New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

OpenWork Desktop CDP Driver

by different-ai in different-ai/openwork

Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.

Custom licenceAuto-check passedTesting & QA

Install OpenWork Desktop CDP Driver

skills CLI
$ npx skills add different-ai/openwork --skill drive-desktop-cdp -a claude-code

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

GitHub CLI
$ gh skill install different-ai/openwork drive-desktop-cdp --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/different-ai/openwork.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/drive-desktop-cdp .claude/skills/drive-desktop-cdp && 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
drive-desktop-cdp
GitHub stars
24k
Token cost
~465 tokens
SKILL.md length
128 words
Files
2 (incl. scripts)
Skills in repo
33
Repo updated
First seen
Licence
Custom licence

At a glance

Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.

  • Checking a UI change in the OpenWork desktop app by hand
  • SKILL.md covers Find the window, Commands and Rules
  • Runs JavaScript scripts from its folder; calls node, pnpm and sqlite3
  • Reproducing a chat state by sending a prompt to a fresh session

What it does

The skill uses a small Node script, cdp.mjs, to control a running OpenWork desktop window through CDP. It can evaluate JavaScript, take screenshots, open a new session, send a prompt with a chosen model and wait for the run to finish. It is meant for checking UI changes by hand and reproducing chat states quickly, while formal verdicts belong in evals/specs tests.

The window is found at the default CDP address when running pnpm dev, or through a world started with the evals world script, which prints its own address; CDP_URL is set to that address for every command. The rules: always run new-session first and never type into an existing session, remember that a world started with --allow-shared-state uses your real config and history so anything sent is real, reload after state-heavy changes, and read the stored history in SQLite when the UI hides something.

When your agent uses it

  • Checking a UI change in the OpenWork desktop app by hand
  • Reproducing a chat state by sending a prompt to a fresh session
  • Capturing a screenshot of the running desktop window

Example prompts

  • “Open a new session in the running OpenWork window, send hello with the default model and screenshot the reply.”
  • “Evaluate document.title in the desktop window over CDP.”
  • “Reload the window and capture a screenshot so I can see the layout change.”

Requirements

  • Node.js, to run cdp.mjs
  • A running OpenWork desktop window started with pnpm dev or an evals world
  • sqlite3, to read stored session history

What it can do on your machine

Read from SKILL.md and the folder at commit 4ccc9e9. 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

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • pnpm
    • sqlite3

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    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

OpenWork Desktop CDP Driver loads about 465 tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 128 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~465

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 128 words (~465 tokens).

“For verdicts, write or run an evals/specs test (write-a-spec, run-tests). This skill is for checking changes by hand and reproducing states quickly.”

— opening of SKILL.md by different-ai, Custom licence
name
drive-desktop-cdp

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in .opencode/skills/drive-desktop-cdp of different-ai/openwork.

  • SKILL.md
  • scripts/cdp.mjs

Open the folder on GitHubat commit 4ccc9e9

Compare with similar skills

OpenWork Desktop CDP Driver 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.

OpenWork Desktop CDP Driver compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
OpenWork Desktop CDP Driver this skilldifferent-ai/openwork24k—~465Automated safety check: PassCustom licence
Pipensx Bug Report Triagei3sey/pipensx221—~1.5kAutomated safety check: NotesGPL-3.0
Structured Bug ReportsDonchitos/Claude-Code-Game-Studios26k—~2.5kAutomated safety check: NotesMIT
Bug ReproducerAnastasiyaW/codex-claude-code-config154—~4.1kAutomated safety check: PassMIT
Bug Fix TDDstacklok/toolhive-studio170—~1.7kAutomated safety check: NotesApache-2.0
Dough Bug Fixingterryyin/lizard2.6k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • Pipensx Bug Report Triage

    i3sey/pipensx

    Decodes QR-code bug report photos and screenshots from the pipensx app into a log, then triages crashes and update, download or install failures.

    221 GitHub stars~1.5k tokensUpdated 7 days ago
    Testing & QAAuto-check: notes

  • Structured Bug Reports

    Donchitos/Claude-Code-Game-Studios

    Turns a description into a structured bug report, or scans code for likely bugs, then verifies and closes reports through four modes.

    26k GitHub stars~2.5k tokensUpdated yesterday
    Testing & QAAuto-check: notes

  • Bug Reproducer

    AnastasiyaW/codex-claude-code-config

    Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix.

    154 GitHub stars~4.1k tokensUpdated today
    Testing & QAAuto-check passed

  • Bug Fix TDD

    stacklok/toolhive-studio

    Reproduce and fix bugs using TDD. An agent skill from stacklok/toolhive-studio.

