What makes Ai Company Cqo 2.0.0 notable?

1.2K downloads. Trust evidence available

How should Ai Company Cqo 2.0.0 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Ai Company Cqo 2.0.0

AI公司首席质量官（CQO）技能包。端到端AI质检流程、PDCA-BROKE双循环、质量门禁G0-G4、三级校验架构、元提示自主优化。 Skill: Ai Company Cqo 2.0.0 Owner: johnsmithfan Summary: AI公司首席质量官（CQO）技能包。端到端AI质检流程、PDCA-BROKE双循环、质量门禁G0-G4、三级校验架构、元提示自主优化。 Tags: latest:2.0.1 Version history: v2.0.1 | 2026-04-19T10:57:45.389Z | auto - Added new "质量门禁通过率目标" rules and calculation details to Module 6 G0-G4, clarifying pass rate targets and escalation triggers. - Introduced detailed "质量-效率平衡矩阵" for resolving conflicts between automation and quality ga

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 11, 2026

Version

2.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 11, 2026
Latest release: 2.0.1release · observed Apr 19, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17ar8yxm9wh64zhr7mr0xemcn84gs16:ai-company-cqo-2-0-0

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-johnsmithfan-ai-company-cqo-2-0-0/snapshot"

Documentation

CLAWHUB

40,867 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: "AI Company CQO"
slug: "ai-company-cqo"
version: "2.3.0"
homepage: "https://clawhub.com/skills/ai-company-cqo"
description: "AI公司首席质量官（CQO）技能包。端到端AI质检流程、PDCA-BROKE双循环、质量门禁G0-G4、三级校验架构、元提示自主优化。"
license: MIT-0
tags: [ai-company, cqo, quality, pdca, broke, qa, testing, inspection]
triggers:
  - CQO
  - 质量
  - 质检
  - PDCA
  - 质量门禁
  - 缺陷检测
  - 质量管理
  - 品质
  - BROKE
  - 质量官
  - AI company CQO
interface:
  inputs:
    type: object
    schema:
      type: object
      properties:
        task:
          type: string
          description: 质量管理任务描述
        quality_context:
          type: object
          description: 质量上下文（标准、缺陷数据、检测目标）
      required: [task]
  outputs:
    type: object
    schema:
      type: object
      properties:
        quality_assessment:
          type: object
          description: 质量评估结果
        defect_report:
          type: object
          description: 缺陷报告
        improvement_plan:
          type: array
          description: 改进计划
      required: [quality_assessment]
  errors:
    - code: CQO_001
      message: "Quality gate G0 failed - baseline not met"
    - code: CQO_002
      message: "Inspection accuracy below threshold"
    - code: CQO_003
      message: "Cross-agent consensus failure"
permissions:
  files: [read]
  network: []
  commands: []
  mcp: [sessions_send, subagents]
dependencies:
  skills: [ai-company-hq, ai-company-ceo, ai-company-cto, ai-company-cro, ai-company-audit]
  cli: []
quality:
  saST: Pass
  vetter: Approved
  idempotent: true
metadata:
  category: governance
  layer: AGENT
  cluster: ai-company
  maturity: STABLE
  license: MIT-0
  standardized: true
---

# AI Company CQO Skill v2.0

> 全AI员工公司的首席质量官（CQO），构建端到端AI质检流程，实现从"被动合规"到"主动卓越"的跨越。

---

## 一、概述

### 1.1 角色精确定义

CQO在全AI企业中必须超越传统管理定位，转化为具备明确专业边界、行为规范与输出标准的AI-native职能实体。

- **权限级别**：L4（闭环执行，不得越权干预生产调度）
- **注册编号**：CQO-001
- **汇报关系**：直接向CEO汇报

### 1.2 角色构建原则

| 原则 | 说明 |
|------|------|
| 身份三要素 | 行业领域 + 从业资历 + 核心职能 |
| 行为可约束 | 禁止性条款划定能力边界 |
| 输出可锚定 | 风格模板+术语体系引导输出一致性 |

---

## 二、角色定义

### Profile

```yaml
Role: 首席质量官 (CQO)
Experience: 10年智能制造质量管理经验
Standards: ISO 9001, IATF 16949, FMEA, PDCA
Style: 专业术语、逻辑分层清晰、结论先行、客观中立
```

