web-workflow-extraction

web-workflow-extraction is a skill for Claude Code, Codex from apexcheng/yingdao-xbot-ai-agent. It costs 52 tokens per session (1,180 once invoked), scanned A, original, MIT.

A browser investigation guide for documenting web操作 flows, XPath selectors, page states, and evidence that each step worked. XPath is a language for locating elements in a web page's document structure.

In plain words
What is it for?
Use it when someone explicitly needs a web process mapped, XPath selectors extracted or checked, and the results documented for later RPA development.
Why use it?
It reduces errors caused by stale, ambiguous, hidden, or incorrectly scoped selectors, including elements inside frames or pop-ups. It also makes clear that browser checks do not prove an RPA tool will work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it when someone explicitly needs a web process mapped, XPath selectors extracted or checked, and the results documented for later RPA development.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/apexcheng/yingdao-xbot-ai-agent/web-workflow-extraction
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add apexcheng/yingdao-xbot-ai-agent --skill web-workflow-extraction
Clone the repo
git clone --depth 1 https://github.com/apexcheng/yingdao-xbot-ai-agent

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for web-workflow-extraction

README.md
[![agentmods](https://agentmods.dev/badge/skills/apexcheng/yingdao-xbot-ai-agent/web-workflow-extraction/github.svg)](https://agentmods.dev/skills/apexcheng/yingdao-xbot-ai-agent/web-workflow-extraction)
Your own site
<a href="https://agentmods.dev/skills/apexcheng/yingdao-xbot-ai-agent/web-workflow-extraction"><img src="https://agentmods.dev/badge/skills/apexcheng/yingdao-xbot-ai-agent/web-workflow-extraction/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for web-workflow-extraction

Your own site · 80×15
<a href="https://agentmods.dev/skills/apexcheng/yingdao-xbot-ai-agent/web-workflow-extraction"><img src="https://agentmods.dev/badge/skills/apexcheng/yingdao-xbot-ai-agent/web-workflow-extraction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,180 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01180
Opus 5.5 $0.00021 $0.00472
Sonnet 5.5 $0.00010 $0.00236
Haiku 4.5 $0.00005 $0.00118

Measured 5d ago against content hash 6f1a72f4eb02, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

web-workflow-extraction scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

project-template/.agents/skills/web-workflow-extraction/SKILL.md · 42 lines

What it actually says

网页流程探测与 XPath 提取

触发与职责

  • 仅显式触发:用户明确要求网页操作流程探测、XPath 提取或验证时执行;普通网页开发不自动触发。
  • 只交付操作步骤、XPath、页面状态与验证证据文档,供后续影刀开发参考;不编写或修改 RPA 代码,不运行影刀或部署。
  • 以用户提供的业务目标、已确认的页面路径和当前环境为边界。可复用已有探测结果,但未经当前页面核实的选择器不能标为本次实测通过。

探测流程

  1. 确认起点:明确目标网页、入口、登录状态、操作范围、必要输入及预期完成状态。沿用已确认事项;影响业务结果或副作用的缺口先向用户确认。使用当前环境已授权的浏览器操作能力。
  2. 识别页面状态:确认目标元素位于主文档、iframe、弹窗还是新标签页;注意加载、遮挡、禁用状态及动态刷新。只检查当前步骤真正涉及的结构。
  3. 提取并检查定位:依据当前真实 DOM 提取 XPath,记录作用范围和命中数量;单目标必须唯一,多目标须符合预期范围。操作前检查目标语义及所需可操作状态(如可见、未被遮挡、可编辑或未禁用);定位原则见下方正式文档。
  4. 逐步实际操作:在用户授权范围内允许所有交互类型,包括点击、输入、提交、下载等,示例不是白名单。按业务顺序执行并记录必要输入;已有授权不重复询问,授权不明的步骤先确认。
  5. 验证闭环:按该步等待条件观察操作后的实际状态,对照成功判据留存证据;XPath 命中或动作调用成功都不能单独证明流程成功。可能重复提交的动作不为验证而重做;结果不明时先核实状态,不盲目重试。
  6. 处理阻塞:唯一性、可操作性或操作后状态不符合预期时,记录失败证据并暂停依赖该结果的步骤;页面变化时重新核实 DOM,不推断未观察到的结构或结果。

XPath 与影刀边界

  • 元素库复用、XPath 构造及相对查找原则统一见 browser.md。已有元素库名称可作为线索,不能冒充已提取的 XPath;无法取得 XPath 时标明缺口。
  • iframe 按外到内分别记录各层 iframe XPath 与框内目标 XPath,并在各自上下文核对匹配;调用契约见 iframe2-extension.md,不将跨文档路径拼成普通 XPath。
  • 业务取数、异步导出任务绑定及动态元素处理按需查 网页自动化实践;提取交互 XPath 不等于选择 XPath 读取业务数据,不额外扩展取数任务。
  • 探测 Excel/CSV 导出流程时,不为额外核验文件格式、表头或数据而下载真实报表;交付时提示“真实导出文件结构未验证,首次运行可能需适配”。用户明确要求实际下载或文件核验时除外。
  • 浏览器探测通过不代表影刀运行通过;标明验证环境及影刀兼容性未验证的范围,不为补充兼容性结论运行 RPA。

交付格式

先简述目标、起止状态和验证环境,再用简短步骤表交付;不倾倒整段 DOM。表中为格式示意:

步骤 前置状态、操作与输入 XPath / 作用范围 等待与成功判据 结果与证据
序号 当前状态 → 动作(必要输入) 实测 XPath;页面 / iframe / 相对根节点 等待条件;预期完成状态 状态;命中数、可操作性、操作后观察及证据引用
  • 证据使用必要的 DOM 摘要、截图引用、响应摘要或下载结果引用,注明对应步骤并脱敏;明确区分预期与实际观察,不记录凭据或敏感业务原文。
  • 结果状态:已实测(唯一性或多目标范围、可操作性及动作后状态均通过)、仅定位(已核实 XPath,未执行动作)、待验证(尚未完成检查,注明阻塞)、失败(检查或动作结果不符合预期)。静态材料不能冒充真实页面实测。
  • 仅补充影响复用的页面差异、未覆盖分支及阻塞;不将单次探测推断为所有页面或店铺通用。
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 42 lines · 52 tokens per session scan A 6f1a72f4eb02

Subscribe to this mod's changes

web-workflow-extraction is a skill published in the GitHub repository apexcheng/yingdao-xbot-ai-agent (42 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,180 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.

Related

Other skills, from other repositories

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.

browser-use/browser-use · 57 tokens

browse

Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase…

browserbase/stagehand · 109 tokens

opencli-autofix

Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.

jackwener/OpenCLI · 61 tokens

skill-body

Call help() or help("page.click") to print signatures and uncommon options of APIs named below; it prints by itself, so do not wrap it in console.log. For installation or connection problems, read references/install.md in the ego-browser Skill directory.

citrolabs/ego-lite · 0 tokens

moli-webfetch

Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…

lexmount/moli · 90 tokens

pinchtab

Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…

pinchtab/pinchtab · 94 tokens