Control Tabbit Browser in a task-isolated Playwright workspace; never switch browser backends.

MITAuto-check passedTesting & QA

Install Tabbit

skills CLI
$ npx skills add Tabbit-Browser/dsh-tabbit --skill tabbit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Tabbit-Browser/dsh-tabbit tabbit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Tabbit-Browser/dsh-tabbit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tabbit .claude/skills/tabbit && rm -rf skills-src

Use ~/.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/

Facts

Skill name
tabbit
GitHub stars
102
Token cost
~780 tokens
SKILL.md length
309 words
Files
6 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Control Tabbit Browser in a task-isolated Playwright workspace; never switch browser backends.

  • Tasks that involve Browser testing
  • SKILL.md covers Choose invocation, Persistent workspace and Load details only when needed
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Browser automation

What it does

Tabbit is an agent skill from Tabbit-Browser/dsh-tabbit. Control Tabbit Browser in a task-isolated Playwright workspace; never switch browser backends.

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/information-extraction.md`, `references/interaction-helpers.md` and `references/platform-invocation.md`).

It sits in Testing & QA, covering Browser testing and Browser automation. It works with Playwright and DeepSeek. The repository describes itself as: Tabbit Browser plugins for Deepseek Harness. The licence is MIT.

When your agent uses it

  • Tasks that involve Browser testing
  • Tasks that involve Browser automation

Example prompts

  • “/tabbit”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit c377e72. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tabbit loads about 780 tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 25 tokens; SKILL.md has 309 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~780
With references · SKILL.md plus every file in references/, read only if the agent opens them
~10k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from Tabbit-Browser/dsh-tabbit at commit c377e72, republished under its MIT licence (© Tabbit-Browser). 309 words, ~780 tokens.

Download SKILL.mdSave it as .claude/skills/tabbit/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
tabbit
description
Control Tabbit Browser in a task-isolated Playwright workspace; never switch browser backends.

Tabbit

Choose invocation

  • Set <launcher> to macOS/POSIX "$HOME/.local/bin/tabbit-cli" or Windows PowerShell & "$env:LOCALAPPDATA\Tabbit\LocalAgent\bin\tabbit-cli.exe". Do not assume tabbit-cli is on PATH.
  • If the command tool returns a reusable process handle and supports later stdin writes through pipe-backed stdin (non-PTY on Windows), run <launcher> persistent once. This is preferred.
  • Otherwise use <launcher> nodejs --task NAME immediately. Reuse the exact name for every command. Do not try persistent first. Read platform invocation for CMD and code input.

Persistent workspace

Send newline frame; wait for its response. Never detach or background the process. Commands renew a five-minute lease; expiry keeps tabs/group and stops animation.

Send bootstrap first with a concise display taskName. In code, navigate, act, verify with Playwright expect, then return proof:

json
{"op":"bootstrap","taskName":"Save-profile","requestId":"save-01","code":"await page.goto('https://example.test/profile',{waitUntil:'domcontentloaded'}); await page.getByRole('button',{name:'Save'}).click(); await expect(page.getByText('Saved')).toBeVisible(); return {verified: true};"}

If bootstrap returns queued, wait with {"op":"inspect","requestId":"save-01","waitMs":60000}; never resubmit.

Split only when the returned state changes the next decision. Later run frames name a path-safe requestId: {"op":"run","requestId":"save-02","code":"return await page.title();"} Send {"op":"tabs"} before bootstrap to take over an existing tab; include its exact tabId in claimTabIds. Inventory creates no task, Page, tab, or group. Later frames omit task identity.

The workspace owns only context.pages()/pages() and places every owned tab in its one group. Prefer semantic locators, bounded loops, same-program verification. Use status and result.value.

Before the final response, finish exactly once: send {"op":"finish"} in persistent mode or run <launcher> finish --task NAME otherwise. Plain finish retains tabs and the resumable group. Use {"op":"finish","keep":false} only for explicit discard or necessary cleanup. It closes only session-created tabs, never claimed or resumed tabs.

Load details only when needed

Do not preload these references:

© Tabbit-Browser, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/tabbit of Tabbit-Browser/dsh-tabbit.

  • SKILL.md
  • references/information-extraction.md
  • references/interaction-helpers.md
  • references/platform-invocation.md
  • references/playwright-recipes.md
  • references/runtime-recovery.md

Open the folder on GitHubat commit c377e72

Compare with similar skills

Tabbit 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.

