Routes a web request through the cheapest tier that can finish it, from headless extraction with WAF bypass up to a real stealth or signed-in browser, with screenshots as proof.
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add code-yeongyu/oh-my-openagent --skill ultimate-browsing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install code-yeongyu/oh-my-openagent ultimate-browsing --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/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/shared-skills/skills/ultimate-browsing .claude/skills/ultimate-browsing && 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 "ultimate-browsing" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/shared-skills/skills/ultimate-browsing into .claude/skills/ultimate-browsing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultimate-browsing", 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/code-yeongyu/oh-my-openagent/tree/dev/packages/shared-skills/skills/ultimate-browsingType 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 code-yeongyu/oh-my-openagent --skill ultimate-browsing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install code-yeongyu/oh-my-openagent ultimate-browsing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/shared-skills/skills/ultimate-browsing .agents/skills/ultimate-browsing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ultimate-browsing" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/shared-skills/skills/ultimate-browsing into .agents/skills/ultimate-browsing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultimate-browsing", 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 code-yeongyu/oh-my-openagent --skill ultimate-browsing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install code-yeongyu/oh-my-openagent ultimate-browsing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/shared-skills/skills/ultimate-browsing .cursor/skills/ultimate-browsing && 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 "ultimate-browsing" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/shared-skills/skills/ultimate-browsing into .cursor/skills/ultimate-browsing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultimate-browsing", 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/code-yeongyu/oh-my-openagent.git --path packages/shared-skills/skills/ultimate-browsing--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 code-yeongyu/oh-my-openagent --skill ultimate-browsing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install code-yeongyu/oh-my-openagent ultimate-browsing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/shared-skills/skills/ultimate-browsing .gemini/skills/ultimate-browsing && 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 "ultimate-browsing" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/shared-skills/skills/ultimate-browsing into .gemini/skills/ultimate-browsing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultimate-browsing", 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 code-yeongyu/oh-my-openagent ultimate-browsingInstalls 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 code-yeongyu/oh-my-openagent --skill ultimate-browsing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/shared-skills/skills/ultimate-browsing .github/skills/ultimate-browsing && 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 "ultimate-browsing" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/shared-skills/skills/ultimate-browsing into .github/skills/ultimate-browsing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultimate-browsing", 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 code-yeongyu/oh-my-openagent --skill ultimate-browsing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install code-yeongyu/oh-my-openagent ultimate-browsing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/shared-skills/skills/ultimate-browsing .opencode/skills/ultimate-browsing && 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 "ultimate-browsing" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/shared-skills/skills/ultimate-browsing into .opencode/skills/ultimate-browsing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultimate-browsing", 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.
ultimate-browsingRoutes a web request through the cheapest tier that can finish it, from headless extraction with WAF bypass up to a real stealth or signed-in browser, with screenshots as proof.
This skill covers everything a plain fetch cannot finish: a page that renders in JavaScript, a click or a form, a screenshot, a login that must persist across pages, or a host that blocks generic fetchers with a WAF or a 403. A mandatory routing phase picks the cheapest tier first and climbs only when it cannot do the job: Tier 1 is headless extraction with WAF bypass, Tier 1.5 reaches for platform-native APIs, especially on Chinese platforms, and Tier 2 opens a real browser, either an owned stealth-mode engine the code launches or the user's own already signed-in browser.
Tier 1, called insane-search, is roughly ten times faster than spinning up a browser and handles most blocked-page requests through curl_cffi TLS impersonation, yt-dlp across more than a thousand sites, official public APIs, mobile URL transforms, provenance-tagged Wayback and archive.today snapshots, a key-gated Jina Reader, and a Playwright real-Chrome fallback, with the engine living inside the skill as a Python module invoked with a target URL and options such as a CSS selector for positive-proof validation or a device type. A result pulled from an archive snapshot is explicitly a dated copy and must be reported with its snapshot timestamp, never presented as the live page.
The skill ships its own engine code, including fetch-chain, referer and surrogate-archive modules plus Playwright templates for desktop and mobile Chrome, and an ATTRIBUTION.md file, with a reference file for each tier to read before acting.
Read from SKILL.md and the folder at commit cbd7dd2. 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.
Ships 1 file in scripts/ (Python and JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3yt-dlpcurlghFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
r.jina.aiv2ex.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
JINA_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Tiered Web Browsing and Scraping loads about 2.7k tokens when it runs, and up to ~25k if it reads all its reference files. Until then it costs about 75 tokens; SKILL.md has 830 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 patterns that need a careful read before installing.
n3 scripts/extract_cookies.py --browser chrome --domain youtube.com --output ~/.local/state/omo-cookies/youtube.cookies.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); the scripts in this folder are not scanned.
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 830 words (~2,722 tokens).
“Web access for everything a plain fetch cannot finish: a page that renders in JS, a click or a form, a screenshot, a login that must persist across pages, or a host that blocks generic fetchers (WAF / 403 /…”
SKILL.md and 64 other files (scripts, references) in packages/shared-skills/skills/ultimate-browsing of code-yeongyu/oh-my-openagent.
Open the folder on GitHubat commit cbd7dd2
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in code-yeongyu/oh-my-openagent, which our catalogue first saw on October 7, 2026.
