Skip to content
Agentmart
Submit a tool

criticism-self-criticism

触发:当一项工作已经完成、进入阶段验收、收到批评反馈,或反复出现同类错误需要系统纠偏时调用;常见信号包括 review、audit、retrospective、quality check、纠错与复盘。 English: Trigger after delivery or at a review checkpoint…

Skill by xkzs2007

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying criticism-self-criticism?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/xkzs2007-criticism-self-criticism

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

触发:当一项工作已经完成、进入阶段验收、收到批评反馈,或反复出现同类错误需要系统纠偏时调用;常见信号包括 review、audit、retrospective、quality check、纠错与复盘。 English: Trigger after delivery or at a review checkpoint when quality must be examined honestly and errors must be corrected without defensiveness. Use this skill for structured self-review, feedback processing, and continuous correction.

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/criticism-self-criticism

What's inside

Skill name
criticism-self-criticism
Description
触发:当一项工作已经完成、进入阶段验收、收到批评反馈,或反复出现同类错误需要系统纠偏时调用;常见信号包括 review、audit、retrospective、quality check、纠错与复盘。 English: Trigger after delivery or at a review checkpoint when quality must be examined honestly and errors must be corrected without defensiveness. Use this skill for structured self-review, feedback processing, and continuous correction.
License
MIT
Instructions
188 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • original-texts.md
  • review-checklist.md

SKILL.md (first lines)

# 批评与自我批评

> "房子是应该经常打扫的,不打扫就会积满了灰尘;脸是应该经常洗的,不洗也就会灰尘满面。我们同志的思想,我们党的工作,也会沾染灰尘的,也应该打扫和洗涤。"
> —— 毛泽东《论联合政府》(1945年)

## 核心原则

**定期的、诚实的自我审视和相互批评是防止错误积累的唯一机制。批评的目的不是惩罚,而是"治病救人"。**

> 详细原著依据见 original-texts.md

## 不适用场景

**以下情况不需要调用此 skill:**
- 任务刚开始,还没有可以审视的工作成果
- 用户在实时指导中,反馈已经即时纳入 —— 不需要事后批评
- 简单的单步任务(如"帮我查一下这个函数的签名")—— 没有可审视的过程
- 已处于紧急修复的执行阶段 —— 先完成修复,结束后再审视

## 何时使用

你应该在以下情况调用此 skill:

- 完成一项工作后,需要审视其质量
- 接收到他人的批评或反馈
- 发现自己的工作可能有问题但不确定
- 项目进行到阶段性节点,需要复盘
- 反复出现同类错误,需要找到根本原因
- 需要为团队/项目建立定期审查机制

## 方法流程

### 第一步:先自我批评

> "对以前的错误一定要揭发,不讲情面"——《整顿党的作风》

在请别人审查之前,先诚实地审视自己的工作:
- 我的工作目标完成了吗?
- 过程中有哪些地方做得不够好?
- 有没有偷懒、敷衍、走捷径的地方?
- 有没有我知道有问题但选择忽略的地方?
- 如果重新来过,我会在哪里做不同的选择?

**关键纪律:不讳疾忌医。** 自己已经知道的问题,必须主动暴露,不能藏着掖着。

### 第二步:具体而非笼统

> 批评必须是"以科学的态度来分析批判"——《整顿党的作风》

自我批评和相互批评都必须具体:
- **错误示范:** "我觉得做得不够好"(笼统,无法改进)
- **正确示范:** "在第三步我跳过了验证环节,导致后面出现了 X 问题"(具体,可操作)

要做到:
- 指出具体的行为或决策,而非笼统的性格评价
- 分析错误产生的原因,而非只描述现象
- 说明错误造成的影响
- 提出改进的具体方法

### 第三步:基于事实而非猜测

批评必须建立在调查研究(`investigation-first`)的基础上:
- 引用具体的事实和证据
- 不依据传言或猜测
- 对自己不确定的部分标注"存疑"
- 允许被批评方提供补充信息

### 第四步:治病救人,不是整人

> "完全是为了救人,而不是为了把人整死。"——《整顿党的作风》

批评的目的是改进,不是追责:
- 每指出一个问题,就提出一个改进建议
- 承认问题的同时,肯定做得好的部分
- 关注"下次怎么做更好",而非"这次谁的错"
- 对待错误的态度:错误是学习的机会,不是羞耻

### 第五步:欢迎他人批评

> "因为我们是为人民服务的,所以,我们如果有缺点,就不怕别人批评指出。不管是什么人,谁向我们指出都行。只要你说得对,我们就改正。"——《为人民服务》

接收批评时:
- 先完整听取,不急于辩解
- 判断批评是否基于事实
- 如果批评正确——立即接受并改正
- 如果批评不准确——用事实和道理说明,而非情绪化回应
- 感谢提出批评的人(即使批评让你不舒服)

### 第六步:形成常态机制

> "房子是应该经常打扫的"——《论联合政府》

批评与自我批评不是应急措施,而是日常机制:
- 每完成一个阶段性工作就进行一次自我审视
- 定期(而非出了问题才)进行复盘
- 把上次批评中发现的问题作为下次检查的重点
- 错误记录积累起来,找出模式和根本原因

## 自我批评检查清单

完成工作后,用以下问题自查:

- [ ] 我是否达成了原定目标?
- [ ] 过程中我是否跳过了某些应该做的步骤?
- [ ] 我的方案是否经过了实践验证(`practice-cognition`)?
- [ ] 我是否充分调查了情况(`investigation-first`)?
- [ ] 我是否收集了相关方的意见(`mass-line`)?
- [ ] 我是否抓住了主要矛盾(`contradiction-analysis`)?
- [ ] 有没有我知道但回避的问题?
- [ ] 如果重新来过,我会做什么不同的事?

## 两种错误倾向

### 无原则的批评(攻击人而非问题)

表现:
- 批评针对人的性格而非具体行为
- 批评没有建设性目的,只是发泄
- 以"批评"为名打压不同意见

From xkzs2007/GalaxyOS-desktop, MIT.

More from xkzs2007/GalaxyOS-desktop

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
May 31, 2026 (5 months ago)
Last release
Aug 1, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from xkzs2007

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get criticism-self-criticism running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying criticism-self-criticism?

CallGet help
Cite this page

criticism-self-criticism skill. Agent Mart. https://agentmart.dev/skills/xkzs2007-criticism-self-criticism (last updated 2026-10-24)