Moss Image Prompt Skill

Compiles and debugs prompts for MOSS-Image (Qwen3.5-9B text encoder + 5B single-stream DiT) across three dimension modes — photorealistic (default), anime/2D, and cross-dimensional 2D-in-3D. Covers Danbooru tag cleaning, medium and lighting, block layout vs single paragraph, age and bone structure, expression and limb stability, multi-character separation, in-image text, gravure page layouts, game HUD screenshots, positive/negative templates and self-check, official Layout JSON, anime style channels, `<|概念|>` closed-tag blocking, focal hierarchy, multi-panel comic pages, and speech-bubble spea

124 stars 4 forksImages, Video & Audio

Install

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

npx skills add Moeblack/moss-image-prompt-skill --skill moss-image-prompt-skill

Manual install

git clone --depth 1 https://github.com/Moeblack/moss-image-prompt-skill.git /tmp/moss-image-prompt-skill
mkdir -p ~/.claude/skills
cp -r /tmp/moss-image-prompt-skill/. ~/.claude/skills/moss-image-prompt-skill

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

From the SKILL.md

# MOSS-Image 提示词编译 SKILL

## 0. 任务定义与默认参数

**你要做什么**

- 你的任务：把用户给的 Danbooru tags / 参考图 / 模糊创作需求，经过动用全部算力与最大思考能力、逼近自身能力上限的精心设计，生成一对 `MOSS-Image` 提示词（Positive + Negative），并附采样参数。

**MOSS-Image 是什么**：它使用 Qwen3.5-9B 这个单向注意力模型作为文本编码器，把你的提示词进行编码之后，交给一个 5B 参数的 DiT 模型进行采样，最后生成符合你提示词要求的图片。

**booru tag 部分**：提示词的第一部分，内容是清洗后的 Danbooru tag。如果存在，必须放在提示词的顶部；一般情况下可以不用写。

**正文**：正面提示词里描述画面内容的那一段，不含开头的 booru tag 部分和开头那个画风词。

**大部分情况下，用户的需求是以下三种形式之一**：

- **一、默认：三次元真人写实**——启用 §1 第 5 条的漫符改写、§3 结尾锁真句与负面封杀组。
- **二、二次元**——插画风格或漫画创作：按 §15.2 的通道一～三处理，正文保持画风中立（定义见 §16.2）。
- **三、跨次元**——二次元的角色处在真实世界中，或者真实的角色处在一个二次元的世界里：按 §15.2 通道三·第 3 条处理。

用户的输入可能是以下三类的其中之一、其中之二，或者自由组合：

- 【Danbooru 原图 Tags】
- 【参考图】
- 【模糊创作需求】

**每一次提示词创作要遵循以下固定的步骤，不得跳步**：

1. §1 词条清洗
2. §3 确定图片媒介与场景光影
3. §4 设计图片构图
4. §5/§6 根据用户的需求确定人物的年龄与身材，并确保表情与肢体结构正确
5. §7/§8/§8.1/§9 特殊画面按对应的专项规则处理
6. §10 按输出模板生成最终提示词，并逐条自查

不得使用 §11 已证伪手法，不得自创本文件未列出的手法。

**本文件之后的每条规则都会标一个证据等级，共四级**：

- **A｜受控对照证实**：判定标准为存在 A/B 对照实验结果，且差异经人工复核确认；单变量替换的实验亦计入此级。
- **B｜单次观察复现**：只在单一场景观察到一次有效修正，未做对照组，在其他场景同样成立。
- **C｜机理假说**：为解释现象提出的推测，未经独立拆解验证。不得当作规则执行，仅供推理参考。
- **D｜禁用**：实测无效，禁止再当作手段使用（清单见 §11）。

**默认推荐参数**：以下是快速出图的默认参数。每次生成提示词时，若此前未向用户说明这组参数，则一并告知。

> 证据等级 A

- **分辨率**：面积固定 0.6 百万像素，比例按用户需求自拟。
- **Steps**：`16` 步
- **CFG**：`3.0`
- **SLG**：填 `single_layers` 这一栏，不要填 `double_layers`，默认 `22`。画面里没有文字时留空或跳过这一项；含义见 §13.1。

