
Story Cover
- 9.2k installs
- 4.7k repo stars
- Updated July 27, 2026
- worldwonderer/oh-story-claudecode
story-cover is an agent skill that analyzes novel genre and generates Chinese web fiction cover images with embedded title and author text via GPT-Image-2.
About
The story-cover skill generates professional Chinese web novel covers from a book title and author name. Agents infer genre from title keywords using cover-styles references, then build English prompts with text, style, and scene layers including platform-specific typography rules. Required environment variables include GPT_IMAGE_API_KEY and BOOK_DIR; optional settings cover base URL, model, size, and reference images for image-to-image edits. The workflow collects title, pen name, target platform, and output directory, produces two or three composition variants, calls gpt-image-2 via curl with jq-safe JSON bodies, decodes base64 PNG output with versioned filenames, and saves prompt copies for iteration. Quality checks cover text rendering, genre match, composition, and platform fit. Image-to-image mode downloads URL references and posts multipart form data to the edits endpoint. Triggers include /story-cover, cover design requests, and Chinese phrases for novel cover generation. Use when creating web fiction covers with embedded title and author text.
- Infers genre from title keywords with priority rules and platform style references.
- Builds three-layer English prompts for typography, platform style, and scene composition.
- Calls gpt-image-2 via curl and jq with base64 decode and versioned PNG output.
- Supports text-to-image and reference-image edits with saved prompt and ref sidecars.
- Quality checklist covers text clarity, genre match, composition, and platform adaptation.
Story Cover by the numbers
- 9,213 all-time installs (skills.sh)
- +764 installs in the week ending Jul 28, 2026 (Skillselion tracking)
- Ranked #90 of 1,340 Generative Media skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
story-cover capabilities & compatibility
- Capabilities
- genre inference from title keywords with platfor · three layer english prompt construction for text · gpt image 2 api integration with curl, jq, and b · text to image and reference image edit workflows · versioned output with prompt sidecar files for i
- Works with
- openai
- Use cases
- image generation · copywriting · orchestration
- Requires keys
- GPT_IMAGE_API_KEY
What story-cover says it does
根据书名、作者名自动分析题材风格,调用 GPT-Image-2 直接生成含标题和署名的专业级网文封面。
npx skills add https://github.com/worldwonderer/oh-story-claudecode --skill story-coverAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 9.2k |
|---|---|
| repo stars | ★ 4.7k |
| Security audit | 1 / 3 scanners passed |
| Last updated | July 27, 2026 |
| Repository | worldwonderer/oh-story-claudecode ↗ |
How do I generate a genre-appropriate web novel cover with readable Chinese title and author typography for a target platform?
Generate Chinese web novel cover images with genre-aware typography and GPT-Image-2 API calls via curl, jq, and base64.
Who is it for?
Authors or publishers creating vertical web novel covers who can provide GPT_IMAGE_API_KEY, title, pen name, and output directory.
Skip if: Skip for Western print book layouts, video thumbnails, or cover work without OpenAI-compatible image API access.
When should I use this skill?
User triggers /story-cover, asks for novel cover design, or requests Chinese web fiction cover generation with title and author.
What you get
Versioned PNG covers under BOOK_DIR with saved prompt text, optional reference metadata, and platform-aligned visual style.
