Agent Skill
Browser Cdp skill
browser-cdpzenstory-ai/oh-story-claudecodeskills/browser-cdp/SKILL.md
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.
always on
94 tokname + description
once used
2,237 tokSKILL.md body
bundled files
11 scripts
repo stars
7.9kGitHub
Install the Browser Cdp skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/zenstory-ai/oh-story-claudecode --skill browser-cdp
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/zenstory-ai/oh-story-claudecode.git /tmp/oh-story-claudecode mkdir -p ~/.claude/skills cp -R /tmp/oh-story-claudecode/skills/browser-cdp ~/.claude/skills/browser-cdp
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 94 tok |
| When the agent uses it | The SKILL.md instructions | 2,237 tok |
| Only if opened | 1 bundled files (40 KB) | varies |
Until it is used, browser-cdp costs about 14× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 13 skills from zenstory-ai/oh-story-claudecode would load 1,271 tokens of descriptions. Skills vs MCP study
Checks
- Ships scripts the agent can run. Read them before installing.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Browser CDP 操作工具
- 前置条件
- 启动流程（每次都按这个顺序）
- 启动脚本选项
- 常用操作
- 打开页面并等待加载
- 提取页面文本
- 提取 Auth Token
- 复杂 JS（含引号 / $ / 反引号）
- 页面交互（snapshot 拿元素引用）
- 停止 / 清理
- 长命令加超时
- 超时包装
- 已知限制
- 常见问题
More skills from zenstory-ai/oh-story-claudecode
- storyzenstory-ai/oh-story-claudecode
网络小说工具箱主入口。根据用户需求自动路由到对应 skill，并可启动本地 Dashboard。触发方式：/story、$story、/story dashboard、/网文、「我想写小说」「记住我的写作习惯」「打开工作台」「检查更新」。
7.9k263 tok idle · 3,786 in use - story-coverzenstory-ai/oh-story-claudecode
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 生成含标题和署名的专业级网文封面；Codex CLI 优先使用内置 ImageGen，无需单独 API Key。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」。
7.9k93 tok idle · 2,716 in use - story-deslopzenstory-ai/oh-story-claudecode
网文去AI味。从表达、叙事用笔、故事因果三层诊断并修复文本，保留作者文风与已定剧情。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。
7.9k470 tok idle · 3,149 in use - story-importzenstory-ai/oh-story-claudecode
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」。
7.9k599 tok idle · 3,321 in use - story-long-analyzezenstory-ai/oh-story-claudecode
长篇网文拆文。保留黄金三章、逐章摘要、剧情、情绪、节奏、角色、设定和文风接口，以连续章节块完成因果、双时间线、关系与三维节奏分析；兼容旧成果直接使用、按需增强和断点续跑。含可选三层灵感库管道（灵感库、跨书灵感聚合、更新灵感库）。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」或提供小说文本文件路径。
7.9k5150 tok idle · 3,049 in use - story-long-scanzenstory-ai/oh-story-claudecode
长篇网文扫榜。分析起点、番茄、晋江、七猫等平台排行榜与新书数据，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」「扫七猫新书」。
7.9k773 tok idle · 2,515 in use - story-long-writezenstory-ai/oh-story-claudecode
长篇网文规划与写作。支持只讨论结构、只写大纲或指定细纲，明确要求正文后再写章节。触发方式：/story-long-write、/写长篇、「帮我开书」「定设定」「出卷纲」「规划剧情」「写大纲」「补细纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。
7.9k1396 tok idle · 3,989 in use - story-reviewzenstory-ai/oh-story-claudecode
多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。
7.9k674 tok idle · 5,778 in use