当你需要开发/排查 HTTP 抓取、SSRF、Playwright 受控浏览器、本地字体增强截图，或判断 webfetch 与 browser 工作流如何选型时使用。
$ npx skills add xrkseek/XRK-AGT --skill xrk-crawl -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install xrkseek/XRK-AGT xrk-crawl --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/xrkseek/XRK-AGT.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/xrk-crawl .claude/skills/xrk-crawl && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "xrk-crawl" agent skill from https://github.com/xrkseek/XRK-AGT/tree/main/.cursor/skills/xrk-crawl into .claude/skills/xrk-crawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xrk-crawl", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/xrkseek/XRK-AGT/tree/main/.cursor/skills/xrk-crawlType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add xrkseek/XRK-AGT --skill xrk-crawl -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install xrkseek/XRK-AGT xrk-crawl --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xrkseek/XRK-AGT.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/xrk-crawl .agents/skills/xrk-crawl && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "xrk-crawl" agent skill from https://github.com/xrkseek/XRK-AGT/tree/main/.cursor/skills/xrk-crawl into .agents/skills/xrk-crawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xrk-crawl", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xrkseek/XRK-AGT --skill xrk-crawl -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install xrkseek/XRK-AGT xrk-crawl --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xrkseek/XRK-AGT.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/xrk-crawl .cursor/skills/xrk-crawl && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "xrk-crawl" agent skill from https://github.com/xrkseek/XRK-AGT/tree/main/.cursor/skills/xrk-crawl into .cursor/skills/xrk-crawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xrk-crawl", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/xrkseek/XRK-AGT.git --path .cursor/skills/xrk-crawl--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add xrkseek/XRK-AGT --skill xrk-crawl -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install xrkseek/XRK-AGT xrk-crawl --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xrkseek/XRK-AGT.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/xrk-crawl .gemini/skills/xrk-crawl && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "xrk-crawl" agent skill from https://github.com/xrkseek/XRK-AGT/tree/main/.cursor/skills/xrk-crawl into .gemini/skills/xrk-crawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xrk-crawl", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install xrkseek/XRK-AGT xrk-crawlInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add xrkseek/XRK-AGT --skill xrk-crawl -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/xrkseek/XRK-AGT.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/xrk-crawl .github/skills/xrk-crawl && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "xrk-crawl" agent skill from https://github.com/xrkseek/XRK-AGT/tree/main/.cursor/skills/xrk-crawl into .github/skills/xrk-crawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xrk-crawl", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xrkseek/XRK-AGT --skill xrk-crawl -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install xrkseek/XRK-AGT xrk-crawl --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xrkseek/XRK-AGT.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/xrk-crawl .opencode/skills/xrk-crawl && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "xrk-crawl" agent skill from https://github.com/xrkseek/XRK-AGT/tree/main/.cursor/skills/xrk-crawl into .opencode/skills/xrk-crawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xrk-crawl", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
xrk-crawl当你需要开发/排查 HTTP 抓取、SSRF、Playwright 受控浏览器、本地字体增强截图，或判断 webfetch 与 browser 工作流如何选型时使用。
Xrk Crawl is an agent skill from xrkseek/XRK-AGT. 当你需要开发/排查 HTTP 抓取、SSRF、Playwright 受控浏览器、本地字体增强截图，或判断 webfetch 与 browser 工作流如何选型时使用。
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Security, covering Web application vulnerabilities, Browser testing and Web scraping. It works with Playwright. The repository describes itself as: 这是基于多语言所搭建的基于web，工作流，新型算法组件的智能体. The licence is MIT.
Read from SKILL.md and the folder at commit 63f004e. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Xrk Crawl loads about 1.3k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 244 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from xrkseek/XRK-AGT at commit 63f004e, republished under its MIT licence (© xrkseek). 244 words, ~1,271 tokens.
