Cxp Character Forge

从参考立绘通过 Tripo 兼容代理生成带贴图的 3D 人物，接续 Blender 外形检查、组件修整、按需绑骨动作与资产交付。用于人物建模和已有生成任务续作。

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add CXP-2024/cxp-character-forge --skill cxp-character-forge

Manual install

git clone --depth 1 https://github.com/CXP-2024/cxp-character-forge.git /tmp/cxp-character-forge
mkdir -p ~/.claude/skills
cp -r /tmp/cxp-character-forge/. ~/.claude/skills/cxp-character-forge

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# CXP Character Forge

使用本 skill 目录下的 `scripts/tripo_proxy.py`。首次安装执行 `python scripts/bootstrap.py` 获取固定版本依赖；读取 README 的配置方式。只向用户配置的代理地址发送密钥，不调用上游官方 CLI 的 configure。

## 任务与参考

尊重用户确认的设计、比例、定稿版本与静态/动画用途。先查已有资产和任务记录，避免重复生成。造新人物先确认本机装有 [Charakuru](https://github.com/nanocle/Charakuru) 源码（Releases 下载解压；Node 22+、Blender 5.2、VRM Add-on），作为三视图、重贴图分组、UV 恢复、权重迁移、表情与摇摆物理的方法库，见 [Charakuru 方法](references/charakuru-methods.md)。推荐路线：T 型正背设定图 → **整体一次生成**（每次只调用 1 个任务，不并行、不抽卡，非常耗积分）→ 灰模与网格检查，当场试拆头、头发/刘海、饰品、裙子（拆不开就改图重生成）→ 快速绑定并套一段简单 MMD 动作校验骨架，让 AI 修骨骼节点和权重 → Tripo 重贴图并转回 UV（最耗时）→ 表情 → 最后做物理；制作期间二次元角色默认用原神式快速三渲二材质加灰模检查（渲染快、方便迭代），最后一步才用 [genshin-blender-render](https://github.com/CXP-2024/genshin-blender-render) 做精细渲染；眼睛、嘴部和表情三样缺一不做：Charakuru 方法论、目标原脸型不变、参考角色的完整表情网络与贴图（含口腔结构），见 [表情前提](references/facial-expressions.md)、[眼眉流程](references/eye-brow-expression-workflow.md)；**不要把头和身体分开生成**（颈部接缝、比例、肤色难以接上，这点与 Charakuru 原版不同）。步骤、经验与 MMD 细节见 [人物流程](references/character-workflow.md)；组件拆分清单和每个组件该用 Tripo / Codex 投影 / 几何生成 / 平涂见 [分组件贴图](references/component-texturing.md)，脚本在 `scripts/component_tex/`。与 MMD / 原神 PMX 角色同框时的眼睛精细化（眼白上睑阴影、分层瞳孔、发光闪点）见 [眼睛精细化](references/eye-refinement.md)，脚本在 `scripts/eye_refine/`。Houdini 无界面裙发解算见 [houdini-cloth-hair](references/houdini-cloth-hair.md)；整首分段解算、已认可段只解后段拼接、真实多层裙解算（层间缝合、裙撑、灰模验收）、远端 Linux 安装、授权按机器占用的规则与分块整理见 [houdini-fullsong-remote](references/houdini-fullsong-remote.md)，脚本在 `scripts/houdini_song/`。

先核对 A/T 姿态、头身比例、手指、前后轮廓与遮挡。多视图必须同角色同姿态；不可靠侧背图不应强行参与生成。隐藏面属于补全假设。

Read the full skill on GitHub

Details

Skill name: cxp-character-forge
Repository: CXP-2024/cxp-character-forge
Repo updated: 30 October 2026

FAQ

What does the Cxp Character Forge skill do?

从参考立绘通过 Tripo 兼容代理生成带贴图的 3D 人物，接续 Blender 外形检查、组件修整、按需绑骨动作与资产交付。用于人物建模和已有生成任务续作。

How do I install the Cxp Character Forge skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add CXP-2024/cxp-character-forge --skill cxp-character-forge. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Cxp Character Forge popular?

It lives in CXP-2024/cxp-character-forge, which has 39 GitHub stars and 2 forks.

Related skills

Data Master

MAGA2010/data-master

Analyze datasets with preserved raw inputs, explicit cleaning decisions, reproducible figures and PDF reports. Full statistics for one tabular file; descriptive time-series analysis; integrity profiling for text, image, audio, geographic and mixed inputs. Use for data cleaning, EDA, group comparisons, statistical reports, 跑数据 or 数据分析 with a traceable evidence trail.

Images, Video & Audio

AI Avatar Video

creatify-ai/ai-avatar-video

Complete AI avatar and talking-head video toolkit. Includes script writing for talking-head content, persona selection frameworks, multi-scene composition, voice/audio best practices, green screen techniques, and UGC-style authenticity guides. Integrates with Creatify API for AI Avatar v1/v2, Aurora, Text-to-Speech, Custom Avatars, and Voice Cloning. Use when: "avatar video", "talking head", "AI spokesperson", "lip sync", "UGC video", "Aurora", "text to speech", "voice clone", "AI presenter", "lipsync", "custom avatar", "green screen avatar", "AI narrator", "spokesperson video", "script for av

Images, Video & Audio

Awwwards 3d

tsogjavklann/awwwards-3d

Build production-grade Awwwards-style scroll-driven 3D websites in the visual language of Active Theory, Lusion, 14islands, Bonhomme, Resn, Studio Freight, Locomotive, and Igloo Inc. Use when the user asks for an "Awwwards-style", "scroll-driven 3D", "WebGL hero", "3D landing page", "interactive product showcase", "scroll storytelling site", "cinematic web experience", "creative dev portfolio", "premium 3D site", "Lusion-style", "Active Theory-style", "scroll 3D animation", or mentions Three.js + GSAP + Lenis together. Also triggers on Mongolian phrases like "3D вэб", "scroll-тэй 3D", "premium

Images, Video & Audio

Game Sensitivity Coach

DenisSergeevitch/game-sensitivity-coach

Discover a gamer's mouse settings, transfer sensitivity between games, and refine aim from passive gameplay video and mouse logs. Use for mouse sensitivity calibration, scoped or ADS tuning, cm/360 conversion, or applying and restoring game sensitivity settings. The agent handles settings discovery, image review, and evidence logging; the gamer plays normally.

Images, Video & Audio

Xiaoer Upscale

Jane-xiaoer/claude-skill-xiaoer-upscale

在 Mac 上把图片本地放大/提清晰度(超分辨率),并装好「Finder 右键 → 快速操作 → 超分 4K/8K」。 USE WHEN 用户说图片放大、超分、提清晰度、图糊了、做高清版、把这张图变清楚、 4K/8K 图、image upscale、super resolution、右键放大图片、Mac 右键超分。纯本地离线、不用 API key、不花钱(OpenCV dnn_superres,CPU 即可)。

Images, Video & Audio

Autopunk Media Skills

ur-grue/autopunk-media-skills

394 production-tested Claude skills for media professionals — TV, journalism, YouTube, podcasts, screenwriting, newsletters, PR, and more

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.