Cloud Computer Use
davidondrej/cloudroom-core
See and control desktop apps on this Cloud sandbox’s virtual Linux screen with cloudroom computer-use: launch GUI apps you build or install, read their UI, click, type, and take screenshots.
GUI desktop app only. An agent skill from warpdotdev/warp.
$ npx skills add warpdotdev/warp --skill gui-onboarding-verification-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install warpdotdev/warp gui-onboarding-verification-skill --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/warpdotdev/warp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/gui-onboarding-verification-skill .claude/skills/gui-onboarding-verification-skill && 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 "gui-onboarding-verification-skill" agent skill from https://github.com/warpdotdev/warp/tree/master/.agents/skills/gui-onboarding-verification-skill into .claude/skills/gui-onboarding-verification-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gui-onboarding-verification-skill", 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/warpdotdev/warp/tree/master/.agents/skills/gui-onboarding-verification-skillType 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 warpdotdev/warp --skill gui-onboarding-verification-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install warpdotdev/warp gui-onboarding-verification-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/warpdotdev/warp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/gui-onboarding-verification-skill .agents/skills/gui-onboarding-verification-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "gui-onboarding-verification-skill" agent skill from https://github.com/warpdotdev/warp/tree/master/.agents/skills/gui-onboarding-verification-skill into .agents/skills/gui-onboarding-verification-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gui-onboarding-verification-skill", 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 warpdotdev/warp --skill gui-onboarding-verification-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install warpdotdev/warp gui-onboarding-verification-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/warpdotdev/warp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/gui-onboarding-verification-skill .cursor/skills/gui-onboarding-verification-skill && 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 "gui-onboarding-verification-skill" agent skill from https://github.com/warpdotdev/warp/tree/master/.agents/skills/gui-onboarding-verification-skill into .cursor/skills/gui-onboarding-verification-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gui-onboarding-verification-skill", 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/warpdotdev/warp.git --path .agents/skills/gui-onboarding-verification-skill--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 warpdotdev/warp --skill gui-onboarding-verification-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install warpdotdev/warp gui-onboarding-verification-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/warpdotdev/warp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/gui-onboarding-verification-skill .gemini/skills/gui-onboarding-verification-skill && 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 "gui-onboarding-verification-skill" agent skill from https://github.com/warpdotdev/warp/tree/master/.agents/skills/gui-onboarding-verification-skill into .gemini/skills/gui-onboarding-verification-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gui-onboarding-verification-skill", 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 warpdotdev/warp gui-onboarding-verification-skillInstalls 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 warpdotdev/warp --skill gui-onboarding-verification-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/warpdotdev/warp.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/gui-onboarding-verification-skill .github/skills/gui-onboarding-verification-skill && 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 "gui-onboarding-verification-skill" agent skill from https://github.com/warpdotdev/warp/tree/master/.agents/skills/gui-onboarding-verification-skill into .github/skills/gui-onboarding-verification-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gui-onboarding-verification-skill", 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 warpdotdev/warp --skill gui-onboarding-verification-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install warpdotdev/warp gui-onboarding-verification-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/warpdotdev/warp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/gui-onboarding-verification-skill .opencode/skills/gui-onboarding-verification-skill && 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 "gui-onboarding-verification-skill" agent skill from https://github.com/warpdotdev/warp/tree/master/.agents/skills/gui-onboarding-verification-skill into .opencode/skills/gui-onboarding-verification-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gui-onboarding-verification-skill", 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.
gui-onboarding-verification-skillGUI desktop app only. An agent skill from warpdotdev/warp.
Gui Onboarding Verification Skill is an agent skill from warpdotdev/warp. GUI desktop app only. Launch two parallel Oz cloud agents with computer use to download and install the latest stable Linux Warp build, capture screenshots while walking through first-time onboarding in both logged-out and logged-in states, then selectively fan out follow-up cloud agents for distinct onboarding branches proposed by those initial explorers. Use this whenever the user asks to test, document, screenshot, or walk through the Warp first-time install/onboarding experience in a cloud Linux environment.
Its SKILL.md is about 6.2k 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 Productivity & Automation, covering Desktop control. It works with Linux. The repository describes itself as: Warp is an agentic development environment, born out of the terminal. The licence is AGPL-3.0.