Files
story-cover:小说封面生成
你是小说封面设计师。根据书名和题材,调用 GPT-Image-2 一次性生成包含书名和作者名的完整封面。
核心原则:封面是读者的第一印象,一眼传达题材和氛围。
---
环境变量
| 变量 | 必填 | 默认 | 说明 |
|---|---|---|---|
GPT_IMAGE_API_KEY | ✅ | — | OpenAI 或兼容代理的 API Key |
GPT_IMAGE_BASE_URL | https://api.openai.com/v1 | 兼容代理时改这个 | |
GPT_IMAGE_MODEL | gpt-image-2 | 仅在测试新模型时覆盖 | |
GPT_IMAGE_SIZE | 1024x1536 | gpt-image-2 要求两边为 16 倍数、比例 ≤ 3:1 | |
BOOK_DIR | ✅ | — | 输出目录,建议 ./covers/<书名> |
REF_IMAGE | — | 参考图本地路径或 URL;设置后走 images/edits 图生图 |
备注:gpt-image-2始终返回 base64,请求体不要带response_format(旧 DALL-E 参数,gpt-image 系列不支持)。
---
生成流程
Step 1:收集信息
必填:书名、作者名(笔名)、目标平台、输出目录 BOOK_DIR(建议 ./covers/<书名>,调用前 export) 选填:参考图 REF_IMAGE(本地路径或 URL,设置后切换到图生图)、风格偏好、尺寸(默认竖版 1024x1536)
根据目标平台确定封面风格,加载 references/cover-styles.md 获取详细平台和题材风格。
Step 1.5:题材判定
扫描书名(必要时简介)中的关键词,对照 references/cover-styles.md 的「题材推断规则」表选定题材。
- 单题材命中 → 直接采用
- 多题材命中 → 按优先级取一:仙侠 > 西幻 > 古言 > 现言 > 都市 > 悬疑 > 科幻 > 历史 > 灵异 > 轻小说
- 零命中 → 默认
都市
Step 2:构建提示词
提示词 = 文字层 + 风格层 + 画面层,全部用英文编写。
文字层:书名 + 作者名字体设计
在提示词中直接包含中文书名和作者名,GPT-Image-2 可直接渲染。重点描述字体风格:
Title text '书名' at top center in [书名字体风格].
Author name '作者名' at bottom center in [作者名字体风格].书名字体风格
| 题材 | 描述关键词 |
|---|---|
| 玄幻/仙侠 | bold golden brush calligraphy with metallic glow and sharp strokes |
| 都市 | modern bold sans-serif with metallic silver finish |
| 古言/宫斗 | elegant golden traditional Kai script with ornate decoration |
| 现言/甜宠 | soft rounded handwritten style in white with pink glow |
| 悬疑/推理 | distorted bold cracked letters in blood red |
| 科幻/末世 | neon glowing futuristic font in electric blue |
| 西幻 | metallic embossed fantasy lettering with glow effect |
| 历史/军事 | heavy stone-carved seal script in deep red |
| 灵异/恐怖 | eerie dripping handwritten font in sickly green |
| 轻小说 | colorful cartoon outlined bubbly font |
作者名字体风格(重点:作者名必须精心设计,不能只是"小字")
作者名虽小,但是封面专业感的关键。必须指定:字体 + 颜色 + 装饰元素,让作者名与书名风格呼应但不抢焦点。
| 题材 | 作者名风格提示词 |
|---|---|
| 玄幻/仙侠 | small refined white serif text with faint golden glow, flanked by delicate cloud-scroll ornaments on both sides, resting on a thin horizontal gold line |
| 都市 | small clean white modern text with subtle drop shadow, positioned above a thin silver horizontal divider line |
| 古言/宫斗 | small elegant dark red traditional text inside a thin golden rectangular border frame with corner decorations |
| 现言/甜宠 | small soft pink-white handwritten text with a tiny heart motif on the left side, light sparkle effect |
| 悬疑/推理 | small pale grey text with slight blur effect, almost hidden in the shadows, a thin cracked line underneath |
| 科幻/末世 | small crisp white monospace text with subtle cyan scanline overlay, flanked by small geometric brackets |
| 西幻 | small bronze medieval script text with aged parchment texture, enclosed in a small decorative shield or banner shape |
| 历史/军事 | small dignified white Song typeface text above a double horizontal line in dark red |
| 灵异/恐怖 | small faded grey-green text slightly tilted, with a thin dripping ink line above |
| 轻小说 | small playful rounded white text with pastel color outline, tiny star decorations on both sides |
作者名通用规则:
- 大小:
small(不能太大抢书名焦点,也不能太小看不清) - 位置:
at bottom center,与画面底部保持适当间距 - 必须有装饰元素:线条/边框/小图标/光效中至少一种
- 颜色与背景形成对比但不刺眼
风格层:平台风格
平台风格的描述关键词统一来自 references/cover-styles.md 的「平台风格」节,按目标平台直接取对应关键词串使用,不在本文件维护副本以免与参考文件漂移。
画面层:题材 + 构图
从 references/cover-styles.md 读取题材对应的风格标签、色彩、人物、背景描述。
构图变体(首次输出 2-3 个方案):
| 方案 | 构图 | 适合题材 |
|---|---|---|
| A | 人物特写 + 场景 | 全题材通用 |
| B | 全身像 + 动态姿势 | 玄幻、都市、西幻 |
| C | 纯场景/氛围图 | 悬疑、科幻、历史 |
完整提示词模板
Chinese web novel cover design, [平台风格].
