#488 by GitHub stars

deusyu/translate-book

Translate books (PDF/DOCX/EPUB) into any language using parallel sub-agents. Converts input -> Markdown chunks -> translated chunks -> HTML/DOCX/EPUB/PDF.

Claude Code Codex Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +65 / −2 lines

Before Network or broad shell → After Network or broad shell

a663b1b4f1e6 → 8a2d71cba25c

+ 55 
+ 56 Page-number lines are detected and dropped for PDF input only; EPUB and DOCX
+ 57 keep every standalone number (chapter, verse or exercise numbers). If an EPUB
+ 58 prints its page numbers as text and they show up in the chunks, delete the
+ 59 temp directory before translating and re-run with `--detect-page-numbers`.
+ 247    - 脚注：正文中的引用标记 `[^12]` 与行首的定义标记 `[^12]:` 原样保留，不要改编号、不要删除、不要移动位置，只翻译定义后面的注释文字；定义的续段保持行首四个空格的缩进
- 405 python3 {baseDir}/scripts/merge_and_build.py --temp-dir "<temp_dir>" --title "<translated_title>" --cleanup
+ 411 python3 {baseDir}/scripts/merge_and_build.py --temp-dir "<temp_dir>" --title "<translated_title>"
- 411 The `--cleanup` flag removes intermediate files (chunks, input.html, etc.) after a fully successful build. If the user asked to keep intermediates, omit `--cleanup`.
+ 417 Keep the intermediate files. The chunks, `manifest.json`, and `run_state.json`
+ 418 are what make spot fixes and selective re-translation possible after the build
+ 419 (see Step 9). Add `--cleanup` only when the user explicitly asks to delete
+ 420 intermediates, and tell them first that it permanently deletes `chunk*.md`,
+ 421 `output_chunk*.md`, `input.html`, and `input.md`: after that, fixing a single
+ 422 chunk means converting and translating the whole book again.
+ 440 
+ 441 ### 9. Spot Fixes After the Build
+ 442 
+ 443 If the user finds problems in a few places after the build, fix the affected
+ 444 chunks rather than `output.md`: whenever a chunk changes, the build re-merges
+ 445 `output.md` from the chunks and discards edits made there.
+ 446 
+ 447 1. Find the chunk: search `<temp_dir>/output_chunk*.md` for the passage.
+ 448 2. Either edit `output_chunk<NNNN>.md` directly, or have it re-translated.
+ 449 
+ 450    **Edit.** `record` stamps the chunk as matching the current source and
+ 451    glossary, so first check what the planner still expects from it:
+ 452 
+ 453    ```bash
+ 454    python3 {baseDir}/scripts/run_state.py plan "<temp_dir>"
+ 455    ```
+ 456 
+ 457    If chunk<NNNN> appears in `chunks[]` with action `translate`, recording
+ 458    would hide that. Handle it by reason:
+ 459 
+ 460    - `glossary_term_hash_changed` (its `detail` lists the term ids) or
+ 461      `glossary_term_selection_changed`: bring those terms in line with
+ 462      `glossary.py print-terms-for-chunk "<temp_dir>" "chunk<NNNN>.md"` in the
+ 463      same edit.
+ 464    - `manifest_source_hash_changed`: the source chunk was edited after
+ 465      splitting. Re-run the Step 2 `convert.py` command first, leaving out
+ 466      page-number flags such as `--strip-page-numbers`: once chunks exist,
+ 467      those flags abort and suggest deleting the cached files or the whole
+ 468      temp dir, which would also delete the translations. Without them it
+ 469      keeps the existing chunks and writes their new hashes to
+ 470      `manifest.json`. Skip this and the merge stops with "Source changed
+ 471      since splitting" even after re-translating. Plan again: the chunk is
+ 472      then queued with `source_hash_changed_since_record`.
+ 473    - `source_hash_changed_since_record` or any other reason: re-translate the
+ 474      chunk instead of editing it.
+ 475 
+ 476    Then record the edited output:
+ 477 
+ 478    ```bash
+ 479    python3 {baseDir}/scripts/run_state.py record "<temp_dir>" chunk<NNNN>
+ 480    ```
+ 481 
+ 482    **Re-translate.** Delete `output_chunk<NNNN>.md` and run Steps 3.7–4.5 again. The planner
+ 483    re-checks the whole book, so `translation_chunk_ids` can also list chunks
+ 484    the user did not mention, typically ones whose glossary terms changed after
+ 485    they were translated (`glossary_term_selection_changed` or
+ 486    `glossary_term_hash_changed` in the plan's `chunks[].reasons`). Translate
+ 487    only the chunks the user asked for; if the plan lists others, show the user
+ 488    those chunk ids with their reasons and ask before re-translating them.
+ 489 3. Re-run the Step 7 build command with the same flags. It re-merges because
+ 490    the chunk is newer than `output.md`, then regenerates the HTML and the other
+ 491    formats.