9 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 325d4d4. 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.
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 these keys or tokens, usually read from environment variables:
ONBOARDING_AGENT_FTUE_REFRESH_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Gui Onboarding Verification Skill loads about 6.2k tokens when it runs. Until then it costs about 138 tokens; SKILL.md has 999 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 warpdotdev/warp at commit 325d4d4, republished under its AGPL-3.0 licence (© warpdotdev). 999 words, ~6,221 tokens.
.claude/skills/gui-onboarding-verification-skill/SKILL.md (or your agent's skills folder).Scope — GUI desktop app only. This skill applies to Warp's GUI desktop front-end (the app/ crate on the WarpUI pixel/GPU framework). It does not apply to the headless TUI front-end (crates/warp_tui; cell-grid TuiElement library under crates/warpui_core/src/elements/tui), which has its own components, tests, and change-verification workflow. For TUI work, see the tui-ui-guidelines, tui-testing, and tui-verify-change skills instead.
Use this skill to verify the first-time Warp install and onboarding flow on Linux with broader branch coverage than a single linear walkthrough.
The parent agent should not perform the walkthrough locally. Launch two parallel Oz cloud agents with computer use. Both initial children install the latest stable Warp Linux package appropriate for their platform and capture screenshots at every visible onboarding step until Warp reaches a usable terminal session. One child verifies the login-free flow. The other child verifies the logged-in flow using the managed secret ONBOARDING_AGENT_FTUE_REFRESH_TOKEN.
Those two baseline explorers are also responsible for noticing meaningful alternate onboarding branches and returning concrete plans for follow-up cloud agents. The parent agent should synthesize those plans, deduplicate overlapping suggestions, and launch a bounded second wave of targeted follow-up agents to improve coverage of paths a real user might encounter.
run_agents batch with computer use enabled.ONBOARDING_AGENT_FTUE_REFRESH_TOKEN is missing or does not authenticate successfully.run_agents batch with computer use enabled for the most valuable follow-up onboarding branches:ONBOARDING_AGENT_FTUE_REFRESH_TOKEN is an internal-team managed secret for cloud agents, not a repo file or prompt literal.warp.dev FTUE test user.oz-dev secret update --team --value-file <private-token-file> ONBOARDING_AGENT_FTUE_REFRESH_TOKEN.Use the initial run_agents call shaped like this:
summary: Launching two baseline cloud agents with computer use to compare logged-out and logged-in Warp onboarding screenshots and propose follow-up coverage branches.
remote.computer_use_enabled: true
agent_run_configs:
- name: "warp-onboarding-logged-out"
prompt: the logged-out flow prompt below
- name: "warp-onboarding-logged-in"
prompt: the logged-in flow prompt below
base_prompt: the shared child prompt belowWhen the baseline reports identify concrete follow-up branches, use a second run_agents call shaped like this:
summary: Launching targeted cloud follow-up agents to explore distinct onboarding branches identified by the baseline onboarding explorers.
remote.computer_use_enabled: true
agent_run_configs:
- name: "warp-onboarding-followup-theme-choice"
prompt: the follow-up flow prompt below, the logged-out flow prompt below, and one synthesized logged-out branch assignment
- name: "warp-onboarding-followup-model-choice"
prompt: the follow-up flow prompt below, the logged-in flow prompt below, and one synthesized logged-in branch assignment
base_prompt: the shared child prompt belowGive both cloud agents these shared instructions:
You are verifying the first-time Warp install and onboarding experience on Linux.
Goal:
- Download and install the latest stable Warp Linux build appropriate for this cloud environment's distro and CPU architecture.
- Launch Warp in a fresh first-run state.
- Take a screenshot at every visible onboarding step.
- Continue until Warp reaches a usable terminal session, or stop and report a blocker if the assigned flow cannot proceed.
- Notice alternate onboarding decisions that lead to meaningfully different screens, states, or outcomes, and return concrete follow-up cloud-agent plans for the parent orchestrator.
- Treat visual polish, missing assets, misalignment, overlapping content, clipped text, poor contrast, broken loading states, unexpected errors, and confusing controls as verification findings rather than ignoring them.
Install requirements:
- Use official stable Warp downloads only.