Title text '{书名}' at top center in [书名字体风格].
Author name '{作者名}' at bottom center in [作者名字体风格 — 从上表选择].
[题材风格标签]. [人物描述]. [背景描述].
[色彩指令]. [光效指令].
Professional book cover, high detail digital painting, portrait 2:3 ratio, no watermark提示词技巧(实测验证)
- 人物描述越具体越好:服饰、姿态、发型、表情、道具每个维度都指定
- 背景分层:前景(人物)→ 中景(场景)→ 远景(氛围)
- 光效是指定光源方向 + 颜色(如
dramatic golden light from above) - 用
digital painting style而非photo,避免真人照片感
Step 3:调用 API 并保存
gpt-image-2 始终返回 base64,请求体不要带 response_format。$PROMPT 为 Step 2 拼出的完整提示词。
两种调用方式二选一:未设置 REF_IMAGE → 走「文生图」;设置了 → 走「图生图」。
文生图(默认)
set -euo pipefail
: "${GPT_IMAGE_API_KEY:?请设置 export GPT_IMAGE_API_KEY=你的key}"
: "${PROMPT:?请先 export PROMPT=Step 2 拼好的完整提示词}"
BASE_URL="${GPT_IMAGE_BASE_URL:-https://api.openai.com/v1}"
MODEL="${GPT_IMAGE_MODEL:-gpt-image-2}"
SIZE="${GPT_IMAGE_SIZE:-1024x1536}"
BOOK_DIR="${BOOK_DIR:?请先 export BOOK_DIR=./covers/<书名>}"
mkdir -p "$BOOK_DIR/封面"
# 自增版本号,避免覆盖之前生成的封面
i=1
while [ -f "$BOOK_DIR/封面/封面_v${i}.png" ]; do i=$((i+1)); done
OUT="$BOOK_DIR/封面/封面_v${i}.png"
RESP=$(mktemp)
trap 'rm -f "$RESP"' EXIT
# 用 jq 拼 JSON 体,避免 PROMPT 里的引号/换行/中文把 shell 字符串撑破
BODY=$(jq -n \
--arg m "$MODEL" \
--arg p "$PROMPT" \
--arg s "$SIZE" \
'{model:$m, prompt:$p, size:$s}')
curl -fsS --max-time 180 --retry 2 --retry-delay 5 \
"$BASE_URL/images/generations" \
-H "Authorization: Bearer $GPT_IMAGE_API_KEY" \
-H "Content-Type: application/json" \
-d "$BODY" > "$RESP"
# API 出错时早退,避免把 error JSON 当成 base64 写成损坏 PNG
if jq -e '.error' "$RESP" >/dev/null 2>&1; then
echo "API error:" >&2
jq '.error' "$RESP" >&2
exit 1
fi
# `// empty` 让缺失字段输出空串而非 "null",配合下面的 -s 检查避免写出 3 字节假 PNG
jq -er '.data[0].b64_json // empty' "$RESP" | base64 --decode > "$OUT"
[ -s "$OUT" ] || { echo "empty or malformed output: $OUT" >&2; head -c 300 "$RESP" >&2; exit 1; }
# 落地提示词副本,方便迭代时基于上一次微调
printf '%s\n' "$PROMPT" > "${OUT%.png}.prompt.txt"
file "$OUT"
ls -lt "$BOOK_DIR/封面/"图生图(提供参考图时)
/v1/images/edits 走 multipart/form-data,不能 用 Content-Type: application/json。文本字段用 --form-string(避免 @ 被误判为文件引用),图片字段用 -F image=@path。
set -euo pipefail
: "${GPT_IMAGE_API_KEY:?请设置 export GPT_IMAGE_API_KEY=你的key}"
: "${PROMPT:?请先 export PROMPT=Step 2 拼好的完整提示词}"
BASE_URL="${GPT_IMAGE_BASE_URL:-https://api.openai.com/v1}"
MODEL="${GPT_IMAGE_MODEL:-gpt-image-2}"
SIZE="${GPT_IMAGE_SIZE:-1024x1536}"
BOOK_DIR="${BOOK_DIR:?请先 export BOOK_DIR=./covers/<书名>}"
REF_IMAGE="${REF_IMAGE:?请先 export REF_IMAGE=本地路径或 URL}"