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → a663b1b4f1e6

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 8a2d71cba25c514bfa6b6d6191b1fe21c0fe3229

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/deusyu/translate-book.git .hotskills/deusyu-translate-book && git -C .hotskills/deusyu-translate-book checkout --detach 8a2d71cba25c514bfa6b6d6191b1fe21c0fe3229
# Copy each selected skill directory from .hotskills/deusyu-translate-book into .claude/skills/<skill-name>/

Version-pinned installation · Codex

git clone --filter=blob:none --no-checkout https://github.com/deusyu/translate-book.git .hotskills/deusyu-translate-book && git -C .hotskills/deusyu-translate-book checkout --detach 8a2d71cba25c514bfa6b6d6191b1fe21c0fe3229
# Copy each selected skill directory from .hotskills/deusyu-translate-book into .agents/skills/<skill-name>/

2.4kGitHub stars

182stars in 7 days

1skill in this repository

7commits in 30 days

Heat

8.2

Star growth, last 7 daysAhead of 98% of tracked repositories
Star growth, last 24 hoursAhead of 98% of tracked repositories
Rank movement, last 7 daysAhead of 93% of tracked repositories
Commits, last 30 daysAhead of 73% of tracked repositories
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

translate-book /

How it works

translate-book

When your agent uses it

Translate books (PDF/DOCX/EPUB) into any language using parallel sub-agents. Converts input -> Markdown chunks -> translated chunks -> HTML/DOCX/EPUB/PDF.

What it loads into context

Frontmatter

114 tokens

Always available to the agent

SKILL.md

6,785 tokens

When the skill is activated

Reference documents

21,139 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Workflow

Scripts executed separately

scripts/calibre_html_publish.py
scripts/chunk_context.py
scripts/convert.py
scripts/glossary.py
scripts/manifest.py
scripts/merge_and_build.py
scripts/merge_meta.py
scripts/meta.py
scripts/run_state.py
tests/test_calibre_html_publish.py
tests/test_chunk_context.py
tests/test_convert.py
tests/test_glossary.py
tests/test_manifest.py
tests/test_merge_and_build.py
tests/test_merge_meta.py
tests/test_meta.py
tests/test_run_state.py