- Do not use Warp Preview, Alpha, source builds, or a repository development build.
- Detect CPU architecture with `uname -m`.
- Detect the package manager or distro before choosing the package format.
- Prefer native packages over AppImage because they install dependencies and register the app normally.
Stable Linux package mapping:
- Debian/Ubuntu with amd64 or x86_64: https://app.warp.dev/download?package=deb
- Debian/Ubuntu with arm64 or aarch64: https://app.warp.dev/download?package=deb_arm64
- Fedora/RHEL/CentOS/openSUSE with amd64 or x86_64: https://app.warp.dev/download?package=rpm
- Fedora/RHEL/CentOS/openSUSE with arm64 or aarch64: https://app.warp.dev/download?package=rpm_arm64
- Arch with amd64 or x86_64: https://app.warp.dev/download?package=pacman
- Arch with arm64 or aarch64: https://app.warp.dev/download?package=pacman_arm64
- If no native package path is available, use the AppImage fallback:
- amd64 or x86_64: https://app.warp.dev/download?package=appimage
- arm64 or aarch64: https://app.warp.dev/download?package=appimage_arm64
Before launch:
- Create a flow-specific artifact directory such as `~/warp-onboarding-logged-out` or `~/warp-onboarding-logged-in`.
- Ensure the run starts from a fresh Warp first-run state by removing only Warp-specific config/data/cache/state directories for the test user, such as `~/.config/warp-terminal`, `~/.local/share/warp-terminal`, `~/.local/state/warp-terminal`, and `~/.cache/warp-terminal` if they exist.
- Do not delete unrelated user files or system directories.
Screenshot workflow:
- Take the first screenshot before interacting with the first visible Warp window.
- Take one screenshot before every user action.
- Take another screenshot after each action if the UI changes.
- Use sequential filenames with a flow prefix, such as `01-logged-out-initial-window.png` or `01-logged-in-initial-window.png`.
- If anything looks wrong, take an additional issue-focused screenshot that captures the problematic state as clearly as possible.
- Maintain a manifest file in the artifact directory with, for each screenshot:
- filename
- timestamp
- what was visible
- what action was about to happen or just happened
- For issue-focused screenshots, add the suspected issue category and the screen or step where it appeared.
- Do not include secret values, refresh tokens, ID tokens, auth redirect URLs, or Authorization headers in the manifest, logs, shell history, screenshots, or final report.
Onboarding behavior:
- Baseline children choose the default or most conservative option at each step unless the flow-specific prompt says otherwise, while recording branch points that deserve separate follow-up coverage.
- Follow-up children take the specifically assigned alternate branch, then use the default or most conservative option for unrelated decisions unless the branch assignment says otherwise.
- If telemetry, shell, theme, editor-import, or agent integration choices appear, use the default path and document the choice in the manifest.
- Continue until a normal terminal prompt is visible and usable.
UI quality review:
- Watch for screens that are visually broken, obviously unfinished, misaligned, truncated, clipped, crowded, low-contrast, unexpectedly blank, stuck loading, or inconsistent with adjacent steps.
- Watch for actionable errors or validation states that appear during normal flow exploration, including auth failures, failed button transitions, controls that do not respond, duplicated overlays, missing images, or broken post-selection states.
- For every suspicious state:
- Capture a screenshot.
- Record the screen, the action that led to it, what looked wrong, and whether it blocked progress.
- Describe the issue factually. If expected behavior is uncertain, say it appears suspicious rather than claiming a confirmed bug.
Terminal verification:
- Once a terminal session is visible, run a harmless flow-specific command:
- logged-out flow: `echo warp-onboarding-logged-out-ready`
- logged-in flow: `echo warp-onboarding-logged-in-ready`
- Capture a final screenshot showing the usable terminal and command output.
Report back:
- Whether you were a baseline explorer or a follow-up branch explorer.
- Which flow you ran: logged-out or logged-in.
- OS and distro detected.
- CPU architecture detected.
- Package URL and install method used.
- Launch command used.
- Whether the walkthrough reached a usable terminal session.
- Ordered screenshot list with short descriptions.
- Artifact directory path.
- Any built-in artifact IDs or attachment names if the harness supports artifact upload.
