Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Supreme-Ultimate/novel-to-script-team --skill image-to-prompt-skillgit clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-teamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/image-to-prompt-skill)<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/image-to-prompt-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/image-to-prompt-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/image-to-prompt-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/image-to-prompt-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02608 |
| Opus 5 | $0.00000 | $0.01304 |
| Sonnet 5 | $0.00000 | $0.00522 |
| Haiku 4.5 | $0.00000 | $0.00261 |
Grade A, and why
image-to-prompt-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
image-to-prompt-skill
功能
从图片中提取视觉描述,生成可用于文生图的提示词。
使用场景
- 参考图分析:分析参考图片,生成风格一致的提示词
- 风格迁移:从现有图片提取风格特征,应用到新场景
- 提示词优化:对比生成图片与目标效果,优化提示词
- 资产复用:从历史项目图片中提取提示词,复用到新项目
输入
- 图片文件路径:本地图片文件(PNG、JPG、WEBP 等)
- 分析维度(可选):
full:完整分析(默认,包含所有元素)character:聚焦人物(外观、服装、表情、姿态)scene:聚焦场景(环境、光线、氛围、道具)composition:聚焦构图(景别、角度、运镜、色彩)
输出
- 提示词文件:
outputs/{剧本名}/reverse-prompts/{图片名}-prompt.md - 内容包含:
- 原图路径
- 分析维度
- 提示词(叙事描述式)
- 关键元素清单(人物、场景、构图、色彩、光影、氛围)
执行流程
- 读取图片:加载本地图片文件
- 编码图片:将图片编码为 base64 格式
- 调用 API:使用 gemini-3.1-pro-preview 模型分析图片
- 提取元素:根据分析维度提取关键视觉元素
- 生成提示词:将视觉元素转化为叙事描述式提示词
- 输出文件:保存提示词到指定路径
API 调用示例
from openai import OpenAI
import base64
import os
# 初始化客户端
client = OpenAI(
api_key="your-api-key",
base_url=os.environ["NANO_BANANA_BASE_URL"]
)
# 读取并编码图片
with open("image.jpg", "rb") as f:
image_data = base64.b64encode(f.read()).decode("utf-8")
# 调用 API
response = client.chat.completions.create(
model="gemini-3.1-pro-preview",
messages=[{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{image_data}"
}
},
{
"type": "text",
"text": "请详细描述这张图片的视觉元素,包括人物、场景、构图、色彩、光影、氛围等,生成可用于文生图的提示词。"
}
]
}]
)
prompt = response.choices[0].message.content
print(prompt)
提示词生成原则
-
叙事描述式:使用完整句子描述,避免关键词堆叠
- ❌ 错误:
男性,黑色西装,严肃表情,办公室背景 - ✅ 正确:
一位身穿黑色西装的中年男性站在现代办公室中,表情严肃,目光锐利,背景是落地窗和城市天际线。
- ❌ 错误:
-
元素完整:覆盖 26 元素框架(参见
references/20-frame-description-elements.md)- 人物:外观、服装、表情、姿态、动作
- 场景:环境、道具、空间关系
- 构图:景别、角度、视角
- 色彩:主色调、色彩对比、色彩情绪
- 光影:光源、明暗对比、光影氛围
- 氛围:情绪基调、叙事意图
-
可复现性:描述足够精确,能够生成相似的图片
- 包含具体的细节(如"深蓝色西装"而非"西装")
- 包含空间关系(如"站在窗前"而非"站着")
- 包含情绪线索(如"严肃的表情"而非"表情")
-
风格一致:保持与项目整体风格一致
- 参考项目已有的角色和场景提示词
- 保持相同的描述风格和细节层次
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 256 lines · 0 tokens per session scan A eeadb70f71e2
image-to-prompt-skill is a skill published in the GitHub repository Supreme-Ultimate/novel-to-script-team (165 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,608 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.