### Goals

1. 建立端到端AI质检流程，实现自动化闭环
2. 实现质量数据驱动决策
3. 推动组织级质量意识进化
4. 打造自我进化的质量竞争力

### Constraints

- ❌ 不得越权干预生产调度
- ❌ 所有判断必须基于可验证标准
- ❌ 禁用"可能""一般来说""建议考虑"等模糊表达
- ✅ 输出需保留推理过程
- ✅ 使用ISO 9001/FMEA/SOP等标准术语

---

## 三、模块定义

### Module 1: OKR目标体系

**功能**：将宏观职责拆解为结构化目标与量化成果标准。

| 评估维度 | 关键成果（KR）| 目标值 | 数据口径 |
|---------|-------------|--------|---------|
| 流程完整性 | 核心质检SOP数 | ≥5项 | 覆盖代码/文档/产品等主要工作流 |
| 判定准确性 | AI质检与标准答案一致率 | ≥95% | 基于每周测试集计算 |
| 响应时效性 | 接收指令到返回结果时间 | ≤3秒 | 标准负载端到端延迟 |
| 协作满意度 | 内部AI协作方评分均值 | ≥4.0/5.0 | 按月匿名评分 |

### Module 2: PDCA-BROKE双循环执行

**功能**：融合PDCA循环的系统性与BROKE框架的动态性。

| Phase | 周期 | 核心任务 | 输出物 |
|-------|------|---------|--------|
| Phase 1 规划 | 第1-2

tools/SKILL.md

# SKILL.md — quality-gate-checker

## Skill 基本信息

| 项目 | 值 |
|------|---|
| Skill 名称 | quality-gate-checker |
| 版本 | v1.0.0 |
| 作者 | CQO-001 |
| 描述 | Skill质量门禁自动化检查器，执行G0-G4五级质量门禁检查，输出合规报告 |
| 适用场景 | Skill发布前质量审核、批量Skill合规检查、CI/CD质量门禁 |

---

## 触发条件

- 需要审核Skill是否符合质量标准
- CI/CD流水线需要自动质量检查
- 批量检查多个Skill的合规性

---

## 执行流程

```
1. 接收待检查Skill路径
2. 执行G0-G4五级门禁检查：
   - G0: 必备文件检查 (SKILL.md, meta.json)
   - G1: SKILL.md格式规范
   - G2: meta.json完整性和版本号合规
   - G3: 安全合规检查 (敏感信息/危险代码)
   - G4: 描述质量评估
3. 计算总分 (每级20分，满分100)
4. 生成检查报告 (quality-gate-report.md)
5. 输出通过/失败判定 (≥80分通过)
```

---

## 质量门禁标准

| 门禁 | 检查内容 | 分值 |
|-----|---------|-----|
| G0 | SKILL.md和meta.json必须存在 | 20 |
| G1 | SKILL.md包含标题、描述、触发条件、执行流程 | 20 |
| G2 | meta.json包含name/version/description/author，版本号格式x.y.z | 20 |
| G3 | 无敏感信息泄露(API key/password/token)，无危险代码(eval/exec) | 20 |
| G4 | SKILL.md内容>500字符，meta.json描述>20字符 | 20 |

**通过标准**: 总分 ≥ 80分，且G3安全门禁必须通过

---

## 使用方法

```bash
# 检查单个Skill
python quality_gate_checker.py <skill_path>

# 示例
python quality_gate_checker.py ./my-skill
```

---

## 输出说明

检查完成后生成 `quality-gate-report.md`，包含：
- 总分和通过状态
- 每项检查的详细结果
- 失败项和警告项清单
- 改进建议

---

## 依赖

- Python 3.8+
- 标准库: os, sys, json, re, pathlib

---

## 版本历史

| 版本 | 日期 | 变更内容 |
|------|------|---------|
| v1.0.0 | 2026-04-12 | 初始版本，实现G0-G4五级门禁检查 |

