Browser Automation Edge Cases
aden-hive/hive
Step-by-step procedure for debugging browser automation failures on complex sites such as LinkedIn, Twitter/X, single-page apps and Shadow DOM pages.
Automates a dedicated, logged-in Chrome instance per profile without ever closing the user's own open tabs or browser windows.
$ npx skills add glebis/claude-skills --skill browser-mate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install glebis/claude-skills browser-mate --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/glebis/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/browser-mate .claude/skills/browser-mate && 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 "browser-mate" agent skill from https://github.com/glebis/claude-skills/tree/main/browser-mate into .claude/skills/browser-mate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-mate", 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/glebis/claude-skills/tree/main/browser-mateType 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 glebis/claude-skills --skill browser-mate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install glebis/claude-skills browser-mate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/browser-mate .agents/skills/browser-mate && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "browser-mate" agent skill from https://github.com/glebis/claude-skills/tree/main/browser-mate into .agents/skills/browser-mate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-mate", 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 glebis/claude-skills --skill browser-mate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install glebis/claude-skills browser-mate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/browser-mate .cursor/skills/browser-mate && 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 "browser-mate" agent skill from https://github.com/glebis/claude-skills/tree/main/browser-mate into .cursor/skills/browser-mate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-mate", 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/glebis/claude-skills.git --path browser-mate--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 glebis/claude-skills --skill browser-mate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install glebis/claude-skills browser-mate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/browser-mate .gemini/skills/browser-mate && 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 "browser-mate" agent skill from https://github.com/glebis/claude-skills/tree/main/browser-mate into .gemini/skills/browser-mate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-mate", 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 glebis/claude-skills browser-mateInstalls 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 glebis/claude-skills --skill browser-mate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/browser-mate .github/skills/browser-mate && 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 "browser-mate" agent skill from https://github.com/glebis/claude-skills/tree/main/browser-mate into .github/skills/browser-mate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-mate", 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 glebis/claude-skills --skill browser-mate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install glebis/claude-skills browser-mate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/browser-mate .opencode/skills/browser-mate && 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 "browser-mate" agent skill from https://github.com/glebis/claude-skills/tree/main/browser-mate into .opencode/skills/browser-mate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-mate", 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.
browser-mateAutomates a dedicated, logged-in Chrome instance per profile without ever closing the user's own open tabs or browser windows.
This skill solves a specific conflict: driving Chrome through a remote-debugging session normally means launching it with that flag on, which a sibling skill achieves by quitting the user's Chrome first. This skill instead launches its own dedicated Chrome instance with a separate profile folder and port, which Chrome allows to run alongside the user's main browser without any quitting.
One rule governs the whole skill: it never quits or kills any browser, and its stop command sends a termination signal only to a process matched by both its own dedicated profile folder and its own debug port. Each named profile keeps its own login state after a one-time manual sign-in, since the skill cannot and does not enter passwords itself, and the debug port only listens locally, with a note that this kind of connection carries no authentication of its own for whoever can reach it on that machine.
Read from SKILL.md and the folder at commit 7524dff. 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), which the agent can run.
Shell commands in SKILL.md call:
python3osascriptFrom 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:
chatgpt.comFrom 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.
Non-Destructive Chrome Automation loads about 973 tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 157 tokens; SKILL.md has 305 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); the scripts in this folder are not scanned.
The full file from glebis/claude-skills at commit 7524dff, republished under its MIT licence (© glebis). 305 words, ~973 tokens.
.claude/skills/browser-mate/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Non-destructive Chrome automation. The problem it solves: to attach a CDP/agent-browser
session, Chrome must run with --remote-debugging-port. The real-browser skill achieves
this by quitting Chrome Beta first, destroying the user's open tabs. browser-mate
instead runs a dedicated debug Chrome instance (its own --user-data-dir + port) that
coexists with the user's main browser — Chrome permits concurrent instances when the
data dirs differ, so no quit is needed.
Never quit, pkill, or osascript quit any browser. The skill only ever launches a
new dedicated instance or reuses an existing one. The single stop path sends SIGTERM only
to a process matched by BOTH our dedicated user_data_dir AND our debug port — never the
user's browser.
# Ensure a profile's debug Chrome is up (launch or reuse); prints the PORT on stdout
PORT=$(python3 scripts/browser.py chatgpt)
# Then drive it with agent-browser (always pass --cdp $PORT). See references/agent-browser.md
SID=$(LC_ALL=C tr -dc 'a-z0-9' < /dev/urandom | head -c 6)
agent-browser --cdp $PORT --session $SID open "https://chatgpt.com/"
agent-browser --cdp $PORT --session $SID snapshot -iOther subcommands:
python3 scripts/browser.py list # configured profiles
python3 scripts/browser.py status [profile] # up/down
python3 scripts/browser.py stop chatgpt # SIGTERM OUR instance only (graceful)For the full agent-browser command set (click, fill, upload, screenshot, reliability,
upgrade gotchas), read references/agent-browser.md.