mkdir -p "$BOOK_DIR/封面"
# 自增版本号
i=1
while [ -f "$BOOK_DIR/封面/封面_v${i}.png" ]; do i=$((i+1)); done
OUT="$BOOK_DIR/封面/封面_v${i}.png"
RESP=$(mktemp)
REF_TMP=""
trap '[ -n "$REF_TMP" ] && rm -f "$REF_TMP"; rm -f "$RESP"' EXIT
# URL 先下载到临时文件,本地路径直接用。用裸 mktemp 以保证 macOS/Linux 行为一致。
case "$REF_IMAGE" in
http://*|https://*)
REF_TMP=$(mktemp)
curl -fsSL --max-time 60 -o "$REF_TMP" "$REF_IMAGE"
REF_LOCAL="$REF_TMP"
;;
*)
[ -f "$REF_IMAGE" ] || { echo "参考图不存在: $REF_IMAGE" >&2; exit 1; }
REF_LOCAL="$REF_IMAGE"
;;
esac
curl -fsS --max-time 240 --retry 2 --retry-delay 5 \
"$BASE_URL/images/edits" \
-H "Authorization: Bearer $GPT_IMAGE_API_KEY" \
--form-string "model=$MODEL" \
--form-string "size=$SIZE" \
--form-string "prompt=$PROMPT" \
-F "image=@$REF_LOCAL" > "$RESP"
if jq -e '.error' "$RESP" >/dev/null 2>&1; then
echo "API error:" >&2
jq '.error' "$RESP" >&2
exit 1
fi
# `// empty` 让缺失字段输出空串而非 "null",配合 -s 检查避免写出 3 字节假 PNG
jq -er '.data[0].b64_json // empty' "$RESP" | base64 --decode > "$OUT"
[ -s "$OUT" ] || { echo "empty or malformed output: $OUT" >&2; head -c 300 "$RESP" >&2; exit 1; }
printf '%s\n' "$PROMPT" > "${OUT%.png}.prompt.txt"
printf '%s\n' "$REF_IMAGE" > "${OUT%.png}.ref.txt"
file "$OUT"
ls -lt "$BOOK_DIR/封面/"Step 4:质量检查 + 迭代
| 检查项 | 标准 |
|---|---|
| 文字渲染 | 书名清晰可辨,字体风格匹配题材 |
| 题材匹配 | 视觉风格与书名题材一致 |
| 构图合理 | 主体突出,文字不遮挡核心画面 |
| 平台适配 | 符合目标平台的封面风格调性 |
不满意时调整方向:更换构图、调整色调、换字体风格、换平台风格。
---
参考资料
| 文件 | 何时加载 |
|---|---|
| references/cover-styles.md | 题材→视觉风格映射、平台风格详情、提示词模板 |
---
语言
- 跟随用户的语言回复,用户用什么语言就用什么语言回复
- 中文回复遵循《中文文案排版指北》
小说封面视觉风格库
各题材网文封面视觉风格定义,用于构建 GPT-Image-2 英文提示词。
---
平台风格
番茄小说
视觉:高饱和高对比 / 人物占60%+面部清晰 / 书名大粗有光效(金/红/白) / 大头贴构图+华丽背景 关键词:vibrant saturated colors, eye-catching bold design, character portrait dominating frame, mass-market novel cover style, high contrast
起点
视觉:细腻精致偏写实插画 / 构图讲究层次丰富 / 书名偏传统毛笔楷体 / 色彩沉稳 / 人物场景均衡有电影感 关键词:polished refined illustration, detailed cinematic composition, epic atmospheric, mature sophisticated style, premium quality
晋江
视觉:柔和色调(粉/紫/浅蓝/暖白) / 唯美画风大眼精致五官 / 花瓣光斑丝绸珠宝装饰 / 居中对称画面干净 / 书名优雅行书细圆 关键词:dreamy ethereal aesthetic, soft pastel tones, elegant romantic, delicate beauty, flower petals and bokeh
知乎盐言
视觉:大量留白极简 / 冷淡色(灰/蓝/白/暗色) / 氛围感>人物细节,常用场景/物品/抽象意象 / 书名现代简约无衬线 / 独立电影海报质感 关键词:minimalist literary style, clean composition with negative space, subtle moody atmosphere, independent film poster aesthetic
七猫