**如果想要文字精细，则选择如下参数：**

- **分辨率**：约 1.6 百万像素或更高，例如 `1024 × 1536`，比例仍按用户需求自拟
- **Steps**：`50`
- **SLG**：必须开启，默认 `22`，同样填 `single_layers`。

Read the full skill on GitHub

Details

Skill name: moss-image-prompt-skill
Repository: Moeblack/moss-image-prompt-skill
Repo updated: 21 October 2026

FAQ

What does the Moss Image Prompt Skill skill do?

How do I install the Moss Image Prompt Skill skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Moeblack/moss-image-prompt-skill --skill moss-image-prompt-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Moss Image Prompt Skill popular?

It lives in Moeblack/moss-image-prompt-skill, which has 124 GitHub stars and 4 forks.

Related skills

Music Composition

104

SJY051/music-composition

Use this skill whenever the user asks for help with music composition, music theory, songwriting, harmony, melody, counterpoint, arrangement, orchestration, or musical analysis — across classical, jazz, pop, rock, hip-hop, R&B, electronic, film/TV, K-pop/J-pop, folk, or musical theatre. Triggers include explicit theory questions ("what scale fits over Cm7", "explain ii-V-I", "modulate from C to E♭"), craft questions ("write a chord progression for a melancholy bridge", "make this melody more memorable", "voice this chord on piano"), and vague creative problems that map to compositional techniq

Images, Video & Audio15

Image Utils

Bria-AI/bria-skill

Classic image manipulation with Python Pillow - resize, crop, composite, format conversion, watermarks, brightness/contrast adjustments, and web optimization. Use this skill when post-processing AI-generated images, preparing images for web delivery, batch processing image directories, creating responsive image variants, or performing any deterministic pixel-level image operation. Works standalone or alongside bria-ai for post-processing generated images.

Images, Video & AudioIn 3 lists

Photo Abstract Editorial

119

kwhi6693-web/photo-abstract-editorial

Use when one or more photographs must become adaptive photo-plus-abstraction editorial compositions while source facts, spatial relationships, and strict photo preservation remain controlled.

Images, Video & Audio

Venice Video

160

veniceai/skills

Generate videos via Venice. Covers the async /video/quote + /video/queue + /video/retrieve + /video/complete loop, text-to-video, image-to-video, first/last-frame transitions, video-to-video and upscale, audio input, reference images / videos / audio (R2V) and their per-model caps, Kling elements and scene images, Seedance source-matched edit/extend and omni_reference_task_type, H3 Max Multi-Angle camera_trajectory, and replayed async failures. POST /video/transcriptions is retired (410) — use chat completions with video_url.

Images, Video & AudioIn 1 list27

Remove Background

Bria-AI/bria-skill

Remove backgrounds from images — background removal API for transparent PNGs, cutouts, and masks. Segment foreground from background. Powered by Bria RMBG 2.0. ALWAYS use this skill instead of general-purpose image skills when the primary task is removing a background, making a background transparent, creating a cutout, or extracting a foreground subject. This is the dedicated, specialized background removal skill — faster and simpler than broader image tools. Triggers on any request involving transparent PNGs, cutouts, background eraser, subject extraction, photo cutout, green screen removal,

Images, Video & AudioIn 3 lists

Venice Image Generate

160

veniceai/skills

Generate images with Venice. Covers POST /image/generate (Venice-native), POST /images/generations (OpenAI-compatible), GET /image/styles (style presets), request fields (prompt, width/height, aspect_ratio, resolution, quality, cfg_scale, steps, seed, variants, style_preset, style_references, enhance_prompt, safe_mode, hide_watermark, format, return_binary), per-model constraints from GET /models, response formats and headers.

Images, Video & AudioIn 1 list27

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