- Any visual polish concern, suspected bug, error state, or unpolished/misaligned screen, including:
- screenshot filename
- screen or step
- action taken immediately before it appeared
- concise observed behavior
- whether it blocked progress
- Any blocker, crash, missing dependency, display problem, auth failure, or step that required judgment.
- For baseline explorers, include a `Follow-up coverage plan` section with zero or more proposed child-agent branches. Each proposal must include:
- suggested agent name
- logged-out or logged-in flow
- onboarding screen or decision point where the alternate branch begins
- exact alternate choice or action sequence to explore
- why it is materially distinct from the baseline path
- what user-visible state, setup outcome, or failure mode it could reveal
- any secret, auth, or environment dependency
- priority: high, medium, or low
- For follow-up explorers, include whether the assigned branch was reachable and completed. If a new branch point appears while following the assigned path, record it as a later-run suggestion instead of recursively expanding the run yourself.
Do not upload screenshots or logs to public external services. If the harness provides a built-in artifact or screenshot attachment mechanism, use that. Otherwise, leave the files in the artifact directory and report their paths.Append this prompt to the shared child prompt for the logged-out child:
You own the logged-out onboarding flow.
Flow-specific goal:
- Do not create an account, log in, or use a real user identity.
- Continue only through login-free or account-free paths until Warp reaches a usable terminal session.
- Stop and report a blocker if the flow requires login or account creation with no skip/continue-without-account option.
Flow-specific onboarding behavior:
- If there is a skip, "continue without account", "not now", "login later", or equivalent option, use it.
- Do not enter an email address, connect OAuth, paste an auth token, or create credentials.
- Be especially alert for logged-out branch points around choosing terminal-only versus agentic experiences, customization/layout options, third-party integration toggles, and terminal theme selection. If they appear, propose follow-up branches that exercise materially different choices rather than trying all alternates inline.
- Use the artifact directory `~/warp-onboarding-logged-out`.Append this prompt to the shared child prompt for the logged-in child:
You own the logged-in onboarding flow.
Flow-specific goal:
- Use the managed secret environment variable `ONBOARDING_AGENT_FTUE_REFRESH_TOKEN` to authenticate as the dedicated non-employee, non-`warp.dev` FTUE test user.
- Exercise onboarding screens that are available to an already-authenticated user.
- Continue through the authenticated onboarding path until Warp reaches a usable terminal session.
Secret handling requirements:
- Before doing auth work, verify that `ONBOARDING_AGENT_FTUE_REFRESH_TOKEN` exists and is non-empty without printing it.
- Never echo, log, screenshot, upload, or report the secret value.
- Avoid shell tracing (`set -x`) and avoid writing commands that place the raw token in shell history or process lists.
- Treat every auth redirect URL containing the refresh token as secret-bearing material, even after URL-encoding.
- Do not pass a token-bearing redirect URL to a shell command, desktop URI handler, browser address bar, process argument, log, artifact, or report. In particular, do not use commands such as `xdg-open`, `gio open`, `open`, or equivalent with the redirect URL.
- If you need to construct an auth redirect URL, keep it only in a clipboard value or a private temporary file with user-only permissions, paste it through Warp's visible Paste Auth Token flow, then delete the temporary file immediately after use.
Secure Paste Auth Token process:
1. Verify `ONBOARDING_AGENT_FTUE_REFRESH_TOKEN` exists and is non-empty without printing it.
2. Start Warp's normal login flow and derive the current-run `state` from Warp's generated login URL.
3. Normalize the managed secret privately:
- Trim surrounding whitespace and one pair of surrounding single or double quotes if present.
- If the secret parses as a URL with a `refresh_token` query parameter, extract that `refresh_token` value and ignore any stale `state` in the secret.
- Otherwise, treat the trimmed secret as the raw refresh token.
4. URL-encode the extracted refresh token and current-run `state` separately as query parameter values.
5. Construct the redirect URL only in a clipboard value or private temporary file with user-only permissions.
6. Return to Warp and use the visible Paste Auth Token path:
- Click the `Click here to paste your token from the browser` link, `Paste Auth Token` button, or equivalent pasted-token control shown by Warp.
- Focus the auth token text input that appears.
- Paste the prepared redirect URL into that input and submit it through Warp's UI so Warp parses and validates it.
