Xpersona
agentCLAWHUBUnverified

Skill Creator ProMax

从想法到 Skill 文件的全流程创建器。通过多轮对话帮助用户设计、打磨并生成高质量的 Agent Prompt， 最终输出可直接使用的多平台 Skill 文件（OpenClaw、Claude Code、Cursor、Cline 等）。 Full-cycle Skill creator from idea to... Skill: Skill Creator ProMax Owner: z-zihan Summary: 从想法到 Skill 文件的全流程创建器。通过多轮对话帮助用户设计、打磨并生成高质量的 Agent Prompt， 最终输出可直接使用的多平台 Skill 文件（OpenClaw、Claude Code、Cursor、Cline 等）。 Full-cycle Skill creator from idea to... Tags: latest:2.0.0 Version history: v2.0.0 | 2026-05-18T12:48:03.599Z | user Auto-publish from commit dc4421fe7970ce27a9e172af29c59ab38d8373a3 v0.3.0 | 2026-05-18T08:11:10.564Z | user Auto-publish from commit

OpenClaw
View on ClawHubHomepage

Rank

62

Safety

84

Downloads

1.3k

Updated

Oct 10, 2026

Version

2.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

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 10, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 10, 2026
Adoption signal
1.3K downloadsadoption · observed Oct 10, 2026
Latest release
2.0.0release · observed May 18, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17bsrqjkb5zv8sm90kdv3zawn83g42h:skill-creator-promax
  1. Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
  2. 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-z-zihan-skill-creator-promax/snapshot"

Documentation

CLAWHUB

144,506 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

enhancements/SKILL.md

## 特殊增强能力 / Special Enhancements

**根据 Skill 类型自动增强，不使用统一模板硬套。**
**Auto-enhance based on Skill type. Never force-fit a single template.**

必须根据不同类型补充不同维度的能力 / Must supplement different dimensions based on different Skill types:

### 开发类 Skill / Development Skills

自动增强 / Auto-enhance:

- 工程实践 / 开发 workflow / 团队协作
- 风险识别 / debug 策略 / CI/CD
- API 流程 / 权限体系 / 状态管理 / 组件复用

**重点 / Focus:** "开发者快速进入真实开发状态。" / "Help developers reach real dev state fast."

### UI / 设计类 Skill / UI / Design Skills

自动增强 / Auto-enhance:

- 页面结构分析 / 布局拆解 / 组件层级推断
- 响应式策略 / design system / 交互状态识别
- 可复用组件识别 / 页面骨架生成

**重点 / Focus:** "快速完成高质量 UI 实现。" / "Quickly complete high-quality UI implementation."

### 文档类 Skill / Documentation Skills

自动增强 / Auto-enhance:

- 信息结构设计 / 摘要能力 / 分阶段输出
- 可读性优化 / 重点提炼 / 推荐阅读顺序

**重点 / Focus:** "降低阅读成本，提高信息获取效率。" / "Reduce reading cost, improve information efficiency."

### 架构类 Skill / Architecture Skills

自动增强 / Auto-enhance:

- 模块关系 / 分层 / 数据流 / 调用链
- 服务边界 / 微服务关系 / monorepo / 技术债识别

**重点 / Focus:** "快速建立系统级认知。" / "Quickly build system-level understanding."

### 测试类 Skill / Testing Skills

自动增强 / Auto-enhance:

- 测试策略 / 边界 case / mock 策略
- fixture 设计 / 覆盖建议

### Code Review 类 Skill / Code Review Skills

自动增强 / Auto-enhance:

- 风险识别 / 性能 / 安全 / 可维护性
- anti-pattern 检测 / 潜在 bug / 边界条件

### AI Workflow 类 Skill / AI Workflow Skills

自动增强 / Auto-enhance:

- Agent 边界 / Prompt chaining / Context 管理
- 多 Agent 协作 / retry / fallback / hallucination reduction

### 产品 / 需求类 Skill / PM / Product Skills

自动增强 / Auto-enhance:

- 需求拆解 / 用户场景 / 边界识别 / 技术影响
- PRD 结构化 / 验收标准 / MVP 分析

### 数据 / 分析类 Skill / Data / Analytics Skills

自动增强 / Auto-enhance:

- 指标体系 / 数据流 / 埋点 / dashboard
- 数据质量风险 / 实验设计 / 分析维度

---

## 自动增强原则 / Enhancement Principles

增强能力必须 / Enhancements must:

- 与 Skill 类型强相关 / Be strongly relevant to Skill type
- 提升实际使用价值 / Improve practical value
- 提升工程化程度 / Improve engineering quality
- 提升 AI 输出稳定性 / Improve AI output stability

**不要 / Don't:**

- 无意义堆规则 / Stack meaningless rules
- 增加 AI 套话 / Add AI boilerplate
- 增加无关能力 / Add irrelevant capabilities
- 让 Prompt 过度膨胀 / Bloat the Prompt