Tiered Web Browsing and Scraping 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 |
|---|---|---|---|---|---|---|
| Tiered Web Browsing and Scraping this skillcode-yeongyu/oh-my-openagent | 70k | — | ~2.7k | Automated safety check: Warn | Custom licence | |
| Anti Detect Browserantibrow/anti-detect-browser-skills | 914 | — | ~9.8k | Automated safety check: Warn | MIT | |
| Skyvern Browser AutomationSkyvern-AI/skyvern | 23k | — | ~2.9k | Automated safety check: Pass | AGPL-3.0 | |
| Skyvern Browser AutomationSkyvern-AI/skyvern | 23k | — | ~1.9k | Automated safety check: Pass | AGPL-3.0 | |
| Camofox Browserredf0x1/camofox-browser | 410 | — | ~4.6k | Automated safety check: Pass | MIT | |
| Playwright Bowserdisler/bowser | 265 | — | ~1.1k | Automated safety check: Notes | None |
antibrow/anti-detect-browser-skills
Drive Chromium from standard Playwright APIs with a real-device fingerprint applied in the kernel, one persistent isolated profile per identity, and a per-profile proxy whose exit IP sets timezone…
Skyvern-AI/skyvern
Picks the right Skyvern CLI command for a web task, from quick yes/no checks to reusable multi-page workflows, instead of falling back to plain page fetching.
Skyvern-AI/skyvern
Automates websites with Skyvern's AI browser agent to fill forms, extract data, download files, log in and run multi-step workflows through SDKs, REST, MCP or a CLI.
redf0x1/camofox-browser
Anti-detection browser automation for AI agents. An agent skill from redf0x1/camofox-browser.
disler/bowser
Headless browser automation using Playwright CLI. An agent skill from disler/bowser.
alirezarezvani/claude-skills
A skill your agent uses when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows.
code-yeongyu/oh-my-openagent
Searches and rewrites code by syntax-tree shape across 25 languages with ast-grep, for codemods, structural queries and YAML lint rules, using a Python wrapper script.
code-yeongyu/oh-my-openagent
Drives a real browser through the omowright library, either the user's own signed-in browser or a separate browser the code launches, for forms, QA, screenshots and scraping.
code-yeongyu/oh-my-openagent
Tests the omo Codex plugin in an isolated CODEX_HOME with a local mock model, proving hooks fired through app-server notifications without touching ~/.codex.
code-yeongyu/oh-my-openagent
Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.
code-yeongyu/oh-my-openagent
Detects which languages a project uses, installs the matching language server, writes its config and checks it with a real call so diagnostics and go-to-definition work.
code-yeongyu/oh-my-openagent
Tests the opencode coding agent itself: its CLI, server, plugin hooks and events, the terminal UI under tmux, and its SQLite session database, using tested helper scripts.
Works with
Routes a web request through the cheapest tier that can finish it, from headless extraction with WAF bypass up to a real stealth or signed-in browser, with screenshots as proof. This skill covers everything a plain fetch cannot finish: a page that renders in JavaScript, a click or a form, a screenshot, a login that must persist across pages, or a host that blocks generic fetchers with a WAF or a 403.5 reaches for platform-native APIs, especially on Chinese platforms, and Tier 2 opens a real browser, either an owned stealth-mode engine the code launches or the user's own already signed-in browser.
Tiered Web Browsing and Scraping fits situations like: extracting content from a page blocked by a WAF or Cloudflare; rendering and interacting with a page that needs JavaScript, a click or a form; taking a screenshot as provenance for a research or browsing task; reaching a page that needs a persistent login across requests.
Run `npx skills add code-yeongyu/oh-my-openagent --skill ultimate-browsing -a claude-code`. Or copy the skill folder (packages/shared-skills/skills/ultimate-browsing in code-yeongyu/oh-my-openagent) into .claude/skills/ultimate-browsing in your project. Claude Code loads it when a task matches its description.
Run `npx skills add code-yeongyu/oh-my-openagent --skill ultimate-browsing -a codex`. Or copy the skill folder (packages/shared-skills/skills/ultimate-browsing in code-yeongyu/oh-my-openagent) into .agents/skills/ultimate-browsing 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 code-yeongyu/oh-my-openagent --skill ultimate-browsing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ultimate-browsing, .gemini/skills/ultimate-browsing, .github/skills/ultimate-browsing and .opencode/skills/ultimate-browsing in your project.
Going by SKILL.md and its folder, Tiered Web Browsing and Scraping needs Python and JavaScript for the scripts in its folder, the command-line tools its instructions call (python3, yt-dlp, curl and gh) and credentials named JINA_API_KEY. Our summary lists: Python with curl_cffi and yt-dlp for the headless extraction tier; Playwright with a real or stealth Chrome build for the browser tier; Optionally a Jina Reader API key.
SKILL.md names 2 domains. In commands or code: r.jina.ai and v2ex.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md flagged 1 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Tiered Web Browsing and Scraping has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 22k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Tiered Web Browsing and Scraping: Anti Detect Browser (antibrow/anti-detect-browser-skills, 914 stars), Skyvern Browser Automation (Skyvern-AI/skyvern, 23k stars), Skyvern Browser Automation (Skyvern-AI/skyvern, 23k stars) and Camofox Browser (redf0x1/camofox-browser, 410 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
code-yeongyu (a GitHub user) maintains it in code-yeongyu/oh-my-openagent, which has 69,850 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on October 7, 2026.
Source: code-yeongyu/oh-my-openagent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