    170 GitHub stars~1.7k tokensUpdated today
    Testing & QAAuto-check: notes

  • Dough Bug Fixing

    terryyin/lizard

    Resolves a reported discrepancy, defect, or regression by gathering expected versus actual behavior and passing the report into bounded shared execution, or by placing known larger or inconclusive…

    2.6k GitHub stars~3.7k tokensUpdated 2 days ago
    Testing & QAAuto-check passed

  • Plugin Testing

    glittercowboy/plugin-freedom-system

    Validates audio plugins through automated tests, pluginval, or manual DAW testing.

    217 GitHub stars~3.1k tokensUpdated 10 mo ago
    Testing & QAAuto-check: notes

More from different-ai/openwork

All 33 skills in this repo

  • Fake Model Provider Faults

    different-ai/openwork

    Makes the desktop app's model provider fail on demand, with refused connections, resets, stalls and HTTP 4xx and 5xx errors, so error and retry states can be reproduced.

    24k GitHub stars~642 tokensUpdated today
    Auto-check passed

  • OpenWork Model Alias Manager

    different-ai/openwork

    Manages OpenWork's inference model aliases, discounts and overlays over the upstream OpenRouter catalog, and triggers the GitHub workflow that refreshes base models.

    24k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Reproduce Chat States

    different-ai/openwork

    Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.

    24k GitHub stars~673 tokensUpdated today
    Auto-check passed

  • OpenWork Electron Browser Automation

    different-ai/openwork

    Attaches OpenCode browser tools to the OpenWork Electron dev app through CDP to explore its UI, send a composer task and debug, not to give test verdicts.

    24k GitHub stars~780 tokensUpdated today
    Auto-check passed

  • Daytona Sandbox Operations

    different-ai/openwork

    Covers Daytona CLI setup, sandbox debugging, keeping a sandbox alive and which credentials the CLI uses, for when Daytona itself is the problem rather than the tests.

    24k GitHub stars~917 tokensUpdated today
    Auto-check passed

  • Daytona Seeded Cloud Demo

    different-ai/openwork

    Spins up a persistent OpenWork Cloud Den demo on a Daytona sandbox, seeds it with Acme Robotics data and returns shareable URLs and login details.

    24k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about OpenWork Desktop CDP Driver

What does OpenWork Desktop CDP Driver do?

Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks. mjs, to control a running OpenWork desktop window through CDP. It can evaluate JavaScript, take screenshots, open a new session, send a prompt with a chosen model and wait for the run to finish.

When should I use OpenWork Desktop CDP Driver?

OpenWork Desktop CDP Driver fits situations like: checking a UI change in the OpenWork desktop app by hand; reproducing a chat state by sending a prompt to a fresh session; capturing a screenshot of the running desktop window.

How do I install OpenWork Desktop CDP Driver in Claude Code?

Run `npx skills add different-ai/openwork --skill drive-desktop-cdp -a claude-code`. Or copy the skill folder (.opencode/skills/drive-desktop-cdp in different-ai/openwork) into .claude/skills/drive-desktop-cdp in your project. Claude Code loads it when a task matches its description.

How do I install OpenWork Desktop CDP Driver in Codex?

Run `npx skills add different-ai/openwork --skill drive-desktop-cdp -a codex`. Or copy the skill folder (.opencode/skills/drive-desktop-cdp in different-ai/openwork) into .agents/skills/drive-desktop-cdp in your project. Codex loads it when a task matches its description.

Can I use OpenWork Desktop CDP Driver 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 different-ai/openwork --skill drive-desktop-cdp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/drive-desktop-cdp, .gemini/skills/drive-desktop-cdp, .github/skills/drive-desktop-cdp and .opencode/skills/drive-desktop-cdp in your project.

What does OpenWork Desktop CDP Driver need to run?

Going by SKILL.md and its folder, OpenWork Desktop CDP Driver needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node, pnpm and sqlite3). Our summary lists: Node.js, to run cdp.mjs; A running OpenWork desktop window started with pnpm dev or an evals world; sqlite3, to read stored session history.

Does OpenWork Desktop CDP Driver 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 OpenWork Desktop CDP Driver 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does OpenWork Desktop CDP Driver use?

OpenWork Desktop CDP Driver has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does OpenWork Desktop CDP Driver use?

About 465 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to OpenWork Desktop CDP Driver?

Skills that share tags, products or a category with OpenWork Desktop CDP Driver: Pipensx Bug Report Triage (i3sey/pipensx, 221 stars), Structured Bug Reports (Donchitos/Claude-Code-Game-Studios, 26k stars), Bug Reproducer (AnastasiyaW/codex-claude-code-config, 154 stars) and Bug Fix TDD (stacklok/toolhive-studio, 170 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains OpenWork Desktop CDP Driver?

different-ai (a GitHub organization) maintains it in different-ai/openwork, which has 23,967 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 9, 2026.

Source: different-ai/openwork on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.