Tabbit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tabbit this skillTabbit-Browser/dsh-tabbit102—~780Automated safety check: PassMIT
playwright-cli Browser Automationgithub/gh-aw5.3k23 repos~2.8kAutomated safety check: PassMIT
Playwright Skilllackeyjb/playwright-skill3.2k—~1.9kAutomated safety check: PassMIT
Anti Detect Browserantibrow/anti-detect-browser-skills914—~9.8kAutomated safety check: WarnMIT
Agenttinyfish-io/tinyfish-cookbook2.2k—~1.1kAutomated safety check: PassMIT
Measure Startup RequestsTriliumNext/Trilium38k—~1.5kAutomated safety check: PassAGPL-3.0

Similar skills

  • Official

    Drives a real browser from the command line with playwright-cli to open pages, interact, mock requests, save state and work with Playwright tests.

    5.3k GitHub starsUsed in 23 repos~2.8k tokens
    Testing & QAAuto-check passed
  • Playwright Skill

    lackeyjb/playwright-skill

    Complete browser automation with Playwright. An agent skill from lackeyjb/playwright-skill.

    3.2k GitHub stars~1.9k tokensUpdated 6 days ago
    Testing & QAAuto-check passed
  • Anti Detect Browser

    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…

    914 GitHub stars~9.8k tokensUpdated 1 mo ago
    Testing & QAAuto-check: warnings
  • Agent

    tinyfish-io/tinyfish-cookbook

    Default browser automation agent — click, fill forms, navigate, log in, and extract structured data from any website using a natural-language goal, or run the same task across multiple sites in…

    2.2k GitHub stars~1.1k tokensUpdated 5 days ago
    Testing & QAAuto-check passed
  • Measure Startup Requests

    TriliumNext/Trilium

    A skill your agent uses when measuring what the Trilium client loads at startup — "what loads at boot?", "did this change reduce the startup bundle?", "is <dependency lazy?", or any before/after…

    38k GitHub stars~1.5k tokensUpdated today
    Testing & QAAuto-check passed
  • Playwright MCP Browser Control

    Hainrixz/editor-pro-max

    Drives a live browser through the Playwright MCP server to navigate, inspect, fill forms and screenshot pages, with snapshot-first habits and output-size care.

    260 GitHub stars~2k tokensUpdated 6 mo ago
    Testing & QAAuto-check passed

Questions about Tabbit

What does Tabbit do?

Control Tabbit Browser in a task-isolated Playwright workspace; never switch browser backends. Tabbit is an agent skill from Tabbit-Browser/dsh-tabbit. Control Tabbit Browser in a task-isolated Playwright workspace; never switch browser backends.

When should I use Tabbit?

Tabbit fits situations like: tasks that involve Browser testing; tasks that involve Browser automation.

How do I install Tabbit in Claude Code?

Run `npx skills add Tabbit-Browser/dsh-tabbit --skill tabbit -a claude-code`. Or copy the skill folder (skills/tabbit in Tabbit-Browser/dsh-tabbit) into .claude/skills/tabbit in your project. Claude Code loads it when a task matches its description.

How do I install Tabbit in Codex?

Run `npx skills add Tabbit-Browser/dsh-tabbit --skill tabbit -a codex`. Or copy the skill folder (skills/tabbit in Tabbit-Browser/dsh-tabbit) into .agents/skills/tabbit in your project. Codex loads it when a task matches its description.

Can I use Tabbit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Tabbit-Browser/dsh-tabbit --skill tabbit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tabbit, .gemini/skills/tabbit, .github/skills/tabbit and .opencode/skills/tabbit in your project.

What does Tabbit need to run?

SKILL.md names no scripts, command-line tools or credentials: Tabbit is instructions for the agent only. Our summary lists: Node.js.

Does Tabbit access the network?

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.

Is Tabbit safe to install?

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.

What licence does Tabbit use?

Tabbit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tabbit use?

About 780 tokens (SKILL.md is roughly 3.1k 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 9.3k tokens, read only when the agent opens those files.

What are the alternatives to Tabbit?

Skills that share tags, products or a category with Tabbit: playwright-cli Browser Automation (github/gh-aw, 5.3k stars), Playwright Skill (lackeyjb/playwright-skill, 3.2k stars), Anti Detect Browser (antibrow/anti-detect-browser-skills, 914 stars) and Agent (tinyfish-io/tinyfish-cookbook, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tabbit?

Tabbit-Browser (a GitHub organization) maintains it in Tabbit-Browser/dsh-tabbit, which has 102 GitHub stars. The repository was last updated on September 10, 2026.

Source: Tabbit-Browser/dsh-tabbit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.