Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-teamnpx agentmods add skills/supreme-ultimate/novel-to-script-team/image-generation-skillWrote 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-generation-skill)<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/image-generation-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/image-generation-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-generation-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/image-generation-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 | $0.00035 | $0.01145 |
| Opus 5 | $0.00017 | $0.00573 |
| Sonnet 5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
image-generation-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 10d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
image-generation-skill
概述
调用 nano banana API 将服化道/分镜提示词转化为图片。支持两种模式:
- 纯文本生图:提示词 → API → PNG 图片
- 参考图生图:提示词 + 本地参考图(base64 编码)→ API → PNG 图片
前置条件
.env或环境变量中配置了NANO_BANANA_API_KEY和NANO_BANANA_BASE_URL- Python 3 已安装
requests库已安装(pip install requests)
输入
- 提示词文件:
outputs/{剧本名}/assets/character-prompts.md、scene-prompts.md或prop-prompts.md - 单条提示词:直接传入文本
- 可选参考图:本地图片路径
输出
- 角色图:
outputs/{剧本名}/images/characters/{前缀}-{序号}.png - 场景图:
outputs/{剧本名}/images/scenes/{前缀}-{序号}.png - 物品图:
outputs/{剧本名}/images/props/{前缀}-{序号}.png
执行流程
步骤1:环境检查
确认 .env 中有 NANO_BANANA_API_KEY 和 NANO_BANANA_BASE_URL:
test -f .env && grep -q "NANO_BANANA_API_KEY" .env && grep -q "NANO_BANANA_BASE_URL" .env
步骤2:生成角色图(第一批,无外部依赖)
python scripts/generate_image.py \
--prompt-file "outputs/{剧本名}/assets/character-prompts.md" \
--output-dir "outputs/{剧本名}/images/characters" \
--prefix char
步骤3:生成物品图(第二批,白底独立策略,仅同族物品间有依赖)
python scripts/generate_image.py \
--prompt-file "outputs/{剧本名}/assets/prop-prompts.md" \
--output-dir "outputs/{剧本名}/images/props" \
--image-base-dir "outputs/{剧本名}/images" \
--prefix prop
步骤4:生成场景图(第三批,依赖角色图和物品图,通过 --image-base-dir 跨文件引用)
python scripts/generate_image.py \
--prompt-file "outputs/{剧本名}/assets/scene-prompts.md" \
--output-dir "outputs/{剧本名}/images/scenes" \
--image-base-dir "outputs/{剧本名}/images" \
--prefix scene
生成顺序很重要:角色 → 物品 → 场景 → 帧图,确保被引用的图先生成。场景引用角色图和物品图,所以必须在场景之前生成。帧图依赖角色图和场景图,所以最后生成。
步骤5:生成帧图(第四批,按集组织,依赖角色图 + 场景图)
帧图由 seedance-storyboard-skill 在生成提示词时同步输出到 03-frame-requests.md。帧图按集组织,不跨集累积。
python scripts/generate_image.py \
--prompt-file "outputs/{剧本名}/storyboard/ep<N>/03-frame-requests.md" \
--output-dir "outputs/{剧本名}/images/frames/ep<N>" \
--image-base-dir "outputs/{剧本名}/images" \
--prefix frame
帧图类型说明:
- 首帧图:用于 I2V-首帧模式,锁定开场构图
- 尾帧图:用于首尾帧模式,锁定结束画面
- 分镜参考图:用于多参考模式多时段,引导各时段画面
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.
- 10d ago First seen · 104 lines · 35 tokens per session scan A 781e4b77a74c
image-generation-skill is a skill published in the GitHub repository Supreme-Ultimate/novel-to-script-team (163 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 1,145 once invoked, about $0.0002 per session on Opus 5. 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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
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.