Files

.claude/commands/release.mddoc1,315 bytes
.clawhubignoreasset118 bytes
.github/FUNDING.ymlasset68 bytes
.github/workflows/ci.ymlasset581 bytes
.gitignoreasset455 bytes
AGENTS.mddoc5,131 bytes
CLAUDE.mddoc3,861 bytes
LICENSEasset1,064 bytes
README.mddoc25,577 bytes
README.zh-CN.mddoc24,925 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
SKILL.mdcore27,461 bytes
assets/poster/pages/poster-en.pageasset21,213 bytes
assets/poster/pages/poster.pageasset21,389 bytes
assets/poster/style.mddoc4,166 bytes
assets/poster/translate-book-poster-en.jpgasset227,579 bytes
assets/poster/translate-book-poster-en.pptdasset1,237 bytes
assets/poster/translate-book-poster.jpgasset234,120 bytes
assets/poster/translate-book-poster.pptdasset1,229 bytes
scripts/calibre_html_publish.pyruns13,336 bytes
scripts/chunk_context.pyruns3,897 bytes
scripts/convert.pyruns60,151 bytes
scripts/glossary.pyruns22,286 bytes
scripts/manifest.pyruns5,943 bytes
scripts/merge_and_build.pyruns45,226 bytes
scripts/merge_meta.pyruns43,840 bytes
scripts/meta.pyruns9,720 bytes
scripts/run_state.pyruns12,734 bytes
scripts/template.htmlasset13,263 bytes
scripts/template_ebook.htmlasset7,158 bytes
tests/.artifacts/.gitkeepasset1 bytes
tests/.artifacts/README.mddoc289 bytes
tests/baselines/README.mddoc3,905 bytes
tests/baselines/diligent-dick/SOURCE.mddoc4,329 bytes
tests/baselines/diligent-dick/diligent-dick.epubasset352,310 bytes
tests/baselines/sleepy-hollow/SOURCE.mddoc2,806 bytes
tests/baselines/sleepy-hollow/sleepy-hollow.epubasset287,033 bytes
tests/baselines/standard-alice/SOURCE.mddoc5,083 bytes
tests/baselines/standard-alice/standard-alice.epubasset10,635,439 bytes
tests/test_calibre_html_publish.pyruns3,705 bytes
tests/test_chunk_context.pyruns3,110 bytes
tests/test_convert.pyruns52,078 bytes
tests/test_glossary.pyruns31,506 bytes
tests/test_manifest.pyruns4,018 bytes
tests/test_merge_and_build.pyruns29,686 bytes
tests/test_merge_meta.pyruns93,250 bytes
tests/test_meta.pyruns6,242 bytes
tests/test_run_state.pyruns8,159 bytes

Read SKILL.md


# Book Translation Skill

You are a book translation assistant. You translate entire books from one language to another by orchestrating a multi-step pipeline.

## Workflow

### 1. Collect Parameters

Determine the following from the user's message:
- **file_path**: Path to the input file (PDF, DOCX, EPUB, or Markdown) — REQUIRED
- **target_lang**: Target language code (default: `zh`) — e.g. zh, en, ja, ko, fr, de, es
- **concurrency**: Number of parallel sub-agents per batch (default: `8`)
- **temp_root**: Optional directory under which `{filename}_temp/` should be created
- **epub_cover**: Optional explicit cover image path for EPUB output

View the complete source on GitHub

Skills included

translate-book

Repository facts

License: MIT
Created: Mar 15, 2026
Last pushed: Oct 29, 2026
Forks: 271
Open issues: 1
Project activity: Active

Rank over the last 12 weeks

Now #488 · best #420 · down 40 in 30 days

#503 on Nov 1
#504 on Nov 2
#503 on Nov 3
#491 on Nov 4
#489 from Nov 5 to Nov 6
#488 since Nov 7

79 earlier periods

#534 on Aug 2
#528 on Aug 7
#524 on Aug 8
#511 on Aug 9
#525 on Aug 10
#528 on Aug 11
#524 from Aug 12 to Aug 14
#508 on Aug 15
#515 on Aug 16
#517 on Aug 17
#533 on Aug 18
#525 on Aug 19
#524 on Aug 20
#529 on Aug 21
#512 on Aug 22
#530 on Aug 23
#531 on Aug 24
#541 on Aug 25
#528 on Aug 26
#540 on Aug 27
#539 on Aug 28
#521 on Aug 29
#511 on Aug 30
#538 on Aug 31
#544 on Sep 1
#536 on Sep 2
#519 on Sep 3
#472 on Sep 4
#468 on Sep 5
#466 on Sep 6
#454 on Sep 7
#456 on Sep 8
#447 on Sep 9
#444 on Sep 10
#442 on Sep 11
#439 on Sep 12
#438 on Sep 13
#448 on Sep 14
#445 on Sep 15
#452 on Sep 16
#442 on Sep 17
#449 on Sep 18
#433 on Sep 19
#441 on Sep 20
#443 on Sep 21
#447 on Sep 22
#441 on Sep 23
#432 on Sep 24
#431 on Sep 25
#428 on Sep 26
#439 on Sep 27
#444 on Sep 28
#450 on Sep 29
#446 on Sep 30
#440 on Oct 1
#439 on Oct 2
#427 on Oct 3
#420 on Oct 4
#431 on Oct 5
#437 on Oct 6
#443 on Oct 7
#448 on Oct 8
#451 on Oct 9
#444 from Oct 10 to Oct 11
#456 on Oct 12
#451 on Oct 13
#454 on Oct 14
#455 on Oct 15
#450 on Oct 17
#460 on Oct 18
#472 from Oct 19 to Oct 20
#479 on Oct 21
#472 on Oct 22
#471 on Oct 23
#458 on Oct 24
#495 on Oct 25
#500 on Oct 28
#501 on Oct 29
#502 from Oct 30 to Oct 31

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 4, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 30 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

1 broad permissionin 1 file: SKILL.md:1
No dangerous shell commands
67 network referencesin 6 files: tests/test_convert.py:562 README.md:11 README.zh-CN.md:11 and 3 more
3 obfuscation signalsin 1 file: scripts/convert.py:929
No instruction overrides
18 executable scriptsin 18 files: scripts/calibre_html_publish.py:1 scripts/chunk_context.py:1 scripts/convert.py:1 and 15 more
No access to secrets
No requests to vote in Hot

Show all 89 signals by file

`.github/FUNDING.yml`

Network accessline 1

# .github/FUNDING.yml github: deusyu custom: ["https://deusyu.app"]

Network accessline 3
```
custom: ["https://deusyu.app"]
```

`README.md`

Network accessline 11

> Inspired by [claude_translater](https://github.com/wizlijun/claude_translater). The original project uses shell scripts as its entry point, coordinating the Claude CLI with multiple step scripts to perform chunked translation. This projec

Network accessline 53

- **Agent runtime** — Codex, Claude Code, or OpenClaw, installed and ready to run skills - **Calibre** — `ebook-convert` command must be available ([download](https://calibre-ebook.com/))

Network accessline 54

- **Calibre** — `ebook-convert` command must be available ([download](https://calibre-ebook.com/))

Network accessline 55

- **Pandoc** — for HTML↔Markdown conversion ([download](https://pandoc.org/))

Network accessline 74

mkdir -p ~/.agents/skills git clone https://github.com/deusyu/translate-book.git ~/.agents/skills/translate-book

Network accessline 75

git clone https://github.com/deusyu/translate-book.git ~/.agents/skills/translate-book

Network accessline 89

mkdir -p ~/.claude/skills git clone https://github.com/deusyu/translate-book.git ~/.claude/skills/translate-book

Network accessline 90

git clone https://github.com/deusyu/translate-book.git ~/.claude/skills/translate-book

Network accessline 170

For bugs and feature requests, please open a [GitHub issue](https://github.com/deusyu/translate-book/issues) as described above. For questions, ideas, or anything else, you can reach me here:

Network accessline 172

| Channel | Link | |---------|------| | X (Twitter) | [@0xdeusyu](https://x.com/0xdeusyu) |

Network accessline 173

|---------|------| | X (Twitter) | [@0xdeusyu](https://x.com/0xdeusyu) | | Telegram | [@DeusThink](https://t.me/DeusThink) |

