

maintainer-gate-testing-codex.md

harness on that client.

The "read and execute inline" pattern depends on the AI being able to:

Read a file path provided as a reference (most AI clients support this)
Treat that file's content as operating instructions for the current turn (most AI clients support this for SKILL.md-style instructions)
Read additional referenced standards docs at invocation time (all major AI clients support this)

If any of these are unreliable on a given client, that client cannot use this dispatch skill effectively.

有关所有4个子代理+调度技能的标准跨客户端状态，请参阅子代理兼容性矩阵。截至v2.16.0，本技能的状态总结：在Claude Code + Codex CLI上为PRODUCTION（生产可用）；在Cursor / Windsurf / Copilot CLI / Gemini CLI上为EXPERIMENTAL（实验性）。若维护人员希望在非Claude客户端上获得跨客户端可靠性，可在该客户端上重新运行

maintainer-gate-testing-codex.md

测试工具。

“读取并内联执行”模式依赖AI具备以下能力：

读取作为参考提供的文件路径（大多数AI客户端支持此功能）
将该文件内容作为当前轮次的操作指令（大多数AI客户端支持SKILL.md风格的指令）
在调用时读取额外引用的标准文档（所有主流AI客户端支持此功能）

如果某客户端在上述任何一项上不可靠，则该客户端无法有效使用本调度技能。

Reference Files

参考文件

Canonical sub-agent definition:
```
subagents/pm-critic.md
```

Behavioral spec:

docs/internal/release-plans/v2.16.0/spec_pm-critic.md

User-facing guide:
```
docs/guides/adversarial-review.md
```
Runtime components catalog:
```
docs/reference/runtime-components.md
```
Output template:
```
references/TEMPLATE.md
```
Worked example:
```
references/EXAMPLE.md
```

标准子代理定义：
```
subagents/pm-critic.md
```

行为规范：

docs/internal/release-plans/v2.16.0/spec_pm-critic.md

用户指南：
```
docs/guides/adversarial-review.md
```
运行时组件目录：
```
docs/reference/runtime-components.md
```
输出模板：
```
references/TEMPLATE.md
```
示例：
```
references/EXAMPLE.md
```