.claude/skills/xrk-crawl/SKILL.md (or your agent's skills folder).src/infrastructure/crawl/index.js — 插件、workflow、HTTP 只从这里 import（#infrastructure/crawl/index.js）。
import {
fetchWithPolicy,
runWebFetch,
buildWebFetchRuntime,
assertUrlSafeForFetch,
PlaywrightAgentSession,
launchOptionsFromBrowserRuntime,
toPlaywrightAgentLaunchOptions,
createLocalFontScreenshotHelper,
DEFAULT_DEVICE_SCALE_FACTOR,
DOM_TWEAK_LABEL_COLON_HALF,
} from '#infrastructure/crawl/index.js'fetchWithPolicy 实现在 #utils/fetch-with-retry.js，由 crawl 门面 re-export。
| 场景 | 能力 | 实现文件（均在 src/infrastructure/crawl/） |
|---|---|---|
| 简单 API / 无需 JS 渲染 | fetchWithPolicy | #utils/fetch-with-retry.js |
| 正文提取、Readability、Firecrawl | runWebFetch | web-fetch-executor.js |
| 开放域检索 | runWebSearch | web-search-executor.js + web-search-registry.js |
| 零配置免费检索 | runParallelFreeSearch | web-search-parallel-free.js + web-search-mcp-client.js |
| 浏览器运行时 | buildBrowserRuntime | crawl-config.js（ai-workflow.crawl + renderer.playwright） |
| runtime → launch | toPlaywrightAgentLaunchOptions / launchOptionsFromBrowserRuntime | crawl-config.js |
MCP web_fetch / web_search | workflow/web.js | 内部用 crawl |
| JS 渲染、交互、截图 | PlaywrightAgentSession | playwright-session.js |
| MCP 受控浏览器 | workflow/browser.js | browser_* 工具 |
| 截图字体/样式与线上一致 | createLocalFontScreenshotHelper | page-screenshot-enhance.js |
选型：HTTP 能拿正文 → runWebFetch；要渲染或 PNG → Playwright。
业务/插件禁止手抄 executablePath / launchArgs / 只挑部分字段。统一：
// 推荐：配置链 + 业务覆盖（viewport / DPR）
await PlaywrightAgentSession.using(
launchOptionsFromBrowserRuntime({ deviceScaleFactor: 3, viewport: { width: 520, height: 960 } }),
async (session) => { /* ... */ }
)
// 已有 runtime 对象时
const rt = buildBrowserRuntime()
await PlaywrightAgentSession.launch(toPlaywrightAgentLaunchOptions(rt))映射会带上：navigationTimeoutMs、ssrfPolicy、closeTimeoutMs、pageCrashRetries、opTimeoutMs、系统浏览器路径、launchArgs。
稳定性（底层默认，插件勿再造）：
| 能力 | 说明 |
|---|---|
using(..., { crashRetries: 1 }) | 整轮 Target/Page crashed → 换新浏览器再跑 |
goto / gotoAndCapture | 页崩溃 → recreatePage 后重试（后者含重新导航） |
session.close() | softClosePlaywrightTree（AbortSignal.timeout 竞速），超时不卡死 |
waitUntil | 经 normalizePlaywrightWaitUntil：load（默认）/domcontentloaded/networkidle/commit；非法值回落 load。官方 DISCOURAGED networkidle，优先 load 或交互后断言就绪 |
反模式：同一重型（高 DPR + 字体）会话连开多档位 goto；在插件里硬编码 Chrome 路径 / soft-close / 崩溃正则；默认依赖 networkidle。
ssrf-policy.js：allowlist、legacy IP、DNS pinning、createPinnedDispatcherssrf-guard.js：对外 re-export assertUrlSafeForFetchfetch-guard.js：fetchWithSsrFGuard（每跳 pin DNS + 重定向环）browser-navigation-guard.js：gotoWithNavigationGuard（page.route 拦截）| 方法 | 说明 |
|---|---|
roleSnapshot() | ARIA ref 树 + storeRoleRefsOnPage |
runAct({ kind, ref, ... }) | 含 batch、scrollIntoView、fill fields |
listTabs / newTab / closeTab / focusTab | 多标签 |
getConsoleMessages / getNetworkRequests | 页面观测 |
armDialog / respondDialog | 弹窗 |
goto(url) | gotoWithNavigationGuard + 交互后 SSRF 复检 |
src/infrastructure/crawl/
index.js
ssrf-*.js / fetch-guard.js / browser-navigation-guard.js
playwright-session.js / pw-*.js / act-policy.js
web-fetch-*.js / web-search-*.js / crawl-config.js
page-screenshot-enhance.jsSchema：core/system-Core/commonconfig/system.js → ai-workflow.fields.crawl
默认模板：config/default_config/ai-workflow.yaml → crawl:
运行时数据：data/server_bots/{port}/ai-workflow.yaml → crawl.webFetch / crawl.webSearch / crawl.browser
优先级：调用方 overrides > ai-workflow.crawl > renderer.playwright（browser 启动）> 默认
单一实现：crawl-config.js — resolveWebFetchRuntime / resolveWebSearchConfig / buildBrowserRuntime
禁止在 crawl 模块内读取 process.env 做业务配置；凭据与参数一律写 data/server_bots/{port}/ai-workflow.yaml → crawl.*。
core/system-Core/workflow/web.js → web_fetch / web_searchcore/system-Core/workflow/browser.js → 全量 browser_*（见 docs/system-core.md）src/infrastructure/crawl/ 内并在 index.js 导出，不要在 Core 内复制一份。launch({ browserType: rt.browserType, ... }) 手抄字段——会丢掉 nav 超时与 SSRF。launchOptionsFromBrowserRuntime()；高清截图另开会话并尽量 一次 goto。fetch-with-retry.js、web-fetch-executor.js 已用全局 fetch + AbortSignal.timeout；扩展时沿用，禁止 node-fetch。toBase64() / Uint8Array.fromBase64()，勿 toString('base64')。Error.isError / normalizeError（skill xrk-node-runtime）。docs/system-core.md（web / browser 章节）core/system-Core/plugin/ 下未写入 .gitignore 白名单的 .js 仍会加载，但不计入框架 baseline© xrkseek, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .cursor/skills/xrk-crawl of xrkseek/XRK-AGT.
