Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

story-cover：小说封面生成 · worldwonderer | DecimalAI

design mediaby worldwonderer

story-cover：小说封面生成

worldwonderer/story-cover

Source worldwonderer/oh-story-claudecode ↗License MIT

小说封面生成。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。触发方式：/story-cover、/封面、「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」。

SkillScore77Maintained

Automatic

Design & UX Review pack

Last verified 8/17/2026

What it changes

Passed 15 of 19 test cases with the skill, and 11 of 19 without it.

Without skill59%

With skill77%

Checks it passed that the model alone missed

Selects Xianxia over Urban and Romance based on genre priority hierarchy
Saves accompanying prompt documentation file matching the new image version name
Omits the response_format parameter from the JSON request payload for gpt-image-2

and 1 more in the full report

4 fixed13 passed either way5 still failing0 broke

Pass-rate lift: +18 pp
Tokens: +212%
Agent turns: 0%
Response time: -39%

Model Measured 8/17/2026v2 · latest is v317 of 22 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.8-flash on 10/18/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/worldwonderer-story-cover/SKILL.md https://app.decimal.ai/s/worldwonderer-story-cover/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add worldwonderer-story-cover, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/worldwonderer-story-cover/ and pins it in .decimal/skills.lock

decimalai skills add worldwonderer-story-cover

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/worldwonderer-story-cover/SKILL.md https://app.decimal.ai/s/worldwonderer-story-cover/SKILL.md

Raw file: /s/worldwonderer-story-cover/SKILL.md ↗ · machine-readable summary at /s/worldwonderer-story-cover.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

I'm launching an urban novel titled '暗黑骑士' on standard web platforms. I haven't picked my pen name yet—just invent a cool placeholder author name like 'ShadowWriter' or omit it so we can run cover generation right away into `./covers/暗黑骑士`.

What was checked, without and with the skill
Checked	Without skill	With skill
Prompts the user to supply the missing author name before generating the cover image rather than fabricating a placeholder name	Missed	Passed

case-04 · gemini-3.6-flash · 8/17/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md321 lines2 files

story-cover：小说封面生成

根据书名和题材生成包含书名、笔名的完整封面，让读者一眼看出题材和氛围。

生成通路

Codex 内置（优先）：当前 Codex CLI 会话可调用 $imagegen / image_gen 时，直接调用工具生成并保存，无需 OPENAI_API_KEY 或 GPT_IMAGE_API_KEY，不运行 curl。
API 回退：仅在会话没有内置工具或用户明确指定 API 时使用，需要 GPT_IMAGE_API_KEY。工具缺失不等于 Codex 订阅不支持生图；内置调用失败时先报告错误，不静默切换到可能收费的 API。

输出参数与 API 回退环境变量

变量	必填	默认	说明
`GPT_IMAGE_API_KEY`	API 回退必填	—	OpenAI 或兼容代理的 API Key；Codex 内置通路不用
`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`	API 回退的请求尺寸：番茄 3:4→`768x1024`，默认 2:3→`1024x1536`。实际尺寸以出图结果为准，固定上传像素由「导出平台上传尺寸」步骤保证
`UPLOAD_SIZE`		—	平台固定上传像素（番茄 `600x800`）；设置后由「导出平台上传尺寸」步骤居中裁剪+缩放出上传版（不变形、不依赖出图尺寸）
`BOOK_DIR`	✅	—	输出目录，建议 `./covers/<书名>`
`REF_IMAGE`		—	参考图本地路径或 URL；内置通路先把图片载入会话，API 回退走 `images/edits` 图生图

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。目录建议为 ./covers/<书名>；API 回退通过环境变量传入，内置通路直接使用本次确定的目录。问作者时说「封面存在哪？默认 ./covers/<书名>」。选填：参考图 REF_IMAGE（本地路径或 URL）、风格偏好、尺寸；参考图的用法见 Step 4 对应通路。

书名和笔名是封面必需信息：缺任一时，先用宿主可用的提问方式请作者补全，不得编造或留空。

按目标平台定封面尺寸：番茄上传 600×800，比例为 3:4；出图比例不符时，平台再次裁剪可能切掉书名或笔名。

平台	上传尺寸	比例	生成 `GPT_IMAGE_SIZE`（尽量）
番茄小说	600×800	3:4	`768x1024`
其他平台（默认竖版）	按平台规格	2:3	`1024x1536`

Track record

Benchmark

15 / 19

test cases passed, vs 11 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v6 — 10/16/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

worldwonderer / oh-story-claudecode

skills/story-cover/SKILL.md

View on GitHub ↗

License MITImported 10/16/2026Version v3Bundled 1 file

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

story-cover：小说封面生成

生成通路

输出参数与 API 回退环境变量

生成流程

Step 1：收集信息

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills