Multi-perspective adversarial review. Full/lean modes spawn reviewer agents in parallel when deployed; automatically degrades to solo review if agents are missing, abnormal, or spawn fails, and falls back to built-in rubric when reference files are unreadable. Triggered by: /story-review, /审查, 「审查一下」, 「帮我审一下」
The worldwonderer/story-review skill provides a multi-perspective adversarial review system for AI agent platforms. It is designed to simulate collaborative critique by spawning multiple reviewer agents in parallel under 'full' or 'lean' modes, each offering distinct analytical angles on a story or document. If the necessary reviewer agents are absent, behave abnormally, or fail to spawn, the skill automatically degrades to a solo review mode, ensuring uninterrupted operation. Additionally, if reference files are unreadable or missing, it falls back to a built-in rubric for assessment. This makes it a robust, fault-tolerant tool for developers and users using agents like Claude Code, Cursor, or Codex, providing consistent, adversarial feedback regardless of environment conditions. The skill is triggered via chat commands such as /story-review or localized equivalents.
npx skills add https://github.com/worldwonderer/oh-story-claudecode/tree/main/skills/story-reviewInstalled? Explore more Productivity & Collaboration skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →
Multi-perspective adversarial review. Full/lean modes spawn reviewer agents in parallel when deployed; automatically degrades to solo review if agents are missing, abnormal, or spawn fails, and falls back to built-in rubric when reference files are unreadable. Triggered by: /story-review, /审查, 「审查一下」, 「帮我审一下」
This repo contains 12 individual skills — each has its own dedicated page.
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP, agent-browser, 浏览器操作, 操作浏览器, Chrome CDP, 复用登录态, extract token from browser.
网络小说工具箱主入口。根据用户需求自动路由到对应 skill。 触发方式：/story、/网文、「我想写小说」「帮我写书」「写网文」 当用户意图不明确时触发此 skill，由路由逻辑分发到具体的扫榜/拆文/写作/去AI味/封面 skill。
小说封面生成。根据书名、作者名自动分析题材风格，调用 GPT-Image-2 直接生成含标题和署名的专业级网文封面。 触发方式：/story-cover、/封面、「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」
网文去AI味。检测并清除文本中的AI写作痕迹，让文字回归自然、非模板化。 触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」
逆向导入已有小说。将已写好的小说（半成品或完本）反向解析为标准项目目录结构， 兼容 story-long-write / story-short-write 后续写作流程。内部复用 story-long-analyze / story-short-analyze 的拆解管道，按篇幅自动分流。 触发方式：/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」
长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。 单一深度拆解管道：跑完黄金三章（Stage 1）后产出快速预览报告并询问是否继续全量拆解， 确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告，全程产物落盘 `拆文库/{书名}/`。 触发方式：/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」 「深度拆解」「完整拆解」「系统拆解」或提供小说文本文件路径——全部进入同一管道。
长篇网文扫榜。分析起点、番茄、晋江等平台排行榜数据，提炼市场趋势与热门题材。 触发方式：/story-long-scan、/长篇扫榜、「长篇什么火」「起点排行」
长篇网文写作。从大纲到正文，辅助长篇网络小说的创作，包括世界观、人物、情节线管理。 触发方式：/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」
网文写作工具集基础设施部署。将 hooks/rules/agents/CLAUDE.md 等基础设施部署到用户项目目录。 触发方式：/story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」
短篇网文拆文。拆解爆款短篇小说（番茄短篇 / 故事会 / 知乎盐选 / 追妻 / 世情 / 重生 / 虐渣等通俗题材）的故事核、结构、情感线、反转设计、写作手法、共鸣层次。 单一全量拆解管道：跑完 Stage 2-6 产出完整拆文报告，落盘到 `拆文库/{书名}/`， 下游 `story-short-write` 同时读拆文报告 + 情节节点 + 写作手法 + 原文 + _meta.json 写下一篇。 触发方式：/story-short-analyze、/短篇拆文、「拆短篇」「拆这篇短文」「短篇拆文」 「精细拆解短篇」「8000 字短篇拆解」「番茄短篇拆文」「故事会拆解」「盐言故事拆解」 「分析这篇短篇」——均进入同一管道。
短篇网文扫榜。分析知乎盐言、七猫、黑岩、点众等平台热门短篇数据，捕捉风口题材。 触发方式：/story-short-scan、/短篇扫榜、「短篇什么火」「知乎故事排行」
短篇网文写作。辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控。 触发方式：/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」
Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.
Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.