Network accessline 174

| X (Twitter) | [@0xdeusyu](https://x.com/0xdeusyu) |

Network accessline 175

| Telegram | [@DeusThink](https://t.me/DeusThink) |

Network accessline 176

| Telegram Group (Chinese) | [@talkdeusyu](https://t.me/talkdeusyu) |

Network accessline 177

| Telegram Channel (Chinese) | [@lovedesuyu](https://t.me/lovedesuyu) |

Network accessline 318

Tracking [issue #7](https://github.com/deusyu/translate-book/issues/7) — name/term inconsistency and pronoun/gender errors across chunks. The pipeline now covers high-frequency entities, alias/spelling drift, adjacent-chunk pronoun context,

Network accessline 358

[![Star History Chart](https://api.star-history.com/svg?repos=deusyu/translate-book&type=Date)](https://star-history.com/#deusyu/translate-book&Date)

Network accessline 364

[![Sponsor](https://img.shields.io/github/sponsors/deusyu?label=Sponsor&logo=github)](https://github.com/sponsors/deusyu)

`README.zh-CN.md`

Network accessline 11

> 本项目受 [claude_translater](https://github.com/wizlijun/claude_translater) 启发。原项目以 shell 脚本为入口，配合 Claude CLI 和多个步骤脚本完成分块翻译；本项目则将流程重构为可在 Codex、Claude Code 和 OpenClaw 中使用的 Agent Skill，使用 subagent 按 chunk 并行翻译，并引入 manifest 驱动的完整性校验，将续跑和多格式输出整合为

Network accessline 53

- **Agent 运行环境** — Codex、Claude Code 或 OpenClaw，已安装并可运行 Skill - **Calibre** — `ebook-convert` 命令可用（[下载](https://calibre-ebook.com/)）

Network accessline 54

- **Calibre** — `ebook-convert` 命令可用（[下载](https://calibre-ebook.com/)）

Network accessline 55

- **Pandoc** — 用于 HTML↔Markdown 转换（[下载](https://pandoc.org/)）

Network accessline 74

mkdir -p ~/.agents/skills git clone https://github.com/deusyu/translate-book.git ~/.agents/skills/translate-book

Network accessline 75

git clone https://github.com/deusyu/translate-book.git ~/.agents/skills/translate-book

Network accessline 89

mkdir -p ~/.claude/skills git clone https://github.com/deusyu/translate-book.git ~/.claude/skills/translate-book

Network accessline 90

git clone https://github.com/deusyu/translate-book.git ~/.claude/skills/translate-book

Network accessline 170

Bug 和功能需求请按上一节的要求提 [GitHub issue](https://github.com/deusyu/translate-book/issues)。使用上的疑问、想法或其他事情，可以通过下面这些方式找到我：

Network accessline 172

| 渠道 | 链接 | |------|------| | X (Twitter) | [@0xdeusyu](https://x.com/0xdeusyu) |

Network accessline 173

|------|------| | X (Twitter) | [@0xdeusyu](https://x.com/0xdeusyu) | | Telegram | [@DeusThink](https://t.me/DeusThink) |

Network accessline 174

| X (Twitter) | [@0xdeusyu](https://x.com/0xdeusyu) |

Network accessline 175

| Telegram | [@DeusThink](https://t.me/DeusThink) |

Network accessline 176

| Telegram 交流群 | [@talkdeusyu](https://t.me/talkdeusyu) |

Network accessline 177

| Telegram 频道 | [@lovedesuyu](https://t.me/lovedesuyu) |

Network accessline 318

跟踪 [issue #7](https://github.com/deusyu/translate-book/issues/7) — chunk 之间的人名/术语不一致以及代词/性别错误。当前流水线已覆盖高频实体、别名/拼写漂移、相邻 chunk 的代词上下文，以及术语表变更后的精确重译。整书自然度校验仍是后续质量阶段。整体方案分为四个可独立交付的阶段。

