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

Novel Polish

skill-tulancn-vibe-noveling-novel-polish · by TulanCN

已完成章节正文的质量检查和润色。四轮:工具检测 → AI味修复 → 一致性校验 → 独立润色。触发词:"润色""polish""质检""检查""清理AI味""跑检测"。

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

Install

$ agentstack add skill-tulancn-vibe-noveling-novel-polish

✓ 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-tulancn-vibe-noveling-novel-polish)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo 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 Novel Polish? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

章节润色

对已完成的 正文.md 做四轮质量把关:工具检测 → AI味修复 → 一致性校验 → 独立润色。

第一步:定位章节

读取用户指定的章节正文。无参数时默认取最新完成的章节。

第二步:自动化工具链

依次运行以下工具,每个工具报告违规项:

python3 tools/ai_pattern_checker.py 
python3 tools/translationese_checker.py 
python3 tools/emotion_checker.py 
python3 tools/fragment_checker.py 

工具全部通过 → 跳过第三步,直接进入第四步。

工具有违规 → 记录违规项,进入第三步针对性修复。

第三步:AI 味修复

仅针对第二步工具报告的违规项 + 以下两项 LLM 专项检测:

3.1 对话失真检测

检查对话是否过于客气、理性或功能性。特征:

  • 角色像在开会而非在冲突
  • 互相讲解设定(信息灌输式对话)
  • 缺少攻击性和火气

修复策略:

  • 插入打断、反问或攻击性短句
  • 把设定解释改成行动后果
  • 给角色加非理性反应(偏执、赌气、装傻)

3.2 无功能细节检测

检查不承担叙事功能的微动作和声音描写。特征:

  • 声音描写反复出现但不是关键信息
  • 嘴角上扬、手指敲击等微动作偷渡情绪
  • 删掉对剧情推进无影响

修复策略:

  • 删除无功能细节
  • 改成角色态度判断
  • 改成对话或行动

3.3 工具违规项修复

根据工具报告的具体违规位置和类型,联系前后句整句重写,不做局部换词。修复原则参考 references/fix-guide.md

第四步:一致性校验

调用 consistency-guard agent,检查称谓、时间线、承接、设定冲突。局部修补,不重做结构。

第五步:独立润色

references/polish-rules.md,按 5 条原则对整章做文风转换。不大幅改字数,不改变核心表意。

第六步:闸门自检

对最终正文做定量自查:

| # | 检查项 | 通过标准 | 方式 | |---|--------|----------|------| | ① | 破折号 | 引号外 —— ≤ 1 | 人工 | | ② | 形容词+冒号 | 无 的是:之处: | 人工 | | ③ | 句号碎片 | 非对话连续短句 ≤ 3 | 脚本 | | ④ | 纠正句式 | 无连续使用 | 人工 | | ⑤ | 过渡词 | 无 最终/总之/综上所述 开头段落 | 人工 |

③ 必须脚本验证

python3 tools/fragment_checker.py  --threshold 3

退出码为 0 才通过。不过则修复后重跑,直到通过。

闸门全部通过后写回 正文.md

输出

润色完成后的 正文.md(原地覆盖)。

提示用户:确认后运行 novel-sync。

禁止

  • 大幅改字数或改变核心表意
  • 发现结构问题时在正文阶段硬修——回 novel-discuss 改事件卡
  • 借一致性修补名义重做结构
  • 跳过 fragment_checker 脚本验证

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.