Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AIGNE-io/doc-smith-skillsnpx agentmods add skills/aigne-io/doc-smith-skills/doc-smith-localizeWrote 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/aigne-io/doc-smith-skills/doc-smith-localize)<a href="https://agentmods.dev/skills/aigne-io/doc-smith-skills/doc-smith-localize"><img src="https://agentmods.dev/badge/skills/aigne-io/doc-smith-skills/doc-smith-localize/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/aigne-io/doc-smith-skills/doc-smith-localize"><img src="https://agentmods.dev/badge/skills/aigne-io/doc-smith-skills/doc-smith-localize.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 | $0.00041 | $0.02459 |
| Opus 5.5 | $0.00016 | $0.00984 |
| Sonnet 5.5 | $0.00008 | $0.00492 |
| Haiku 4.5 | $0.00004 | $0.00246 |
Grade C, and why
doc-smith-localize scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. `rm -rf .aigne/doc-smith/cache/task-status && mkdir -p .aigne/doc-smith/cache/task-status`(重建目录,清空旧状态) How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc-Smith 文档翻译
将文档翻译成多种语言,支持批量翻译和术语一致性。
用法
/doc-smith-localize --lang en # 翻译所有文档到英文
/doc-smith-localize -l en -l ja # 翻译到多个语言
/doc-smith-localize -l en -p /overview # 只翻译指定文档
/doc-smith-localize -l en --force # 强制重新翻译
/doc-smith-localize -l en --skip-images # 跳过图片翻译
选项
| 选项 | 别名 | 说明 |
|---|---|---|
--lang <code> |
-l |
目标语言代码(可多次使用) |
--path <docPath> |
-p |
指定文档路径(可多次使用) |
--force |
-f |
强制重新翻译,覆盖已有 |
--skip-images |
跳过图片翻译 |
约束
以下约束在任何操作中都必须满足。
1. Workspace 约束
.aigne/doc-smith/config.yaml和planning/document-structure.yaml必须存在- 不存在时提示用户先使用
/doc-smith生成文档
2. 参数验证约束
- 目标语言不能与源语言(config.yaml 的 locale)相同
--path指定的路径必须存在于 document-structure.yaml- 过滤后无有效语言时报错
3. 增量翻译约束
- 基于源 HTML 的 SHA256 hash(sourceHash)判断是否需要翻译
- hash 未变化的文档自动跳过(除非
--force) - 翻译失败时不覆盖已有翻译、不修改 .meta.yaml
4. Task 分发约束
- 每个文档到每种语言为一个独立翻译任务
- 通过 Task(references/translate-document.md) 分发,所有翻译 Task 必须使用
run_in_background: true,避免执行日志回流到主 agent 上下文 - 每批最多并行 5 个 Task,超过时分批执行
- 如有术语表(
.aigne/doc-smith/glossary.yaml或.md),传递给每个 Task
信号文件机制:
- 每个 Task 完成时在
.aigne/doc-smith/cache/task-status/写入{slug}.status文件 - slug 规则:docPath 去除
/前缀后以-替换/,再拼接-{targetLang}(如/api/overview→en=api-overview-en) - 状态文件内容为 1 行摘要(如
/overview → en: 成功 | hash: abc123) - 主 agent 通过轮询
.status文件判断 Task 是否完成(见"批次执行流程")
5. 图片翻译约束
- 未指定
--skip-images时,扫描 assets 中的图片资源 - 跳过条件(满足任一):
generation.shared: true、目标语言已存在、源语言图片不存在 - 使用
/doc-smith-images --update翻译图片文字 - 翻译后将图片同步到
dist/assets/{key}/images/发布目录 - 翻译后更新图片 .meta.yaml 的 languages 和 translations
6. Config 更新约束
- 翻译完成后,将目标语言添加到 config.yaml 的
translateLanguages数组 - 避免重复添加已存在的语言
- 更新后验证 config.yaml 正确
7. nav.js 重建约束
- Config 更新后必须执行 nav.js 重建:
node skills/doc-smith-build/scripts/build.mjs \ --nav --workspace .aigne/doc-smith --output .aigne/doc-smith/dist - 验证
dist/assets/nav.js包含所有目标语言的 code - 此步骤是语言切换功能生效的关键,绝不能跳过
What ships with it
1 file 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.
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 · 229 lines · 41 tokens per session scan C 5bff363c88dc
doc-smith-localize is a skill published in the GitHub repository AIGNE-io/doc-smith-skills (9 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 2,459 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
doc-smith-localize compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| doc-smith-localizeAIGNE-io/doc-smith-skills | Skill | 9 | 7mo ago | Apache-2.0 | C | 41 | Claude Code |
| translate-bookdeusyu/translate-book | Skill | 2.3k | 8d ago | MIT | A | 42 | Claude Code |
| pdf_translatorForceInjection/AI-fundamentals | Skill | 3.3k | yesterday | Apache-2.0 | A | 47 | Claude Code, Codex |
| translate-docsCherryHQ/cherry-studio | Skill | 53k | yesterday | AGPL-3.0 | A | 42 | Claude Code, Codex |
| azure-ai-translation-document-pybenjaminasterA/antigravity-awesome-skills | Skill | 461 | yesterday | MIT | A | 0 | Claude Code, Codex |
| docutranslateznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | A | 119 | Claude Code, Codex |
| lov-academic-translatorlovstudio/skills | Skill | 72 | 3d ago | MIT | A | 87 | Claude Code, Codex |