← Search

Chinese web-novel cover generator (GPT-Image-2)
Design 🧪 Install ran in our test sandbox · Nov 18, 2026 📌 Pinned version: commit 7408014
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: Codex CLI with its built-in image tool (counts…

Chinese web-novel cover generator (GPT-Image-2)

Generate professional Chinese web-novel covers from title and pen name, with genre-aware fonts and platform sizing — written in Chinese

At a glance
What
Generate professional Chinese web-novel covers from title and pen name, with genre-aware fonts and platform sizing — written in Chinese
Cost
Free
Needs
Codex CLI with its built-in image tool (counts toward Codex usage, no key needed) OR a paid GPT_IMAGE_API_KEY (OpenAI or compatible proxy) for the API fallback; curl, jq and base64 for the API path; ImageMagick or sips optional for platform export sizing
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

Quick answer

Chinese Web-Novel Cover Generator is a free Muse skill that generates professional Chinese web-novel covers from title and pen name, with genre-aware fonts and platform sizing, written in Chinese. From a title and pen name, it detects the genre and builds a three-layer English image prompt, with a text layer using genre-specific font styling. Note: use requires a paid API.

⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 7408014

Step 0, before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: Codex CLI with its built-in image tool (counts toward Codex usage, no key needed) OR a paid GPT_IMAGE_API_KEY (OpenAI or compatible proxy) for the API fallback; curl, jq and base64 for the API path; ImageMagick or sips optional for platform export sizing Install "Chinese web-novel cover generator (GPT-Image-2)" for me. It generates professional Chinese web-novel covers from a book title and pen name: it first looks for the current book in the project and reads the details already on file, detects the genre, builds three-layer English image prompts (title font, author byline design, platform style, scene composition) from its style library, shows 2 to 3 composition proposals and generates only the chosen one (or all of them if asked), via the Codex built-in image tool or the GPT-Image-2 API fallback, with versioned PNG outputs, platform export sizes, and a quality-check loop, by @zenstory-ai, MIT-licensed. Repository: https://raw.githubusercontent.com/zenstory-ai/oh-story-claudecode/74080143dd1ac9a39a930fafd99a0dbbe61b946a/skills/story-cover/SKILL.md (the skill is the whole skills/story-cover/ folder at that commit: SKILL.md plus its references/ subfolder, with references/cover-styles.md and references/api-fallback.md) Pinned version: install the code at commit 74080143dd1ac9a39a930fafd99a0dbbe61b946a exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Updated October 18, 2026: Skill Harbor regenerated this install prompt from the current upstream file. SKILL.md was massively rewritten, from 327 lines down to 148 lines. SKILL.md no longer carries the per-genre font tables, the composition variants table or the detailed API scripts inline: the new file points to references/cover-styles.md for the fonts, platform style and compositions, and to a new file, references/api-fallback.md, for the API environment variables and commands, to be read only when the API path is used, so the whole folder must be installed, not SKILL.md alone. The workflow also changed: the skill now looks for the current book in the project first and reads the title, genre, target platform and other details already on file, asking only for what is missing (the pen name is still asked every time), and it now presents 2 to 3 composition proposals with the genre it settled on and generates only the one the author picks, unless the author asks for all of them. Correction: the previous prompt's safety check spoke of allowed hosts declared in SKILL.md; the new file declares no allowed hosts list, and the only default API base URL named in the files is https://api.openai.com/v1, in references/api-fallback.md. 1. Fetch the whole skills/story-cover/ folder at the pinned commit, SKILL.md and every file under references/, into a temporary folder, then compare SKILL.md with the fingerprint from Skill Harbor's review of 2026-10-18: - SKILL.md: SHA-256 78bb12754981af4fae554c3bd615da56dddd3bf3a729362705a2538b4d0b6774 If it does not match, it changed since the review: do not install it yet, tell me what you found and let me decide. 2. Safety check: read SKILL.md and its reference files and review them for anything suspicious (unexpected network calls, shell commands, credential harvesting); STOP on any red flag and tell me. Tell me in plain words what the skill does when used, which services it connects to, whether it reads or sends any personal information or keys, and anything that seems unusual. Confirm these points from the files: - The Codex built-in image tool is tried first and needs no API key; the API fallback is used only when the session has no built-in tool or I explicitly ask for the API, and it then needs GPT_IMAGE_API_KEY. If a built-in call fails, report the error first and do not silently switch to the possibly paid API. - It first looks for the current book, via .active-book or a book folder found in the project, and reads the title, genre type, target platform and other basic information already recorded there (long-form or short-form layout); it asks only for missing items, and it always asks for the pen name, because the pen name is not in those files. The title and the pen name are required: never invent them or leave them blank. - Save location and ratio: with a book folder, covers go into its 封面 subfolder without asking; without one, under ./covers/{book title}/封面/. The Fanqie platform upload is 600x800, a 3:4 ratio; other platforms are delivered in vertical 2:3 by default, or at the upload pixels the author gives. - Genre and prompt building rely on references/cover-styles.md: the genre is picked from the style library using the recorded genre or synopsis where available, with title inference only as a fallback; an inferred genre is shown with the proposals and the author can change it; the fonts, platform style, characters, background, colours and lighting all come from the same style library section. - It presents 2 to 3 composition proposals, each described in one sentence together with the genre it settled on, and generates only the chosen one; if the author says to generate all of them, each proposal is generated separately. The prompt template keeps the title and the author name inside the central safe area (inner about 85%), with no watermark. - The API environment variables and commands live in references/api-fallback.md, read only when the API path is used. Nothing is sent anywhere during installation itself. 3. When I say yes, install it as a skill: copy SKILL.md and its reference files into the agent's skills directory, in a folder named "story-cover", keeping the references/ subfolder as it is. 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. decide between the Codex built-in path and the paid API key; save GPT_IMAGE_API_KEY in the vault if using the API fallback; the skill is written in Chinese, so work in Chinese when invoking it). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this skill does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit 7408014 · 2026-10-18
🧪 Install ran in our test sandbox · Nov 18, 2026
👁 Observed during the install test · Nov 18, 2026 : registry.npmjs.org
🔎 Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
7408014 · 2026-10-18
Sandbox install test
Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : No commands, network calls, packages, file writes or API keys detected.

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.