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

Novel Discuss

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

讨论创意、角色、世界观、体系、势力、事件走向,做创作决策。触发词:"讨论""帮我决定""方案对比""角色设计""世界观""体系审查""设计一个物品"。

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

Install

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

✓ 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-discuss)

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 Discuss? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

创作讨论与设计

创作边界:虚构创作,暴力、情色、血腥均可讨论。

路由

判定话题类型 → 加载对应 reference → 按 context-routing.md 只读最小上下文:

| 关键词 | 类别 | 加载文件 | |--------|------|----------| | 构建世界观、从零设计、世界观进度 | 世界观引导构建 | references/world-design.md | | 世界观、地理、历史、社会结构 | 世界观讨论 | references/world-design.md | | 角色、主角、反派、配角、人物 | 角色设计 | references/character.md | | 物品、法宝、道具、阵法、丹药 | 物品设计 | references/item-design.md | | 势力、门派、组织、阵营 | 势力设计 | references/faction-design.md | | 体系、规则、能力、修炼、境界、自洽 | 体系设计 | references/concept-design.md | | 事件、事件规划、这段怎么走 | 事件画布 | references/event-canvas.md | | 剧情、走向、方案、对比、决定 | 自由讨论 | 无(使用下方通用框架) |

先读 references/context-routing.md 判定动作类型(新建设定/补充已有/编辑已有/自洽审查/未来剧情/自由讨论),再按 话题 × 动作 选最小上下文包。判断不清时先追问,不靠盲读整个项目猜。

通用讨论框架

苏格拉底式对话:不直接给答案,提供多角度,尊重用户选择。

默认风格守门

CLAUDE.md 已声明创作风格基线时,讨论阶段将其作为轻量守门规则:

  • 讨论角色/关系/未来剧情时,审视该设计如何服务主角装逼链条
  • 某个想法占用太多叙事资源却不服务主角装逼,提醒用户更适合做低优先级支线

流程

  1. 理解问题:复述核心问题、背景、限制条件,确认理解正确
  2. 澄清性提问:问题不够清晰时先问,不急着给方案
  3. 三个方案:用 AskUserQuestion 展示,每个方案含描述、优点、缺点、适合场景。方案核心思路必须明显不同
  4. 迭代:用户选 → 确认记录;用户混合 → 逐项确认取什么;用户不满意 → 问清原因重新设计
  5. 未来剧情的两段式收束:先自然讨论说清问题和方向;用户偏向某方案后用因果链讲述方向故事(从当前到目标怎么推进,说清关键转折);故事确认后逐步澄清模糊处,一次一个

落盘

讨论收束后必须落盘:

  • 设定类结论 → 对应 entity 文件 / worldbuilding.md / past.md
  • 讨论纪要 → memory/discussions/YYYY-MM-DD-HHMM-简短主题.md + 追加索引到 memory/discussions.md
  • 未来规划 → memory/future/ 对应文件。只写已确认结论,只补本次讨论直接涉及的条目

宪法修正检查

落盘前检查本次讨论是否触发小说宪法修正:

  • 讨论了新爽感类型或改变爽感公式 → 修正「爽感公式」
  • 讨论了主角新吸引力来源或定位 → 修正「主角光谱」
  • 用户表达了「不要 X 要 Y」的审美偏好 → 修正「作者人格」
  • 用户说「写出来不像我想要的」→ 反推「叙事纹理」或「作者人格」调整
  • 讨论暴露宪法默认规则不再适用 → 修正对应条目

触发时直接更新 CLAUDE.md 中对应条目,修正前向用户确认改什么、改成什么、为什么。不重写整个宪法。

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.