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 arturseo-geo/claude-code-skills --skill ebook-publishinggit clone --depth 1 https://github.com/arturseo-geo/claude-code-skillsWrote 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/arturseo-geo/claude-code-skills/ebook-publishing)<a href="https://agentmods.dev/skills/arturseo-geo/claude-code-skills/ebook-publishing"><img src="https://agentmods.dev/badge/skills/arturseo-geo/claude-code-skills/ebook-publishing/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/arturseo-geo/claude-code-skills/ebook-publishing"><img src="https://agentmods.dev/badge/skills/arturseo-geo/claude-code-skills/ebook-publishing.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 | $0.00215 | $0.02753 |
| Opus 5.5 | $0.00086 | $0.01101 |
| Sonnet 5.5 | $0.00043 | $0.00551 |
| Haiku 4.5 | $0.00021 | $0.00275 |
Grade A, and why
ebook-publishing 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 2mo 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.
This is a copy
100% identical to ebook-publishing — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultimate Ebook Publishing Skill
Covers the complete lifecycle: write → format → convert → publish → distribute → launch. Includes ebooks, print-on-demand, and AI-narrated audiobooks.
Reference Files — Load When Relevant
| Topic | File | Load when... |
|---|---|---|
| All platforms + royalties | references/platforms.md |
Choosing where to publish, royalty questions |
| Cover design specs | references/cover-specs.md |
Designing or sizing covers for any platform |
| Formatting + conversion | references/formatting.md |
EPUB, PDF, HTML→PDF, Pandoc, Puppeteer |
| Audiobooks | references/audiobooks.md |
ACX, ElevenLabs, KDP Virtual Voice, INaudio |
| ISBN strategy | references/isbn-strategy.md |
Buying ISBNs, KDP trap, dual KDP+IS strategy |
| Promotion + launch | references/promotion.md |
BookBub, permafree, series, ARC, launch plan |
Project Context
If project-context.md exists in the skill directory or .claude/ folder, read it
before any task. It contains brand voice, publishing setup, platform credentials
paths, and infrastructure details — avoids re-explaining context each session.
Workflow Overview
1. Write & Structure
2. Format (EPUB / PDF / HTML→PDF)
3. Cover Design
4. ISBN Decision
5. Platform Strategy (wide vs exclusive, ebook + print + audio)
6. Metadata & SEO
7. Pricing & Royalties
8. Pre-launch + Launch + Post-launch
EPUBCheck Compliance (EPUB 3.0)
EPUBs must pass EPUBCheck for D2D, Apple Books, Kobo, and most aggregators. Common errors and fixes:
| Error | Fix |
|---|---|
<script> tags |
Remove all — EPUB content docs don't allow JavaScript |
<button> tags |
Remove all |
<input>, <select>, <textarea>, <form> |
Remove all form elements |
Event handlers (onclick, onmouseover, etc.) |
Remove all on* attributes |
Orphan <dt>/<dd> outside <dl> |
Convert to styled <p> tags (see below) |
| CSS unbalanced braces | Remove @media blocks (limited EPUB reader support), validate brace count |
Broken fragment identifiers (href="#id" where id missing) |
Convert <a> to <span>, remove href |
| OPF-014 "scripted" property | Caused by script tags — removing scripts fixes it |
What ships with it
16 files 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.
- .github/ISSUE_TEMPLATE/bug-report.md 517 B
- .github/ISSUE_TEMPLATE/new-platform.md 846 B
- .github/ISSUE_TEMPLATE/platform-update.md 963 B
- .github/pull_request_template.md 908 B
- .gitignore 62 B
- CONTRIBUTING.md 3.2 KB
- LICENSE 1.0 KB
- project-context.md 1.7 KB
- README.md 8.3 KB
- references/audiobooks.md 6.4 KB
- references/cover-specs.md 4.2 KB
- references/formatting.md 9.6 KB
- references/isbn-strategy.md 5.4 KB
- references/platforms.md 9.3 KB
- references/promotion.md 7.4 KB
- SECURITY.md 929 B
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.
- 2mo ago First seen · 270 lines · 215 tokens per session scan A 8bdfebbcef70
ebook-publishing is a skill published in the GitHub repository arturseo-geo/claude-code-skills (13 stars, last pushed 7mo ago), licensed MIT. It adds 215 tokens to every session and 2,753 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to ebook-publishing, differing in 0 lines, and is treated as a copy.
ebook-publishing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ebook-publishingarturseo-geo/claude-code-skills | Skill | 13 | 7mo ago | MIT | A | 215 | Claude Code, Codex |
| ecommerce-patternssoftspark/ai-toolkit | Skill | 179 | 10d ago | Apache-2.0 | A | 52 | Claude Code |
| gemini-image-generatoroyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 21 | Claude Code |
| hauslagerist-readerellmos-ai/skills | Skill | 9 | 4d ago | MIT | A | 27 | Claude Code, Codex |
| pool-managerkhalilbenaz/claude-skills-collection | Skill | 27 | 2mo ago | MIT | A | 94 | Claude Code, Codex |
| shopifythatrebeccarae/claude-marketing | Skill | 192 | 5mo ago | MIT | A | 53 | Claude Code, Codex |
| tiktok-adsthatrebeccarae/claude-marketing | Skill | 192 | 5mo ago | MIT | A | 65 | Claude Code, Codex |