agentCLAWHUBUnverified

cosprompt

结构化 AI 绘图提示词生成器。输入角色/主题名称,AI 自动搜索信息、分析特征、决定风格,输出 17 维度结构化提示词(JSON + Markdown 双格式),适用于 Midjourney、Stable Diffusion 等绘图工具。 Skill: cosprompt Owner: fslong520 Summary: 结构化 AI 绘图提示词生成器。输入角色/主题名称,AI 自动搜索信息、分析特征、决定风格,输出 17 维度结构化提示词(JSON + Markdown 双格式),适用于 Midjourney、Stable Diffusion 等绘图工具。 Tags: ai:2.3.0, cosplay:2.3.0, image:2.3.0, latest:2.3.0, poster:2.3.0, prompt:2.3.0 Version history: v2.3.0 | 2026-08-13T17:43:04.163Z | user 新增风格参考表(9条目);新增青蓝暖橙仙侠风控制框架(冷暖对比为魂、场景灵活);style维度示例补充 v2.2.0 | 2026-06-09T03:41:39.406Z | user 融入《美学四讲》三层递进美学深度框架(悦

OpenClaw

Rank

62

Safety

84

Downloads

1.2k

Updated

Oct 10, 2026

Version

2.3.0

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 10/10/2026.

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
1.2K downloadsadoption · observed Oct 10, 2026
Latest release
2.3.0release · observed Aug 13, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s179dxbepyx3dhgg6vsaj80yt583nxj7:cosprompt
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  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-fslong520-cosprompt/snapshot"

Documentation

CLAWHUB

41,339 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: cosprompt
version: 2.3.0
description: 结构化 AI 绘图提示词生成器。输入角色/主题名称,AI 自动搜索信息、分析特征、决定风格,输出 17 维度结构化提示词(JSON + Markdown 双格式),适用于 Midjourney、Stable Diffusion 等绘图工具。
allowed-tools: [Read, Write, Edit, browser_use, grep_search, glob_search]
metadata:
  trigger: 用户需要生成 AI 绘图提示词、角色海报 prompt、Cosplay 海报提示词
---

# Cosprompt - 结构化 AI 绘图提示词生成器

## 这个技能是做什么的?

**一句话**:输入角色名,输出结构化的 AI 绘图提示词。

**使用场景**:
- 想用 Midjourney/SD 生成角色海报,不知道怎么写提示词
- 想生成 Cosplay 海报、电商海报、角色立绘
- 需要结构化、专业化的提示词模板

**工作流程**:
```
用户输入角色名 → AI 搜索角色信息 → 分析标志性特征 → 决定合适风格 → 输出结构化提示词
```

**输出格式**:
- JSON 格式(便于程序调用)
- Markdown 格式(便于阅读复制)
- 纯文本版(直接复制到绘图工具)

---

## 核心理念

**提供思考框架,不写死内容。**

AI 自主完成:
1. 搜索/分析角色信息
2. 决定风格方向
3. 填充具体内容
4. 输出结构化提示词

---

## 金字塔Prompt架构(总纲)

输出按宏观→微观递进,层层约束。角色prompt尤重第六层(服装)与第三层(微表情),cosplay成败在此。

```
第1层 空间与构图    → 比例、场景、世界观背景(定调)
第2层 主体与人物    → 角色名、年龄、种族概貌(锚点)
第3层 微相与情绪    → 五官、微表情、眼神量化、角色气质(传神)
第4层 姿态与动势    → 站立/动态、武器/道具交互、衣摆联动(生姿)
第5层 服装与质感    → 款式、面料、铠甲/布料/配饰、标志性细节(定性)
第6层 光影与镜头    → 光质、色温、焦段、景深、质量标签(定质)
```

每层须呼应角色世界观。不可出现"第1层仙侠古风,第6层赛博朋克"之语义冲突。

---

## 思考维度框架(17 维度)

### 一、主体层(6 维度)

| 维度 | 思考问题 | 示例方向 |
|------|---------|---------|
| **subject** | 主体是什么? | 角色、产品、场景 |
| **age** | 年龄设定? | 少女、青年、成熟、御姐、萝莉 |
| **model** | 身体特征? | 体型、肤色、比例 |
| **face** | 面部特征?见"微表情精度控制" | 五官、表情、眼神方向 |
| **pose** | 姿态动作? | 站姿、坐姿、动态、武器/道具交互 |
| **hair** | 发型特征? | 颜色、长度、造型、发饰 |

### 二、服装层(1 维度)

| 维度 | 思考问题 | 示例方向 |
|------|---------|---------|
| **costume** | 服装特征?见"服装深度描述" | 款式、材质、颜色、铠甲/布料、标志性配饰、版型 |

### 三、风格层(2 维度)

| 维度 | 思考问题 | 示例方向 |
|------|---------|---------|
| **style** | 整体风格?见"风格参考表" | 杂志风、电影风、东方玄幻、赛博朋克、极简、青蓝暖橙仙侠 |
| **mood** | 情绪氛围? | 梦幻、冷酷、温暖、神秘、寂寥 |

### 四、环境层(3 维度)

| 维度 | 思考问题 | 示例方向 |
|------|---------|---------|
| **environment** | 场景环境? | 室内、室外、虚拟、抽象、根据世界观 |
| **lighting** | 光影效果?见"光质描写指南" | 自然光、舞台光、霓虹、柔光 |
| **composition** | 构图方式? | 比例、视角、焦点、留白 |