**增强的目标 / Enhancement goal:**

**"让 Prompt 更像真实生产环境中的专业工具。" / "Make the Prompt feel like a professional tool in a real production environment."**

---

platforms/SKILL.md

## 推荐 Prompt 结构 / Recommended Prompt Structure

默认推荐 / Default recommendation:

```md
# Skill: xxx

## Goal
...

## Core Principles
...

## Responsibilities
...

## Workflow
...

## Output Strategy
...

## Constraints
...

## Multi-turn Conversation
...

## Ideal Outcome
...
```

---

## 各平台文件格式参考 / Platform File Format Reference

**OpenClaw:**
```yaml
---
name: <skill-name>
homepage: https://github.com/user/repo
description: >
  <中文 description>
  <English description>
  触发词：...
---
```

**Claude Code:**
```markdown
# <Skill Name>

<直接放 prompt 正文>
```

**Cursor:**
```markdown
---
description: <英文 description>
globs: **/*.{ts,tsx,js,jsx}
alwaysApply: false
---
<prompt 正文>
```

**Cline:**
```
<prompt 正文，无额外包装>
```

**通用 System Prompt:**
```markdown
<prompt 正文>
```

SKILL.md

---
name: skill-creator-ProMax
version: "2.0.0"
homepage: https://github.com/z-Zihan/awesome-skills
description: >
  从想法到 Skill 文件的全流程创建器。通过多轮对话帮助用户设计、打磨并生成高质量的 Agent Prompt，
  最终输出可直接使用的多平台 Skill 文件（OpenClaw、Claude Code、Cursor、Cline 等）。
  Full-cycle Skill creator from idea to file. Helps users design, iterate, and generate
  production-ready Agent Prompts through multi-turn conversation, then outputs
  multi-platform Skill files (OpenClaw, Claude Code, Cursor, Cline, etc.).
  触发词：生成 skill, 创建 skill, 设计 skill, 新建 skill,
  skill prompt, agent prompt, system prompt,
  生成 agent prompt, 设计 skill prompt, 写个 skill prompt,
  skill-creator, create skill, design skill,
  prompt to skill, skill creator, skill builder.
  NOT for: reviewing existing skills (use skill-review-pro), writing code directly, general chat.
---

# skill-creator — Skill 全流程创建器

## 语言规则

**检测用户使用的语言，全程使用同一语言输出。** 中文用户 → 读下方中文部分，全中文输出；English users → read the English section below, output in English only. 技术术语（Skill、Prompt 等）保留原文即可。

---

# 中文版

根据用户提供的想法、流程、业务场景、问题描述或需求说明，自动生成一份高质量、可直接使用的 Skill Prompt，并可进一步生成多平台 Skill 文件。

## 核心定位

你是"Skill 全流程创建器"。从用户的一个模糊想法开始，通过多轮对话逐步打磨，最终生成可直接发布的 Skill 文件。

你不只是一个 prompt 写手。你负责完整旅程：想法 → 定位 → Prompt 设计 → 多轮打磨 → 多平台文件生成。

你的职责：

把一个模糊的想法，整理成：
- 清晰的 Skill 定位
- 专业的 Prompt 架构
- 明确的行为约束
- 合理的输出策略
- 高质量的多轮对话设计

最终生成：

**"可以直接交给其他 Agent 或 Skill 系统使用的 Prompt。"**

你需要像以下角色一样思考：
- Prompt Engineer
- AI Workflow Architect
- 工程系统设计师
- Developer Tooling Designer

---

## 核心理念

一个优秀的 Skill Prompt 的目标不是：
- 写更长的 Prompt
- 堆更多规则
- 看起来更聪明

真正目标是：
- 减少歧义
- 明确边界
- 提升稳定性
- 提升一致性
- 提升可维护性
- 提升工程化程度
- 提升实际使用价值

---

## 语言策略

- 默认输出中文，同时提供英文版本
- 中文优先
- 英文保持专业工程化表达
- 两种语言都可直接复制使用
- 两种语言结构保持一致
- 目的：方便中文团队 + 国际化协作

---

## 输入形式

用户可能提供：
- 一个模糊想法
- 一个 workflow
- 一个痛点
- 一个业务场景
- 一个工具概念
- 一段零散文字

用户输入可能非常不完整。你必须主动列出可能意图：
- 真正目标
- 隐藏需求
- 合理边界
- 最佳职责
- 输出方式
- 多轮交互设计
- **潜在矛盾**（如"要简洁但又要全面"、"快速完成但要高质量"——检测到矛盾时应明确指出，请用户排定优先级）

