AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Fanyi Xiaoshuo

skill-anarcadia-chuanban-jp-novel-translator-fanyi-xiaoshuo · by Anarcadia

|

No reviews yet
0 installs
4 views
0.0% view→install

Install

$ agentstack add skill-anarcadia-chuanban-jp-novel-translator-fanyi-xiaoshuo

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-anarcadia-chuanban-jp-novel-translator-fanyi-xiaoshuo)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
23d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Fanyi Xiaoshuo? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

长篇小说翻译系统 - 调度层

采用 主调度 + 章节 sub-agent 架构。Sub-agent 由独立 skill fanyi-xiaoshuo-worker 定义。

本 skill 支持两种素材入口:已经拆好的章节文件可以直接放入 source/;未拆分的 .md / .txt / .epub 小说文件,推荐先用 scripts/prepare_source.py 自动抽取章节、判断长度并实际拆分。

建议精翻模型使用 claude-opus-4.6,日常翻译模型使用 DeepSeek-v4-proDeepSeek-V4-Pro 必须使用官方 API、官方源的第三方中转 API,或者 OpenRouter 提供的非 SiliconFlow 供应商源;否则容易在翻译过程中撞到审核,出现拒绝翻译的状况。其他模型不保证翻译质量,也不保证长篇串行流程稳定。


⚠️ 关键约束(必读)

绝对禁止并行启动章节 sub-agent。必须严格串行执行。

  • ❌ 禁止:同时启动多个章节的 sub-agent
  • ❌ 禁止:在前一个 sub-agent 返回结果前启动下一个
  • ✅ 必须:等待章节 N 完成 → 确认结果 → 再启动章节 N+1

违反后果:后章依赖前章的术语表、摘要更新,并行会导致术语不一致、上下文断裂。

工作模式选择

  • 询问模式(默认):遇到术语歧义时,sub-agent 返回术语待定;主对话询问用户后,重新启动同一章节并传入用户术语决策
  • 全自动模式:sub-agent 自行决断所有歧义,记录决策和置信度

架构说明

主对话(轻量调度)
    │
    ├─→ 章节1 sub-agent (fanyi-xiaoshuo-worker skill)
    ├─→ 章节2 sub-agent (fanyi-xiaoshuo-worker skill)
    └─→ ...
  • 主对话:负责初始化、素材准备、启动 sub-agent、确认完成、显示进度、处理用户交互
  • 章节 sub-agent:完成翻译、术语表/摘要/进度文件更新,并返回简短确认

优化收益:主线上下文消耗减少 80%+,可支持超长篇翻译。


工作流概览

阶段一:项目初始化
阶段 1.2:源文件准备(md/txt/epub 自动抽章和实际拆分)
阶段二:翻译主循环(严格串行)
阶段 2.5:批次检查点
阶段 2.6:术语清理提议(每 10 章)
阶段三:后处理(合并、ePub)

执行前必读:[references/workflow.md](references/workflow.md)


主对话职责

  • 初始化项目和准备源文件
  • 只调度和确认,不直接执行章节翻译
  • 启动单个章节 sub-agent,并等待返回
  • 在询问模式下转达术语问题,并将用户决策传回同一章节重试

sub-agent 职责

fanyi-xiaoshuo-worker skill 定义:

  • 完成全部翻译工作
  • 完成全部文件更新
  • 正常完成时返回简短确认;术语待定时返回询问格式

References

  • [workflow.md](references/workflow.md) - 完整工作流步骤
  • [formats.md](references/formats.md) - 文件格式规范
  • [troubleshooting.md](references/troubleshooting.md) - 常见问题排查

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.