Config: ~/.config/browser-mate/profiles.json (auto-created from assets/profiles.example.json
on first run). Each profile:
{ "default": "automation",
"profiles": {
"automation": { "binary": "<chrome binary>", "user_data_dir": "~/.browser-mate/automation", "port": 9222 },
"chatgpt": { "binary": "<chrome binary>", "user_data_dir": "~/.browser-mate/chatgpt", "port": 9223, "default_url": "https://chatgpt.com/" }
} }user_data_dir
(the launcher validates uniqueness and refuses dirs that point at the user's real Chrome
profile).Cannot enter passwords (and must not). For a first-time login, launch the profile, then ask
the user to log in manually in that window once; the session persists in the profile's
user_data_dir for all future runs.
127.0.0.1 (Chrome default). CDP has no auth
— anyone local can drive it. Use on trusted machines; never pass --remote-debugging-address.user_data_dir must never be the user's real Chrome
profile (~/Library/Application Support/Google/Chrome*) — the launcher refuses these.real-browser's launch step; interaction still uses agent-browser.© glebis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (scripts, references, assets) in browser-mate of glebis/claude-skills.
Open the folder on GitHubat commit 7524dff
Non-Destructive Chrome Automation 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 |
|---|---|---|---|---|---|---|
| Non-Destructive Chrome Automation this skillglebis/claude-skills | 388 | — | ~973 | Automated safety check: Pass | MIT | |
| Browser Automation Edge Casesaden-hive/hive | 11k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Browser MCP Agentantibrow/anti-detect-browser-skills | 914 | 1 repos | ~4.2k | Automated safety check: Warn | MIT | |
| Altic Studioaltic-dev/altic-mcp | 172 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Unicliolo-dot-io/Uni-CLI | 273 | — | ~3.8k | Automated safety check: Notes | Apache-2.0 | |
| Drive Screencoleam00/skills | 670 | — | ~5.4k | Automated safety check: Pass | MIT |
aden-hive/hive
Step-by-step procedure for debugging browser automation failures on complex sites such as LinkedIn, Twitter/X, single-page apps and Shadow DOM pages.
antibrow/anti-detect-browser-skills
Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so…
altic-dev/altic-mcp
macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools.
olo-dot-io/Uni-CLI
Comprehensive guide to Uni-CLI — the open Agent-Computer Interface runtime for real software.
coleam00/skills
Take real control of the desktop - list and focus windows, type, paste, click, scroll, and screenshot - on Windows, macOS or Linux, and drive other coding-agent sessions running in terminals.
brightdata/skills
Bright Data MCP handles ALL web data operations. An agent skill from brightdata/skills.
glebis/claude-skills
Runs a human-first workflow for labeling PII spans in a transcript, then scores inter-annotator agreement and drafts an adjudicated gold set.
glebis/claude-skills
This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API.
glebis/claude-skills
This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric…
glebis/claude-skills
Generates a self-contained HTML presentation with article and slides modes, ElevenLabs voiceover narration and optional GPT Image 2 illustrations.
glebis/claude-skills
Writes fictional but realistic coaching or therapy session transcripts for evals, demos and few-shot examples, in several modalities and export formats.
glebis/claude-skills
Walks through Goldratt's Five Focusing Steps to find the real bottleneck in your work, then recommends one automation aimed at it and a list of what not to automate.
Categories
Automates a dedicated, logged-in Chrome instance per profile without ever closing the user's own open tabs or browser windows. This skill solves a specific conflict: driving Chrome through a remote-debugging session normally means launching it with that flag on, which a sibling skill achieves by quitting the user's Chrome first. This skill instead launches its own dedicated Chrome instance with a separate profile folder and port, which Chrome allows to run alongside the user's main browser without any quitting.
Non-Destructive Chrome Automation fits situations like: automating an authenticated site like ChatGPT or LinkedIn without closing your tabs; running a browser automation task that needs a persistent logged-in session; keeping a dedicated automation browser profile separate from your daily browsing.
Run `npx skills add glebis/claude-skills --skill browser-mate -a claude-code`. Or copy the skill folder (browser-mate in glebis/claude-skills) into .claude/skills/browser-mate in your project. Claude Code loads it when a task matches its description.
Run `npx skills add glebis/claude-skills --skill browser-mate -a codex`. Or copy the skill folder (browser-mate in glebis/claude-skills) into .agents/skills/browser-mate 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 glebis/claude-skills --skill browser-mate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/browser-mate, .gemini/skills/browser-mate, .github/skills/browser-mate and .opencode/skills/browser-mate in your project.
Going by SKILL.md and its folder, Non-Destructive Chrome Automation needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and osascript). Our summary lists: macOS; The agent-browser CLI; Python 3 to run the bundled browser script.
SKILL.md names 1 domain. In commands or code: chatgpt.com; the agent is likely to contact it when it follows the instructions. 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Non-Destructive Chrome Automation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 973 tokens (SKILL.md is roughly 3.9k 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 973 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Non-Destructive Chrome Automation: Browser Automation Edge Cases (aden-hive/hive, 11k stars), Browser MCP Agent (antibrow/anti-detect-browser-skills, 914 stars), Altic Studio (altic-dev/altic-mcp, 172 stars) and Unicli (olo-dot-io/Uni-CLI, 273 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
glebis (a GitHub user) maintains it in glebis/claude-skills, which has 388 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on September 26, 2026.
Source: glebis/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.