Network accessline 358

[![Star History Chart](https://api.star-history.com/svg?repos=deusyu/translate-book&type=Date)](https://star-history.com/#deusyu/translate-book&Date)

Network accessline 364

[![Sponsor](https://img.shields.io/github/sponsors/deusyu?label=Sponsor&logo=github)](https://github.com/sponsors/deusyu)

`SKILL.md`

Broad permissionsline 1

Read, Write, Edit, Bash, Glob, Grep, Agent, AskUserQuestion

Network accessline 3

description: Translate books (PDF/DOCX/EPUB) into any language using parallel sub-agents. Converts input -> Markdown chunks -> translated chunks -> HTML/DOCX/EPUB/PDF. allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Agent, AskUserQuesti

Network accessline 4

allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Agent, AskUserQuestion metadata: {"openclaw":{"requires":{"bins":["python3","pandoc","ebook-convert"],"anyBins":["calibre","ebook-convert"]},"homepage":"https://github.com/deusyu/translate

Network accessline 5

metadata: {"openclaw":{"requires":{"bins":["python3","pandoc","ebook-convert"],"anyBins":["calibre","ebook-convert"]},"homepage":"https://github.com/deusyu/translate-book"}}

`scripts/calibre_html_publish.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/chunk_context.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/convert.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 94

namespaces = {             'opf': 'http://www.idpf.org/2007/opf',

Network accessline 95
```
'opf': 'http://www.idpf.org/2007/opf',
```

Network accessline 96

'dc': 'http://purl.org/dc/elements/1.1/',

Network accessline 97
```
'dcterms': 'http://purl.org/dc/terms/'
```

Possible obfuscationline 929

metadata, body = split_front_matter(content.replace('<U+FEFF>', ''))

Possible obfuscationline 948

content = content.replace('<U+FEFF>', '').replace(' ', ' ')

Possible obfuscationline 980

data = base64.b64decode(data_uri.group(2))

Network accessline 1519

if not calibre_path:             print("Error: Calibre ebook-convert not found")             print("Please install Calibre: https://calibre-ebook.com/")

Network accessline 1520

print("Error: Calibre ebook-convert not found")             print("Please install Calibre: https://calibre-ebook.com/")             sys.exit(1)

Network accessline 1521

print("Please install Calibre: https://calibre-ebook.com/")

`scripts/glossary.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/manifest.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/merge_and_build.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/merge_meta.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/meta.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/run_state.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`tests/test_calibre_html_publish.py`

Executable scriptline 1
```
Executable file
```

`tests/test_chunk_context.py`

Executable scriptline 1
```
Executable file
```

`tests/test_convert.py`

Executable scriptline 1
```
Executable file
```

Network accessline 562

_link("#calibre_link-1", _str("cross-reference")), _str(","), SPACE,                   _span(*_words("sic erat"), attrs=[("lang", "lat")]), SPACE,                   _link("https://example.com", _str("site"))),

Network accessline 563

_span(*_words("sic erat"), attrs=[("lang", "lat")]), SPACE,                   _link("https://example.com", _str("site"))),         )

Network accessline 564

_link("https://example.com", _str("site"))),

Network accessline 570

doc["blocks"][0]["c"],             [*_words("A page anchor"), SPACE, _str("cross-reference,"), SPACE,              *_words("sic erat"), SPACE, _link("https://example.com", _str("site"))],

Network accessline 571

[*_words("A page anchor"), SPACE, _str("cross-reference,"), SPACE,              *_words("sic erat"), SPACE, _link("https://example.com", _str("site"))],         )

Network accessline 572

*_words("sic erat"), SPACE, _link("https://example.com", _str("site"))],

Network accessline 618

doc = _doc(_para(             _str("A"), _span(SPACE, _span(ident="page_3")), _str("B"),             _link("https://example.com", SPACE), _str("C"),

Network accessline 619

_str("A"), _span(SPACE, _span(ident="page_3")), _str("B"),             _link("https://example.com", SPACE), _str("C"),         ))

Network accessline 620

_link("https://example.com", SPACE), _str("C"),

Network accessline 628

# Calibre classes such as `pcalibre1` survive on external links and         # would be written out as `[site](https://example.com){.pcalibre1}`.

