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 gogoingai/wenqu-skills --skill wenqu-translategit clone --depth 1 https://github.com/gogoingai/wenqu-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/gogoingai/wenqu-skills/wenqu-translate)<a href="https://agentmods.dev/skills/gogoingai/wenqu-skills/wenqu-translate"><img src="https://agentmods.dev/badge/skills/gogoingai/wenqu-skills/wenqu-translate/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/gogoingai/wenqu-skills/wenqu-translate"><img src="https://agentmods.dev/badge/skills/gogoingai/wenqu-skills/wenqu-translate.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 | $0.00081 | $0.01347 |
| Opus 5 | $0.00041 | $0.00674 |
| Sonnet 5 | $0.00016 | $0.00269 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade A, and why
wenqu-translate 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
英文材料翻译 Skill
用户输入工具
当本技能需要用户确认选择、补充必要信息或授权有副作用的操作时：
- 优先用运行时自带的用户输入工具，例如
AskUserQuestion、request_user_input、clarify、ask_user或等价能力。 - 若没有此类工具，使用带编号或字母选项的文本问答。
- 同一决策阶段中彼此独立的问题可合并提问；后一个问题依赖前一回答时，按依赖顺序逐个问。
- 已由用户当前指令、调用方或文章偏好提供的信息，不重复询问。
- 文中出现的具体工具名均为示例；应替换为当前运行时的等价能力。
工具等价说明（非 Claude Code 环境）
Skill（调用 wenqu-review 做 R2 审查）是 Claude Code 工具名。其他 agent 没有该工具时，直接 Read ~/.agents/skills/wenqu-review/references/r2-translation.md 内联执行。
触发识别
| 场景 | 入口 |
|---|---|
| 用户直接说"翻译一下"、给一段英文要求译成中文（单篇文章量级） | 独立触发，走下方"翻译流程" |
| wenqu-write Step 2 获取素材时源材料是英文 | 被调用，读者画像已由调用方提供，跳过下方"确认读者背景"这一步 |
| 源文档很长（约 4000 词以上）、要翻译多篇与整本书、需要 quick/normal/refined 多模式切换或分块并行翻译 | 超出本技能范围，如实告知用户另寻专门的长文档翻译工具，不要硬凑 |
超出范围的情况
源文档词数明显超过 4000、需要 quick/normal/refined 多模式切换、分块并行翻译，或要翻译整本书/多篇文档时，超出本技能范围：如实告知用户“这个量级超出本技能范围，建议寻找专门的长文档翻译工具”，不要硬凑一份打折扣的翻译。本技能不依赖、也不主动推荐任何第三方技能。
翻译流程
→ 查 references/translation-guide.md（完整方法论：分析→翻译→自查，核心原则，注解密度规则，常见误译信号）
独立触发时，先确认读者背景（决定注解密度）：没有调用方提供读者画像，用 AskUserQuestion 询问"目标读者的技术背景是？"（无背景、初级工程师、中级工程师、高级工程师），再进入翻译。
翻译完成后，强制当场执行一次 R2，不等到全文写完：用 Skill 工具调用 wenqu-review，指定只跑 R2（翻译腔审查）；没有跨技能调用机制时直接 Read ~/.agents/skills/wenqu-review/references/r2-translation.md 内联执行。这一步不可省略——Claude 系模型生成中文时容易出现翻译腔，尤其是刚读完英文源码、文档之后，译者很难察觉自己写出的翻译腔。
依赖
references/translation-guide.md完整自包含，覆盖单篇文章量级的翻译，不需任何外部依赖- R2 审查依赖 wenqu-review（同仓库技能，随套件一起安装）
用户反馈与偏好持久化
本技能不修改自身仓库的 references/translation-guide.md，遇到新的误译模式或用户给出的持久化翻译偏好（专有名词是否保留英文、注解密度、直译信号判定……），改为写入被翻译文章自身的存储目录：{项目根目录}/wenqu-skills/{文件名}/references/preferences.md「翻译偏好」表（表结构见 wenqu-write 的 references/planning/questionnaire.md「写入 preferences.md」一节）。
判定标准：这条反馈下次译同一篇文章时还用得上吗？
- 是（"agent 不要翻译成智能体，保留英文"这类持续适用的取舍）→ 当场往
references/preferences.md「翻译偏好」表里追加一行 - 否（这次这段话的临时改法）→ 不持久化
每次翻译前先查这份文件（被 wenqu-write 调用时通常已加载；独立触发时自己检查该文章的 wenqu-skills/{文件名}/references/preferences.md 是否存在），有已记录的偏好就照着做，不重复问用户。
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.
- 12d ago First seen · 77 lines · 81 tokens per session scan A 87c58509f3be
wenqu-translate is a skill published in the GitHub repository gogoingai/wenqu-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,347 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
blog-locale-audit
Audit a directory of multilingual blog content for completeness, consistency, hreflang correctness, meta-tag parity, and freshness. Builds a translation coverage matrix, flags stale translations, validates hreflang and schema, and emits a prioritized report with runnable fix commands. Use when user says "locale…
blog-localize
Cultural adaptation for translated content. Run AFTER blog-translate completes. Adjusts brand examples, CTAs, legal references, and formality for the target market (German, French, Japanese, Spanish, etc.). Deep cultural adaptation of translated blog posts. Goes beyond translation to swap brand examples, adapt CTAs…
blog-translate
Translate existing blog posts into one or more target languages with SEO-optimized localization. Produces native-quality translations that preserve markdown structure, frontmatter, schema JSON-LD, image and chart embeds, and citation capsules. Localizes keywords, meta tags, numbers, dates, currencies, and quote styles…
subtitle-translate
A subtitle translation tool for existing SRT, VTT, or ASS files. It can create translated or bilingual subtitles and optionally attach them to a video or burn them into the picture.
humanizer-ru
A Russian-text editor that removes bureaucratic wording, filler, copied chatbot patterns and signs of AI writing while keeping facts and examples.
blog-multilingual
One-command multilingual blog creation. Writes a blog post, translates it into user-specified languages, applies cultural adaptation, and emits hreflang tags, sitemap entries, and a CMS-ready language map. The complete write-to-publish pipeline for international content. Orchestrates blog-write, blog-translate…