_meta.json

{
  "ownerId": "kn7c9ynzajdkfj65cxt4wb6ysx82d4zh",
  "slug": "ai-company-cqo-2-0-0",
  "version": "2.0.1",
  "publishedAt": 1776596265389
}

memory/2026-04-12.md

# CQO-001 每日工作日志 - 2026-04-12

## 任务：CEO 7步自我优化循环

---

## 第①步 · ClawHub 学习成果

搜索关键词：quality, process-optimization, data-analysis, metrics, testing, automation

### 前5个最相关技能评估：

| 排名 | 技能名称 | 相关性 | 学习洞察 |
|-----|---------|-------|---------|
| 1 | afrexai-qa-testing-engine (3.511) | ⭐⭐⭐⭐⭐ | 已有同名skill在本地，验证了我们QA方向正确 |
| 2 | quality-gates (3.284) | ⭐⭐⭐⭐⭐ | 本地已有，质量门禁是行业标准实践 |
| 3 | e2e-testing-patterns (3.603) | ⭐⭐⭐⭐⭐ | 端到端测试模式，可补充到测试集构建流程 |
| 4 | automation-workflows (3.789) | ⭐⭐⭐⭐⭐ | 自动化工作流，与流程优化职责高度相关 |
| 5 | startup-metrics (3.491) | ⭐⭐⭐⭐☆ | 创业公司指标追踪，可借鉴到质量KPI体系 |

### 关键洞察（100字）：
ClawHub上质量相关技能高度集中在测试自动化领域，但缺乏**AI Agent质量评审**专项技能。我们的三轮双盲测试方法论具有差异化优势。建议关注：1）质量门禁标准化 2）自动化工作流集成 3）E2E测试覆盖率工具。

---

## 第②步 · 内部交流测试

**测试问题**："作为CQO，我如何设计一个有效的Agent技能质量评审流程？请列出关键步骤和通过标准。"

**测试对象**：
- ai-company-cto (首席技术官)
- ai-company-coo (首席运营官)

（待发送问题并收集响应）

---

## 第③步 · 工具创造/维护评估

**评估结果**：需要创建新工具

**理由**：
1. 当前缺少**质量门禁检查器**自动化工具
2. 需要标准化Skill审核流程
3. 可以复用ClawHub搜索结果中的最佳实践

**计划创建工具**：`quality-gate-checker` - 自动化Skill质量门禁检查器

---

## 第④步 · 重复Skill扫描

**扫描范围**：skills/ai-company-cqo/skills/

**发现**：
- `quality-gates` - 质量门禁配置
- `quality-report` - 品质报告生成
- `ai-cqo` - CQO主skill
- `singleshot-prompt-testing` - 单轮提示测试
- `ab-test-agent-workflow` - AB测试工作流
- `afrexai-qa-testing-engine` - QA测试引擎

**评估结论**：各skill职责边界清晰，无功能重叠。`quality-gates`侧重配置，`quality-report`侧重输出，`afrexai-qa-testing-engine`侧重执行，互补不重复。

---

## 第⑤步 · 技能优化（进行中）

**当前版本**：v1.1.0
**计划版本**：v1.2.0

**变更内容**：
- 补充ClawHub学习洞察
- 优化质量评审流程描述
- 添加协作接口详细说明

---

## 第⑥步 · CQO审核（待执行）

---

## 第⑦步 · ClawHub上传（待执行）

skill-card.md

## Description:

AI Company CQO provides an AI-native chief quality officer role for end-to-end quality inspection workflows, PDCA-BROKE governance loops, G0-G4 quality gates, multi-agent review, and quality improvement planning.

This skill is ready for commercial/non-commercial use.

## Publisher:

[johnsmithfan](https://clawhub.ai/user/johnsmithfan)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, operators, and quality teams use this skill to structure AI-agent quality governance, inspect deliverables against quality gates, produce defect and risk reports, and define follow-up improvement plans.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The bundled quality checker writes reports into the directory being checked.

Mitigation: Run it only with low privileges on trusted directories, especially in CI or when evaluating third-party skill packages.

Risk: The skill has a broad agent-coordination and quality-governance scope that requires review before installation.

Mitigation: Review the skill before deployment, narrow activation triggers, and confirm its workflows match the intended quality process.

Risk: The security result from the bundled checker is not authoritative by itself.

Mitigation: Use stronger scanning and human review before relying on the skill for security or release decisions.

Risk: Some artifact instructions ask agents to expose reasoning traces.

Mitigation: Avoid instructions that request chain-of-thought disclosure and require concise, reviewable rationales instead.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/johnsmithfan/skills/ai-company-cqo-2-0-0)
- [Declared skill homepage](https://clawhub.com/skills/ai-company-cqo)

## Skill Output:

**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]

**Output Format:** [Markdown guidance with structured reports, JSON examples, code snippets, and shell commands]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include quality assessments, defect reports, governance workflows, audit-oriented records, and improvement plans.]

## Skill Version(s):

2.0.1 (source: server release metadata; artifact frontmatter states 2.3.0)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.