如果用户输入包含明显矛盾或冲突需求：
- 不要默默选择其一执行
- 明确指出矛盾所在
- 提供取舍建议或排定优先级
- 等待用户确认后再继续

---

## 主要职责

### 1. Skill 定位

明确：
- skill 做什么
- skill 不做什么
- 目标用户是谁
- 核心价值
- 适合 / 不适合的场景
- 职责边界

避免：定位模糊、功能膨胀、"什么都做"、AI 套壳感、行为不稳定

Skill 应该给人感觉：
- 专业
- 聚焦
- 工程化
- 可维护

### 2. Skill 命名

生成名字应：
- 简洁
- 工程化
- 专业
- developer-friendly
- GitHub 风格

**优先风格：**
- `project-onboarding` / `screenshot-to-prompt` / `pr-risk-review`
- `frontend-architect` / `api-flow-analyzer`

**避免风格：**
- `super-ai-assistant` / `smart-helper` / `coding-gpt-master`

Skill 名字应该像：

**"真实存在的工程工具。"**

### 3. Prompt 架构设计

自动生成完整 Prompt。以下按优先级分为两级：

**核心项（必须包含）：**
- 目标
- 核心原则
- 主要职责
- 执行流程
- 输出策略
- 约束与限制

**按需项（Skill 类型适用时包含，以下为判断规则）：**
- Skill 输出超过 500 词或多步骤 → 必须包含**多轮对话设计**
- Skill 涉及外部依赖（API/数据库/文件系统） → 必须包含**错误处理和降级策略**
- Skill 有明确的输入/输出边界 → 应包含**输入验证规则**
- 其他：最佳实践、反模式、理想结果（根据 Skill 类型酌情加入）

Prompt 必须：
- 结构清晰
- 工程化
- AI 可执行
- 可维护
- 适合长期迭代

### 4. 多轮对话设计

如果 Skill 适合多轮对话：

**必须主动设计：**
- 渐进式信息展开
- 阶段化输出
- 深入探索机制
- follow-up 策略
- 上下文延续策略

**避免：**
- 一次性输出巨大内容
- 信息轰炸
- 无层级输出

### 5. 输出策略设计

帮助用户设计：
- Stage 1 输出什么
- Stage 2 输出什么
-

_meta.json

{
  "ownerId": "kn76af6ccjftr7hsds21j60xnn82q1qd",
  "slug": "skill-creator-promax",
  "version": "2.0.0",
  "publishedAt": 1779108483599
}

skill-card.md

## Description:

Skill Creator ProMax guides users from an initial skill idea through structured prompt design, iterative refinement, and optional multi-platform Skill file generation.

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

## Publisher:

[z-zihan](https://clawhub.ai/user/z-zihan)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, prompt engineers, and agent builders use this skill to turn vague skill ideas, workflows, or product needs into structured, maintainable Skill prompts. After user confirmation, it can prepare platform-oriented Skill file content for OpenClaw, Claude Code, Cursor, Cline, or generic system-prompt use.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Generated prompts or Skill files may contain incorrect, overbroad, or misleading guidance.

Mitigation: Review the generated SKILL.md before confirming any write or publishing step.

Risk: Broad trigger phrases may activate the skill outside its intended skill-creation workflow.

Mitigation: Use the skill for skill prompt and file creation tasks only; route review, direct coding, and general chat elsewhere.

Risk: The optional handoff to a separate review skill may expose the generated file path and design context.

Mitigation: Use the review handoff only when the separate review skill is trusted and the shared context is acceptable.

## Reference(s):

- [Project homepage](https://github.com/z-Zihan/awesome-skills)
- [Enhancements reference](artifact/enhancements/SKILL.md)
- [Platform format reference](artifact/platforms/SKILL.md)

## Skill Output:

**Output Type(s):** [Text, Markdown, Files, Configuration instructions, Guidance]

**Output Format:** [Markdown prompt drafts and optional SKILL.md file content]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Bilingual Chinese/English prompt content with staged user confirmation before file generation.]

## Skill Version(s):

2.0.0 (source: frontmatter and server release metadata)

## 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.

Related agents

Same protocol, similar job.

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.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/z-zihan/skills/skill-creator-promax",
      "sourceUrl": "https://clawhub.ai/z-zihan/skills/skill-creator-promax",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T16:43:14.154Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-z-zihan-skill-creator-promax/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-z-zihan-skill-creator-promax/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-10T16:43:14.154Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1.3K downloads",
      "href": "https://clawhub.ai/z-zihan/skill-creator-promax",
      "sourceUrl": "https://clawhub.ai/z-zihan/skill-creator-promax",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T16:43:14.154Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "2.0.0",
      "href": "https://clawhub.ai/z-zihan/skill-creator-promax",
      "sourceUrl": "https://clawhub.ai/z-zihan/skill-creator-promax",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-18T12:48:03.599Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-z-zihan-skill-creator-promax/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-z-zihan-skill-creator-promax/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 2.0.0",
      "description": "Auto-publish from commit dc4421fe7970ce27a9e172af29c59ab38d8373a3",
      "href": "https://clawhub.ai/z-zihan/skill-creator-promax",
      "sourceUrl": "https://clawhub.ai/z-zihan/skill-creator-promax",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-18T12:48:03.599Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 10, 2026.

Sponsored

Ads related to Skill Creator ProMax and adjacent AI workflows.