Network accessline 629

# would be written out as `[site](https://example.com){.pcalibre1}`.

Network accessline 630

link = {"t": "Link", "c": [["calibre_link-5", ["pcalibre1", "pcalibre"], [["type", "x"]]],                                    [_str("site")], ["https://example.com", "Example"]]}

Network accessline 631

[_str("site")], ["https://example.com", "Example"]]}

Network accessline 636

self.assertEqual(             doc["blocks"][0]["c"][-1],             {"t": "Link", "c": [["", [], []], [_str("site")], ["https://example.com", "Example"]]},

Network accessline 637

doc["blocks"][0]["c"][-1],             {"t": "Link", "c": [["", [], []], [_str("site")], ["https://example.com", "Example"]]},         )

Network accessline 638

{"t": "Link", "c": [["", [], []], [_str("site")], ["https://example.com", "Example"]]},

Network accessline 1126

def test_leaves_remote_and_missing_images_untouched(self):         with tempfile.TemporaryDirectory() as tmp:             text = "![r](https://example.com/x.png)\n![m](missing.png)\n"

Network accessline 1127

with tempfile.TemporaryDirectory() as tmp:             text = "![r](https://example.com/x.png)\n![m](missing.png)\n"             md = self._source(tmp, text)

Network accessline 1128

text = "![r](https://example.com/x.png)\n![m](missing.png)\n"