### 五、镜头层(2 维度)← 新增

| 维度 | 思考问题 | 示例方向 |
|------|---------|---------|
| **lens** | 镜头语言?见"镜头语言指南" | 焦段、光圈、景深、透视、电影感 |
| **quality_tags** | 质量标签?见"质量标签体系" | 渲染精度、平台特定词、风格定调词 |

### 六、文字层(1 维度)

| 维度 | 思考问题 | 示例方向 |
|------|---------|---------|
| **typography** | 文字排版? | 标题、副标题、字体风格、层级 |

### 七、控制层(2 维度)

| 维度 | 思考问题 | 示例方向 |
|------|---------|---------|
| **negative** | 避免什么? | 常见错误、不需要的元素 |
| **aspect_ratio** | 画面比例? | **根据用户需求决定** |

---

## 层级化描述法则

每个维度的描述遵循三层结构:

```
维度名称
├── 基础描述(一句话定义核心)
├── 特征列表(3-5 个关键词)
└── 细节补充(可选,具体参数)
```

关键:**每层都须考量正反双向约束**——不仅要写"是什么",还要写"不是什么"。

---

## 美学深度维度(可选)

对于追求更高美学品质的Prompt,可增加以下思考:

### 情感内核(悦意层)
- 这个角色/场景的情感本质是什么?
- 画面应触发观者的何种情绪?
- 关键词:孤独、温暖、力量、脆弱、神秘、希望...

### 隐喻表达(悦神层)
- 有无象征性元素可融入?
- 是否需要留白或开放性构图?
- 文化/哲学内涵如何通过视觉传达?

### 示例
**普通Prompt**:角色海报,赛博朋克风格
**深度Prompt**:角色海报,赛博朋克风格,情感内核是"高科技低生活"的孤独感,通过霓虹灯下的阴影和模糊的路人传达

---

## 微表情精度控制框架(face 维度强化)

角色prompt中,表情是角色灵魂的窗口。模糊的"微笑""冷酷"远不如精确的微表情描述。

### 六维微表情控制

| 控制维度 | 描述方法 | 示例 |
|---------|---------|------|
| **眼神方向** | 量化+锚点:直视度0~100% + 目光落点 | "眼睑微垂约1/5,目光落于镜头前寸许" |
| **嘴部细节** | 开合度+嘴角方向 | "唇角微扬不露齿,不刻意微笑" |
| **眉毛/眼睑** | 高度+弧度量化 |

_meta.json

{
  "ownerId": "kn71rk0chjcdy7ffgfc08hh9gd83ehq8",
  "slug": "cosprompt",
  "version": "2.3.0",
  "publishedAt": 1786642984163
}

skill-card.md

## Description:

Cosprompt generates structured AI image prompts from a character or theme, using a 17-dimension framework for JSON, Markdown, and plain text outputs for tools such as Midjourney and Stable Diffusion.

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

## Publisher:

[fslong520](https://clawhub.ai/user/fslong520)

### License/Terms of Use:

MIT-0

## Use Case:

External creators and developers use this skill to turn character, cosplay, product, or scene ideas into structured prompts for image-generation tools. It is intended to help organize visual subject, style, composition, lighting, lens, typography, negative prompt, and aspect-ratio details.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The security review flagged under-18 age presets in a cosplay or glamour prompt workflow without clear safety boundaries.

Mitigation: Review or remove under-18 presets before deployment, or require that minors are depicted only in age-appropriate, non-sexual contexts without suggestive clothing, pose, body emphasis, or mood tags.

Risk: The artifact declares broad Write and Edit tool permissions for a prompt-generation workflow.

Mitigation: Remove file-modification permissions unless the deployment specifically requires the skill to modify local files.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/fslong520/skills/cosprompt)

## Skill Output:

**Output Type(s):** [Text, Markdown, JSON, Guidance]

**Output Format:** [JSON, Markdown, and plain text prompt content]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Uses a 17-dimension image-prompt structure covering subject, age, model, face, pose, hair, costume, style, mood, environment, lighting, composition, lens, quality tags, typography, negative prompt, and aspect ratio.]

## Skill Version(s):

2.3.0 (source: frontmatter and server release evidence)

## 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.

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/fslong520/skills/cosprompt",
      "sourceUrl": "https://clawhub.ai/fslong520/skills/cosprompt",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T23:21:24.897Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-fslong520-cosprompt/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-fslong520-cosprompt/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-10T23:21:24.897Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1.2K downloads",
      "href": "https://clawhub.ai/fslong520/cosprompt",
      "sourceUrl": "https://clawhub.ai/fslong520/cosprompt",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T23:21:24.897Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "2.3.0",
      "href": "https://clawhub.ai/fslong520/cosprompt",
      "sourceUrl": "https://clawhub.ai/fslong520/cosprompt",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-13T17:43:04.163Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-fslong520-cosprompt/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-fslong520-cosprompt/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 2.3.0",
      "description": "新增风格参考表(9条目);新增青蓝暖橙仙侠风控制框架(冷暖对比为魂、场景灵活);style维度示例补充",
      "href": "https://clawhub.ai/fslong520/cosprompt",
      "sourceUrl": "https://clawhub.ai/fslong520/cosprompt",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-13T17:43:04.163Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 11, 2026.

Sponsored

Ads related to cosprompt and adjacent AI workflows.