视觉:极度饱和强烈冲击 / 人物华丽服饰装备丰富 / 火焰雷电灵力特效 / 书名大号发光占比大 / 海报感信息密度高 关键词:striking high-impact design, vivid dramatic colors, spectacular visual effects, attention-grabbing poster style
刺猬猫
视觉:日系插画二次元 / 色彩明亮线稿清晰 / Q版元素 / 书名卡通手绘风 / 轻松活泼 关键词:anime illustration style, vibrant colorful, detailed character art, Japanese light novel aesthetic
---
题材推断规则
| 关键词 | 题材 | 风格标签 |
|---|---|---|
| 仙/道/剑/灵/修/宗/天/帝/尊/神 | 玄幻/仙侠 | xianxia fantasy |
| 都市/总裁/校园/重生/系统/学霸/医生/兵王 | 都市 | urban modern |
| 妃/皇/侯/宫/嫡/庶/后/朝/凤/鸾 | 古言 | ancient romance |
| 总裁/契约/替嫁/甜宠/娇妻/萌宝/闪婚 | 现言 | modern romance |
| 诡/案/侦探/悬疑/推理/密室/连环 | 悬疑 | mystery thriller |
| 星际/末世/机甲/赛博/废土/进化 | 科幻 | sci-fi |
| 龙/骑/魔法/异世界/精灵/领主 | 西幻 | western fantasy |
| 三国/大明/大唐/战场/将军/谋士 | 历史 | historical epic |
| 鬼/僵尸/阴阳/风水/盗墓/咒 | 灵异 | supernatural horror |
| 萌/喵/团宠/娇/转生 | 轻小说 | light novel |
---
提示词构建公式
[平台风格] + [文字层:书名+作者名+字体设计] + [题材风格标签] + [人物描述]
+ [背景元素] + [色彩指令] + [光效指令] + [通用修饰]通用修饰:professional book cover design, high detail digital painting, portrait orientation 2:3 ratio, no watermark
文字层必须指定:书名内容+位置(top center)+字体风格+颜色;作者名内容+位置(bottom center)+字体风格+颜色
---
提示词技巧
文字渲染
GPT-Image-2可直接渲染中文。格式:
Title text '书名' at top center in {字体风格}
Author name '作者名' at bottom center in {字体风格}人物描述要具体
不要"a man",要:
a young man in flowing white silk robes with gold embroidery,
long black hair tied in a topknot with a jade crown,
piercing dark eyes, confident expression,
holding a glowing blue spirit sword背景三层
前景(人物/道具) → 中景(场景:山峰/建筑/森林) → 远景(氛围:云海/星空/火焰)
光效
| 光效 | 关键词 | 感觉 |
|---|---|---|
| 神圣 | dramatic golden light from above | 神圣感 |
| 神秘 | cold moonlight from the left casting long shadows | 神秘感 |
| 温暖 | warm sunset glow backlighting the figure | 温暖感 |
| 科幻 | neon blue and purple lights from below | 科幻感 |
避免真人照片感
加 digital painting style,网文封面需要插画感。
构图变体
| 类型 | 关键词 | 适用 |
|---|---|---|
| 人物特写 | close-up portrait, face filling upper half | 强调角色 |
| 全身像 | full body shot, dynamic pose | 展示服装动作 |
| 纯场景 | no human figure, landscape composition | 悬疑/科幻 |
| 双人 | two figures facing each other | 言情类 |
---
风格库
玄幻 / 仙侠
标签:xianxia Chinese fantasy art style, ethereal atmosphere 色彩:青蓝+金色+玄黑,冷色为主,金色/暖色光源点缀 人物:男-长发束冠/散发,持剑/法器,衣袂飘飞 | 女-仙裙飘逸,灵兽伴随,莲花装饰 背景:云海、仙山、古建筑楼阁、灵力光效 光效:divine golden light rays, mystical mist, spiritual energy glow 示例:
Chinese web novel cover, xianxia fantasy style.
Title text '剑道独尊' at top center in bold golden brush calligraphy with metallic glow and sharp strokes.