`tests/test_glossary.py`

Executable scriptline 1
```
Executable file
```

`tests/test_manifest.py`

Executable scriptline 1
```
Executable file
```

`tests/test_merge_and_build.py`

Executable scriptline 1
```
Executable file
```

`tests/test_merge_meta.py`

Executable scriptline 1
```
Executable file
```

`tests/test_meta.py`

Executable scriptline 1
```
Executable file
```

`tests/test_run_state.py`

Executable scriptline 1
```
Executable file
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 2 facts

Contacts www.idpf.org, which SKILL.md, the README and the plugin manifest do not mentionscripts/convert.py:95High confidence
Contacts purl.org, which SKILL.md, the README and the plugin manifest do not mentionscripts/convert.py:96High confidence

Signal confidence: 87 facts

Network access in prose of documentationREADME.md:11Low confidence
Network access in prose of documentationREADME.md:53Low confidence
Network access in prose of documentationREADME.md:54Low confidence
Network access in prose of documentationREADME.md:55Low confidence
Network access in code of documentationREADME.md:74Low confidence
Network access in code of documentationREADME.md:75Low confidence
Network access in code of documentationREADME.md:89Low confidence
Network access in code of documentationREADME.md:90Low confidence
Network access in prose of documentationREADME.md:170Low confidence
Network access in prose of documentationREADME.md:172Low confidence
Network access in prose of documentationREADME.md:173Low confidence
Network access in prose of documentationREADME.md:174Low confidence
Network access in prose of documentationREADME.md:175Low confidence
Network access in prose of documentationREADME.md:176Low confidence
Network access in prose of documentationREADME.md:177Low confidence
Network access in prose of documentationREADME.md:318Low confidence
Network access in prose of documentationREADME.md:358Low confidence
Network access in prose of documentationREADME.md:364Low confidence
Network access in prose of documentationREADME.zh-CN.md:11Low confidence
Network access in prose of documentationREADME.zh-CN.md:53Low confidence
Network access in prose of documentationREADME.zh-CN.md:54Low confidence
Network access in prose of documentationREADME.zh-CN.md:55Low confidence
Network access in code of documentationREADME.zh-CN.md:74Low confidence
Network access in code of documentationREADME.zh-CN.md:75Low confidence
Network access in code of documentationREADME.zh-CN.md:89Low confidence
Network access in code of documentationREADME.zh-CN.md:90Low confidence
Network access in prose of documentationREADME.zh-CN.md:170Low confidence
Network access in prose of documentationREADME.zh-CN.md:172Low confidence
Network access in prose of documentationREADME.zh-CN.md:173Low confidence
Network access in prose of documentationREADME.zh-CN.md:174Low confidence
Network access in prose of documentationREADME.zh-CN.md:175Low confidence
Network access in prose of documentationREADME.zh-CN.md:176Low confidence
Network access in prose of documentationREADME.zh-CN.md:177Low confidence
Network access in prose of documentationREADME.zh-CN.md:318Low confidence
Network access in prose of documentationREADME.zh-CN.md:358Low confidence
Network access in prose of documentationREADME.zh-CN.md:364Low confidence
Broad permissions in the frontmatter of the SKILL.mdSKILL.md:1High confidence
Network access in the frontmatter of the SKILL.mdSKILL.md:3Low confidence
Network access in the frontmatter of the SKILL.mdSKILL.md:4Low confidence
Network access in the frontmatter of the SKILL.mdSKILL.md:5Low confidence
Executable script in code of a file that runsscripts/calibre_html_publish.py:1High confidence
Executable script in code of a file that runsscripts/chunk_context.py:1High confidence
Executable script in code of a file that runsscripts/convert.py:1High confidence
Network access in code of a file that runsscripts/convert.py:94High confidence
Network access in code of a file that runsscripts/convert.py:95High confidence
Network access in code of a file that runsscripts/convert.py:96High confidence
Network access in code of a file that runsscripts/convert.py:97High confidence
Possible obfuscation in code of a file that runsscripts/convert.py:929High confidence
Possible obfuscation in code of a file that runsscripts/convert.py:948High confidence
Possible obfuscation in code of a file that runsscripts/convert.py:980High confidence

and 37 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Path .claude/commands/release.md	`.claude/skills/<skill-name>/`
Codex	Native	Manifest AGENTS.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

[![deusyu/translate-book on hotskills](https://hotskills.dev/badge/deusyu-translate-book.svg)](https://hotskills.dev/skill/deusyu-translate-book/)

deusyu/translate-book

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

translate-book

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Rank over the last 12 weeks

Before you install

.github/FUNDING.yml

README.md

README.zh-CN.md

SKILL.md

scripts/calibre_html_publish.py

scripts/chunk_context.py

scripts/convert.py

scripts/glossary.py

scripts/manifest.py

scripts/merge_and_build.py

scripts/merge_meta.py

scripts/meta.py

scripts/run_state.py

tests/test_calibre_html_publish.py

tests/test_chunk_context.py

tests/test_convert.py

tests/test_glossary.py

tests/test_manifest.py

tests/test_merge_and_build.py

tests/test_merge_meta.py

tests/test_meta.py

tests/test_run_state.py

How the signals fit together

Works with

You might also use

mattpocock/skills

obra/superpowers

tt-a1i/archify

career-ops-hq/career-ops

heygen-com/hyperframes

blader/humanizer

Explore alternatives and comparisons

Add this badge to your README

`SKILL.md`

`.github/FUNDING.yml`

`README.md`

`README.zh-CN.md`

`SKILL.md`

`scripts/calibre_html_publish.py`

`scripts/chunk_context.py`

`scripts/convert.py`

`scripts/glossary.py`

`scripts/manifest.py`

`scripts/merge_and_build.py`

`scripts/merge_meta.py`

`scripts/meta.py`

`scripts/run_state.py`

`tests/test_calibre_html_publish.py`

`tests/test_chunk_context.py`

`tests/test_convert.py`

`tests/test_glossary.py`

`tests/test_manifest.py`

`tests/test_merge_and_build.py`

`tests/test_merge_meta.py`

`tests/test_meta.py`

`tests/test_run_state.py`