Skip to content
Agentmart
Submit a tool

webnovel-review-settings

设定集审核专家。深度检查世界观、力量体系、角色、势力、经济、历史、创意约束等设定文件的质量与自洽性,输出问题清单。

Skill by ricky-theseus

IndexedGPL-3.0★ 76
Write a review

Chalk Labs

Need help deploying webnovel-review-settings?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ricky-theseus-webnovel-review-settings

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

设定集审核专家。深度检查世界观、力量体系、角色、势力、经济、历史、创意约束等设定文件的质量与自洽性,输出问题清单。

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/webnovel-review-settings

Tools it pre-approves 7

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read
  • Grep
  • Bash
  • Edit
  • Write
  • Agent
  • AskUserQuestion

What's inside

Skill name
webnovel-review-settings
Description
设定集审核专家。深度检查世界观、力量体系、角色、势力、经济、历史、创意约束等设定文件的质量与自洽性,输出问题清单。
License
GPL-3.0
Allowed tools
Read, Grep, Bash, Edit, Write, Agent, AskUserQuestion
Instructions
137 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves any shell command

Agent Skills spec issues

  • name: "webnovel-review-settings" does not match folder "review-settings"

Files (2)

  • SKILL.md
  • setting-review-dimensions.md · references/

SKILL.md (first lines)

# 设定集审核 (Setting Review Expert)

## 目标

逐文件、逐维度检查项目设定集的质量与自洽性,输出结构化问题清单。不评分,只找问题 + 给修复方向。

## 原则

1. 只读审核,不修改设定文件(除非用户明确要求)。
2. 每条问题必须有证据(引用设定原文),不凭感觉。
3. 问题按维度分组,标注严重度(阻断/高/中/低)。
4. 无问题也显式声明"该维度通过"。

## 执行流程

### Step 1:解析项目根 + 加载设定文件

```bash
export WORKSPACE_ROOT="${CLAUDE_PROJECT_DIR:-${OPENCODE_PROJECT_DIR:-$PWD}}"
export CLAUDE_PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-${OPENCODE_PLUGIN_ROOT:-}}"
export SCRIPTS_DIR="${CLAUDE_PLUGIN_ROOT}/scripts"
export PROJECT_ROOT="$(python -X utf8 "${SCRIPTS_DIR}/webnovel.py" --project-root "${WORKSPACE_ROOT}" where 2>/dev/null || echo "${WORKSPACE_ROOT}")"
```

确认设定集目录存在:
```bash
Get-ChildItem -LiteralPath "${PROJECT_ROOT}/设定集" -Name
```

### Step 2:逐文件加载设定

必须读取的设定文件(根据 `--scope` 过滤):
- `世界观.md` — always
- `力量体系.md` — always
- `主角卡.md` — always
- `反派设计.md` — always
- `行文约束集.md` — if exists
- `女主卡.md` — if exists
- `主角组.md` — if exists (多主角)
- `大纲/总纲.md` — 创意约束对齐用
- `.story-system/MASTER_SETTING.json` — 调性/禁忌参照
- `.webnovel/idea_bank.json` — 创意约束来源

### Step 3:逐维度审核

详见 `references/setting-review-dimensions.md`。核心维度:

| 维度 | 检查要点 |
|------|---------|
| **世界观自洽性** | 物理法则无矛盾、地理-历史-社会逻辑链完整、核心规则不可绕过 |
| **力量体系完整性** | 境界有战力参照、代价明确、越级规则清晰、漏洞有解释 |
| **角色设定深度** | 欲望→缺陷→弧线对齐、OOC警戒合理、关系网无遗漏 |
| **势力格局合理性** | 各方有动机非标签化、平衡有制衡因素、关系表自洽 |
| **经济与资源** | 货币锚定物明确、购买力稳定、稀缺性规则成立 |
| **时间线逻辑** | 关键节点有日期、因果链连续、无时序矛盾 |
| **创意约束落地** | 反套路规则已写入设定、硬约束不可绕过、卖点不空泛 |
| **行文约束与设定一致性** | 行文约束与世界观/角色匹配,不冲突 |

### Step 4:输出问题清单

```markdown
## 设定集审核报告

项目:{project_name}
审核时间:{timestamp}
审核范围:{scope}

### 通过项(无问题)
- 世界观自洽性:通过
- ...

### 问题清单

#### [阻断] 问题标题
- 文件:设定集/xxx.md 第N行
- 证据:原文引用
- 问题:具体矛盾/缺失点
- 修复方向:建议的修改方案

#### [高] ...
#### [中] ...
#### [低] ...

### 审核总结
N个阻断 / M个高优 / K个中低优
```

## 严重度定义

| 级别 | 定义 |
|------|------|
| 阻断 | 逻辑矛盾会导致写作卡死或读者出戏(如战力体系自毁、核心规则被绕过后无解释) |
| 高 | 明显漏洞,写作中大概率触发(如货币购买力忽高忽低、角色动机链断裂) |
| 中 | 潜在隐患,边缘场景触发(如某个配角关系未定义、边境地名未交代) |
| 低 | 完善性建议(如可补充日常物价参考、可增加一个历史事件) |

## 快速模式 (`--quick`)

只检查阻断级和高优问题,跳过中低优完善性建议。`--scope` 可指定单维度如 `worldview`。

## 与 webnovel-init 集成

`webnovel-init` 在 Step 7(最终确认)之后、执行生成之前,可调用本技能对已收集的设定做审核。

调用方式:在 init 流程中,收集完所有设定后,触发:

```text
设定已收集完毕,接下来由设定审核专家做最终质检:
/webnovel-review-settings --quick
```

审核通过(无阻断)→ 进入执行生成。
审核未通过(有阻断)→ 展示问题,让用户选择:修改后重审 / 跳过继续生成 / 中断。

## 作者友好最终报告契约

最终回复必须面向作者,不输出原始 JSON 或长命令日志。使用固定三段式:

```text

From ricky-theseus/DaisyWriter, GPL-3.0.

More from ricky-theseus/DaisyWriter

Signals

Stars
76
Forks
5
Open issues
0
Last commit (this folder)
Jun 23, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
GPL-3.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ricky-theseus

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get webnovel-review-settings running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying webnovel-review-settings?

CallGet help
Cite this page

webnovel-review-settings skill. Agent Mart. https://agentmart.dev/skills/ricky-theseus-webnovel-review-settings (last updated 2026-10-24)