Author name '青椒炒肉' at bottom center in small refined white serif text with faint golden glow, flanked by delicate cloud-scroll ornaments, resting on a thin horizontal gold line.
A young swordsman in flowing white robes standing on a mountain peak,
holding a glowing blue spirit sword, long black hair flowing in the wind.
Ethereal clouds swirling below, dramatic golden divine light from above,
spiritual energy particles. Dark misty mountain peaks in background.
Color palette: deep blue, gold, white, black.
Professional book cover, high detail digital painting, portrait 2:3 ratio, no watermark都市
标签:modern urban contemporary style, clean cinematic composition 色彩:深蓝+灰色+金色,霓虹点缀(夜景)/暖橙(黄昏) 人物:男-西装/休闲装干练轮廓分明 | 女-时尚穿搭自信表情 背景:城市天际线、高端办公室、校园、霓虹街道 光效:sharp city lights, sunset glow reflecting on glass buildings, neon rim light
古言 / 宫斗
标签:ancient Chinese romance palace drama, elegant classical beauty 色彩:正红+金色+墨黑,华贵厚重 人物:女-华服盛装凤冠步摇精致妆容 | 男-帝王/将军威严或温润 背景:宫殿、庭院、红墙、珠帘、屏风、灯笼 光效:warm lantern light, golden candle glow, silk fabric shimmering
现言 / 甜宠
标签:modern romance cover art, soft dreamy warm atmosphere 色彩:粉色+暖白+浅金,温暖柔和 人物:双人构图为主,甜蜜互动(拥抱/对视/牵手) 背景:咖啡厅、花园、温馨室内、夕阳海滩 光效:soft warm backlighting, dreamy bokeh, gentle sunset glow
悬疑 / 推理
标签:dark mystery thriller, noir atmosphere, high contrast shadows 色彩:黑色+深灰+暗蓝,血红/冷白点缀 人物:剪影/半遮面/背影,冷静或紧张 背景:雨夜街道、老旧建筑、密室、暗巷 光效:dramatic chiaroscuro, single spotlight, rain-slicked reflections
科幻 / 末世
标签:sci-fi cyberpunk, futuristic technology, post-apocalyptic 色彩:深蓝+黑+银色,霓虹蓝/电子紫/能量绿点缀 人物:机甲装/战术服/实验室服,科幻武器/全息界面 背景:太空、废墟城市、实验室、空间站 光效:holographic blue glow, neon rim lighting, energy arcs
西幻
标签:western high fantasy, epic medieval atmosphere 色彩:深蓝+暗金+银白,火焰红/魔法紫点缀 人物:骑士铠甲/法师长袍/游侠皮甲,伴随龙/狮鹫 背景:城堡、龙巢、魔法阵、广阔原野 光效:magic spell glow, dramatic stormy sky, firelight from torches
历史 / 军事
标签:historical Chinese war epic, grand battlefield panorama 色彩:铁灰+暗红+土黄,金甲光泽/烽火橙点缀 人物:将军铠甲/谋士长袍,持兵器 背景:战场、城墙、军营、烽火 光效:dramatic battlefield firelight, smoke-filled sky, sunset over war
灵异 / 恐怖
标签:Chinese supernatural horror, eerie ghostly atmosphere 色彩:墨黑+幽绿+暗红,纸白/烛光黄点缀 人物:道士装扮/普通人陷入诡异,鬼影/纸人/僵尸 背景:墓地、古庙、暗巷、棺材 光效:eerie green glow, flickering candlelight, cold ghostly luminescence
轻小说 / 二次元
标签:anime light novel cover, vibrant colorful moe style 色彩:明亮多色,星光/花瓣点缀 人物:Q版/萌系角色,猫耳/翅膀等萌属性 背景:奇幻世界、校园、异世界、星空 光效:sparkly star effects, magical particle effects, soft luminous glow
Related skills
FAQ
What API does story-cover use?
GPT-Image-2 via OpenAI-compatible images/generations or images/edits endpoints with base64 PNG responses.
Which environment variables are required?
GPT_IMAGE_API_KEY and BOOK_DIR; GPT_IMAGE_BASE_URL, model, size, and REF_IMAGE are optional.
How is genre selected?
Title keywords are matched against cover-styles rules with priority ordering; zero hits default to urban fiction style.
Is Story Cover safe to install?
skills.sh reports 1 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.