Open the folder on GitHubat commit 63f004e
Xrk Crawl next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Xrk Crawl this skillxrkseek/XRK-AGT | 138 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Authenticated Session Acquisitiontransilienceai/communitytools | 563 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Extractactionbook/actionbook | 1.6k | 2 repos | ~3.4k | Automated safety check: Pass | Apache-2.0 | |
| Brightdata Proxybrightdata/skills | 264 | — | ~5.1k | Automated safety check: Pass | MIT | |
| Open BrowserJasonHonKL/Openbrowser | 114 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Playwright Bowserdisler/bowser | 265 | — | ~1.1k | Automated safety check: Notes | None |
transilienceai/communitytools
Acquire an authenticated session THROUGH MFA/OTP on an in-scope target and emit a reusable session artifact (Playwright storageState + Bearer) so executors can test the post-auth attack surface.
actionbook/actionbook
Extract structured data from websites and produce an executable Playwright script plus extracted data.
brightdata/skills
Generate working code that routes HTTP requests through Bright Data proxy networks (Datacenter, ISP, Residential, Mobile) and help users decide which network and IP pool type to use (shared pool…
JasonHonKL/Openbrowser
A skill your agent uses whenever the task involves browsing web pages, extracting page content, clicking forms, or completing web workflows.
disler/bowser
Headless browser automation using Playwright CLI. An agent skill from disler/bowser.
sanity-io/sanity
A skill your agent uses when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling…
xrkseek/XRK-AGT
Produce immersive vertical short videos (口播/科普/产品讲解) without AI-slop aesthetics.
xrkseek/XRK-AGT
当你需要开发或排查 HTTP API（core//http/.js）、理解 HttpApi 基类、HttpApiLoader、业务层约定时使用。
xrkseek/XRK-AGT
编写或审查 core/src 代码时，确保使用 Node 26 稳定 API，禁止旧写法（fetch/exec/错误/二进制）。AI 改 Core 前必读。
xrkseek/XRK-AGT
在 GitHub 搜索成熟开源实现、对比方案、读 issue/PR 时使用。架构选型、unfamiliar 领域、找业界最佳实践时主动调用。
xrkseek/XRK-AGT
当你需要配置/新增/排查 LLM 提供商（OpenAI/Azure/Gemini/Anthropic/Ollama/各类兼容网关）时使用；确保 YAML/Schema/代码一致。
xrkseek/XRK-AGT
编写或审查 core//www 静态页、校园 WebView 兼容、HttpResponse 前端解包时使用。Core www 走浏览器兼容层（xrk-www-compat）。含零配置静态与有 sign.json（纯静态/产物/反代，sign↔server 合并）挂载。
Works with
Categories
当你需要开发/排查 HTTP 抓取、SSRF、Playwright 受控浏览器、本地字体增强截图，或判断 webfetch 与 browser 工作流如何选型时使用。. Xrk Crawl is an agent skill from xrkseek/XRK-AGT.
Xrk Crawl fits situations like: tasks that involve Web application vulnerabilities; tasks that involve Browser testing; tasks that involve Web scraping.
Run `npx skills add xrkseek/XRK-AGT --skill xrk-crawl -a claude-code`. Or copy the skill folder (.cursor/skills/xrk-crawl in xrkseek/XRK-AGT) into .claude/skills/xrk-crawl in your project. Claude Code loads it when a task matches its description.
Run `npx skills add xrkseek/XRK-AGT --skill xrk-crawl -a codex`. Or copy the skill folder (.cursor/skills/xrk-crawl in xrkseek/XRK-AGT) into .agents/skills/xrk-crawl in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xrkseek/XRK-AGT --skill xrk-crawl -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xrk-crawl, .gemini/skills/xrk-crawl, .github/skills/xrk-crawl and .opencode/skills/xrk-crawl in your project.
SKILL.md names no scripts, command-line tools or credentials: Xrk Crawl is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Xrk Crawl is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Xrk Crawl: Authenticated Session Acquisition (transilienceai/communitytools, 563 stars), Extract (actionbook/actionbook, 1.6k stars), Brightdata Proxy (brightdata/skills, 264 stars) and Open Browser (JasonHonKL/Openbrowser, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
xrkseek (a GitHub user) maintains it in xrkseek/XRK-AGT, which has 138 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 1, 2026.
Source: xrkseek/XRK-AGT on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
