Token导航 LogoToken导航TokenDH.com
运维权限需确认clawhub未标认证来源可访问clear审计通过

writers-room-story-engine作家室故事引擎

Agent Skill

writers-room-story-engine 用于辅助前端页面、组件、样式和交互逻辑开发,适合在 OpenClaw 中需要维护前端项目、生成组件或检查界面实现时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

9,517

周安装

385

GitHub Stars

公开资料未说明

下载量

2,988
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:writers-room-story-engine(作家室故事引擎)
来源仓库:https://github.com/jackterror/writers-room-story-engine
安装命令:
openclaw skills install writers-room-story-engine
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install writers-room-story-engine

简介

协调模块化故事开发流程,根据当前阶段路由至基础构建、世界设定或场景编写子技能。

  • 适用于小说、游戏剧本等长内容创作,保持叙事连贯性与角色发展一致性。
  • 自动诊断项目进度并推荐下一步行动,输出章节大纲与情节冲突解决方案。
  • 需读取项目元数据与创作历史,注意版权归属与素材引用合规性。
  • 建议在多人协作时明确分工边界,避免重复劳动与风格漂移问题。

SKILL.md

name
writers-room-story-engine
description
Orchestrates modular story development by diagnosing the current phase and routing to the right story skill for foundations, worldbuilding, scene writing, or revision. Use when building a story from scratch, improving an outline, strengthening narrative structure, or guiding story development in staged workflows.

Writers Room Story Engine

Use this skill as the primary orchestration layer for Writers Room Story Engine.

Its job is to diagnose the current story phase, determine what is missing, and route to the appropriate supporting module instead of jumping straight into prose.

Supporting modules

  • story-suite/designing-stories.md
  • story-suite/creating-story-foundations.md
  • story-suite/building-storyworlds.md
  • story-suite/writing-story-scenes.md
  • story-suite/revising-stories.md

Fallback

  • MEGA-SKILL.md is the fallback one-file version for simplified testing or deployment.

Purpose

The Writers Room Story Engine skill should not jump straight into prose when no story exists yet.

It should work through stages:

  1. story foundation
  2. world support when needed
  3. scene writing
  4. revision

This skill should determine what exists, what is missing, and which supporting module should be used next.

Required behavior

1. Diagnose the current phase first

Before generating long-form output, determine:

  • does a premise already exist?
  • does a story core already exist?
  • does an ending direction already exist?
  • does a protagonist already exist?
  • do major beats already exist?
  • does the world need to be built or adapted?
  • are scenes ready to draft?
  • is there already a draft that needs revision?

2. Route to the correct skill

Use:

  • story-suite/designing-stories.md to orchestrate overall development
  • story-suite/creating-story-foundations.md when nothing exists yet or the foundation is weak
  • story-suite/building-storyworlds.md when the world needs to support story through pressure, values, conflict, and consequence
  • story-suite/writing-story-scenes.md when beats exist and scenes should be drafted
  • story-suite/revising-stories.md when a story, outline, or draft is weak

3. Preserve stage discipline

Do not skip foundation work unless the user explicitly asks to skip it.

By default, foundation work should build:

  • seed options
  • story core
  • ending direction
  • protagonist engine
  • Story Spine
  • major beats

Treat the protagonist engine as:

  • want
  • need
  • lie
  • ghost
  • spine
  • comfort zone
  • pressure
  • stakes

Do not jump into scene writing if:

  • the protagonist is still generic
  • the ending direction is unclear
  • the beats are still and-then shaped

4. Keep worldbuilding story-relevant

Do not let the skill generate lore for its own sake.

World details must create:

  • pressure
  • consequences
  • choices
  • conflict
  • values
  • risk

Worldbuilding should be used when needed, not automatically overbuilt. If the story needs only light world support, keep it minimal.

5. Use stage outputs

At each phase, the skill should produce outputs the next phase can use.

Example:

  • foundation creates premise, protagonist, ending direction, Story Spine, and beats
  • worldbuilding maps pressures to protagonist and plot
  • scene writing turns beats into scenes
  • revision diagnoses weaknesses and repairs structure

6. Enforce story quality principles

This skill should reject or flag outputs with:

  • passive protagonists
  • and-then plotting
  • weak stakes
  • lore dumps
  • scenes with no turn
  • coincidence-based rescue
  • predictable first-thought choices
  • endings that do not test the story’s core truth

7. Enforce revision priority

When revising:

  • diagnose the highest-level failure first
  • repair story core before prose
  • repair character before polishing dialogue
  • repair plot before polishing sentences
  • do not start with line editing if the structure is broken

Recommended default workflow

  1. Orchestrate with story-suite/designing-stories.md
  2. Build with story-suite/creating-story-foundations.md
  3. Support with story-suite/building-storyworlds.md when needed
  4. Draft with story-suite/writing-story-scenes.md
  5. Improve with story-suite/revising-stories.md

Recommended orchestration behavior

When the user asks for a story from zero

  • do not immediately write the full story
  • first generate 3 strong premise options
  • pick the strongest
  • define the story core
  • define the ending direction
  • build protagonist engine
  • build Story Spine
  • build major beats
  • then ask whether to continue into scenes or continue automatically

When the user asks directly for prose

  • do a compressed internal foundation pass first
  • do not skip seed, story core, protagonist, ending direction, and beats internally
  • then write the story

When the user asks for stories in an existing world

  • identify what is already established
  • build only story-relevant world pressure
  • connect world elements to protagonist, stakes, and plot
  • avoid lore dumping

When the user asks for revision

  • diagnose the highest-level failure first
  • do not start with sentence-level polish if structure is broken

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

75.67%
按下载量换算2,261

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills