OpenClaw Role Builder

Build and manage OpenClaw roles — create AI character personas and generate identity-consistent photos — installable via ClawHub or git clone.

What This Skill Does

Capability	Sub-skill	Example triggers
Character creation — build a full 6-file persona (identity, soul, voiceprint, …) for any public figure or fictional character	INLINECODE0	创建角色, 创建clone, 新建人物, "create a character"
Character switching — swap the active character in your workspace

openclaw-character-creator | /shift, 切换角色 | | Identity-consistent selfies & portraits — generate images where the character's face stays consistent | tuqu-photo-api | 自拍, 写真, 发张图, "take a selfie" | | Freestyle image generation — landscapes, objects, edits without a character in frame | tuqu-photo-api | 风景, 物品, 角色出镜, edit-only | | Prompt enhancement, presets, billing — discover styles, improve prompts, check balance, recharge | tuqu-photo-api | "enhance prompt", "check balance" |

Installation

Via ClawHub (recommended)

CODEBLOCK0

Via npx skills

CODEBLOCK1

Or install individual sub-skills:

CODEBLOCK2

Manual (git clone)

CODEBLOCK3

Prerequisites

Requirement	Why
python3	Required by `tuqu-photo-api` for the `tuqu_request.py` helper
TuQu service key

Needed for authenticated image-generation calls — obtain from | | OpenClaw | The host agent that loads and executes these skills |

Verify Installation

CODEBLOCK4

Quick Start

Once installed, start a new OpenClaw session and try:

- "帮我创建一个科比的角色" — creates a Kobe Bryant character with full persona files
"来张自拍" — generates an identity-consistent selfie of the current character
"/shift" — switches to a different character in your roster
"拍张风景照" — generates a landscape without forcing the character into frame

Included Skills

openclaw-character-creator

Build high-consistency AI character personas with a full 6-file model (3 auxiliary + 3 main). Supports both well-known public figures and fictional/original characters, with workspace scaffolding and global role registration.

See openclaw-character-creator/SKILL.md for full usage.

tuqu-photo-api

Generate identity-consistent selfies, portraits, group photos, and freestyle images for OpenClaw characters via the tuqu.ai API. Covers prompt enhancement, preset discovery, character management, billing, and recharge flows.

See tuqu-photo-api/SKILL.md for full usage.

File System Access

This skill collection writes to the following paths:

Skill	Path	What is stored
openclaw-character-creator	INLINECODE9	Character names and workspace paths (no credentials)
openclaw-character-creator

No service keys, tokens, or other credentials are persisted to disk by any script in this collection.
TuQu service keys are only used at runtime via --service-key CLI flags and are never written to config files.

Security Boundaries

1. Write scope: All file writes are confined to ~/.openclaw/ (the paths listed above). No

skill in this collection writes outside that directory.

2. Read scope: Skills read only their own bundled reference files (under the skill's

references/ directory) and character workspace files under ~/.openclaw/. No arbitrary filesystem reads.

3. Credential handling: TuQu service keys are passed exclusively via the --service-key CLI

flag to tuqu_request.py. The script does not read credentials from environment variables, config files, or any persisted store. Keys must never be written to disk.

4. Network scope: All outbound API calls go through scripts/tuqu_request.py, which restricts

requests to the known hosts (photo.tuqu.ai, billing.tuqu.ai). No ad-hoc curl, wget, or other HTTP tools.

5. Shell commands: Only the specific bundled Python scripts and mkdir for workspace

scaffolding are executed. No arbitrary shell commands.

Dependencies

The openclaw-character-creator skill expects tuqu-photo-api to be installed as well. Install both for full functionality.

OpenClaw 角色构建器

构建和管理OpenClaw角色——创建AI角色人设并生成身份一致的照片——可通过ClawHub或git clone安装。

该技能的功能

能力	子技能	触发示例
角色创建 — 为任何公众人物或虚构角色构建完整的6文件人设（身份、灵魂、声纹……）	openclaw-character-creator	创建角色, 创建clone, 新建人物, create a character
角色切换 — 在工作区中切换当前激活的角色

安装

通过ClawHub（推荐）

bash
clawhub install openclaw-role-builder

通过npx skills

bash
npx skills add tuquai/openclaw-role-builder --all

或安装单个子技能：

bash
npx skills add tuquai/openclaw-role-builder --skill openclaw-character-creator
npx skills add tuquai/openclaw-role-builder --skill tuqu-photo-api

手动安装（git clone）

bash
git clone https://github.com/tuquai/openclaw-role-builder.git ~/.openclaw/skills/openclaw-role-builder

前提条件

要求	原因
python3	tuqu-photo-api 的 tuqu_request.py 辅助脚本需要
TuQu服务密钥

用于认证的图像生成调用——从获取 | | OpenClaw | 加载和执行这些技能的主代理 |

验证安装

bash
openclaw skills list

应同时显示 openclaw-character-creator 和 tuqu-photo-api

快速开始

安装完成后，启动一个新的OpenClaw会话并尝试：

- 帮我创建一个科比的角色 — 创建包含完整人设文件的科比·布莱恩特角色
来张自拍 — 生成当前角色身份一致的自拍照
/shift — 切换到角色列表中的另一个角色
拍张风景照 — 生成风景图像，不强制角色出镜

包含的技能

openclaw-character-creator

使用完整的6文件模型（3个辅助文件 + 3个主文件）构建高一致性的AI角色人设。支持知名公众人物和虚构/原创角色，包含工作区脚手架和全局角色注册。

完整用法请参见 openclaw-character-creator/SKILL.md。

tuqu-photo-api

通过tuqu.ai API为OpenClaw角色生成身份一致的自拍、肖像、合影和自由风格图像。涵盖提示词增强、预设发现、角色管理、计费和充值流程。

完整用法请参见 tuqu-photo-api/SKILL.md。

文件系统访问

该技能集合写入以下路径：

技能	路径	存储内容
openclaw-character-creator	~/.openclaw/ROLES.json	角色名称和工作区路径（不含凭证）
openclaw-character-creator

本集合中的任何脚本均不会将服务密钥、令牌或其他凭证持久化到磁盘。
TuQu服务密钥仅在运行时通过 --service-key CLI标志使用，绝不会写入配置文件。

安全边界

1. 写入范围： 所有文件写入仅限于 ~/.openclaw/（上述列出的路径）。本集合中的任何技能都不会写入该目录之外。
读取范围： 技能仅读取其自带的参考文件（位于技能的 references/ 目录下）以及 ~/.openclaw/ 下的角色工作区文件。不进行任意文件系统读取。
凭证处理： TuQu服务密钥仅通过 --service-key CLI标志传递给 tuqurequest.py。该脚本不会从环境变量、配置文件或任何持久化存储中读取凭证。密钥绝不能写入磁盘。
网络范围： 所有出站API调用均通过 scripts/tuqurequest.py 进行，该脚本将请求限制在已知主机（photo.tuqu.ai、billing.tuqu.ai）。不使用临时的 curl、wget 或其他HTTP工具。
Shell命令： 仅执行特定的捆绑Python脚本和用于工作区脚手架搭建的 mkdir 命令。不执行任意shell命令。

依赖关系

openclaw-character-creator 技能期望同时安装 tuqu-photo-api。请同时安装两者以获得完整功能。

openclaw-role-builder开爪角色构建器