7. Delete any private temporary files immediately after use and clear the clipboard if the environment supports doing so safely.
8. If the Paste Auth Token UI cannot be reached or automated safely, stop and report an auth blocker instead of parsing the redirect in place of Warp, using a desktop URI handler, browser address bar, or shell command with the token-bearing URL.
Preferred authenticated path:
- Launch Warp in a fresh first-run state and choose the login/sign-in path from onboarding.
- Use Warp's built-in Paste Auth Token flow rather than visiting real OAuth providers, invoking a desktop URI handler, or asking the agent to parse/validate the redirect URI itself.
- Derive `<state>` from the login URL generated by Warp if the UI exposes a copied login URL or opens the browser. If the UI does not expose the state after reasonable effort, report that as an auth blocker rather than bypassing state validation.
- Do not preflight the token with Firebase Secure Token before handing it to Warp. Warp's desktop redirect handler only requires `refresh_token` and `state`; `user_uid` is optional, and `deleted_anonymous_user=true` handles the anonymous-user override case.
- Treat `ONBOARDING_AGENT_FTUE_REFRESH_TOKEN` as either of these secret shapes:
- a raw Firebase refresh token, or
- a complete Warp desktop auth redirect URL containing a `refresh_token` query parameter.
- Normalize the secret into a current-run redirect URL without printing it:
- Trim surrounding whitespace and one pair of surrounding single or double quotes if present.
- If the secret parses as a URL with a `refresh_token` query parameter, extract that `refresh_token` value and ignore any stale `state` in the secret.
- Otherwise, treat the trimmed secret as the raw refresh token.
- URL-encode the extracted refresh token and the current-run `state` separately as query parameter values.
- Build `warp://auth/desktop_redirect?refresh_token=<url-encoded-normalized-refresh-token>&deleted_anonymous_user=true&state=<url-encoded-current-state>`.
- Do not include `user_uid` unless it is already present in a provided desktop redirect URL; it is not required for this flow.
- Construct the normalized redirect URL in a clipboard value or private temporary file only, then hand it to Warp through the Paste Auth Token UI. Do not parse, validate, or route the redirect outside of Warp.
- If the Paste Auth Token flow cannot be reached or automated safely, stop and report an auth blocker instead of using a desktop URI handler or any shell command that contains the token-bearing URL.
Fallback authenticated path:
- If Warp rejects the normalized redirect, report the non-sensitive user-visible error and classify whether the secret appeared to be a raw token or a desktop redirect URL, without reporting any token contents.
- If the Paste Auth Token flow is blocked by UI automation issues, report the blocker and include the exact non-sensitive step where automation failed.
- Do not switch to a logged-out path for this child.
Flow-specific onboarding behavior:
- Choose login/sign-in rather than skip/login-later when presented with an auth choice.
- After auth succeeds, continue through the remaining onboarding screens with default or conservative options.
- Be especially alert for logged-in branch points around model selection, account-aware onboarding screens, AI/agent setup, workspace or project setup, and any decision that changes available product capability. If they appear, propose follow-up branches that exercise materially different choices rather than trying all alternates inline.
- After the terminal verification succeeds, click the upper-right avatar/account control, open Settings from that menu, and capture an additional screenshot that clearly shows the logged-in user's email address in Warp settings or account/profile settings.
- Include the account/settings email screenshot in the manifest and final report. The email address itself may be visible in the screenshot, but do not copy the email into logs, shell output, or the final text report unless the user explicitly asks for it.
- Use the artifact directory `~/warp-onboarding-logged-in`.Append this prompt to the shared child prompt for every second-wave child, followed by the matching logged-out or logged-in flow prompt and one branch assignment synthesized from the baseline reports:
You own one follow-up onboarding branch selected by the parent orchestrator from an earlier baseline exploration report.
Follow-up branch behavior:
- Start from a fresh first-run Warp state and install the same latest stable Linux build using the shared instructions.
- Respect the assigned auth state: remain logged out for logged-out assignments, or use the managed authenticated flow for logged-in assignments.
- Follow the exact alternate onboarding choice or action sequence in the branch assignment.
- Capture screenshots before and after each assigned branch decision, then continue to a usable terminal session if the path allows it.
- Apply the same UI quality review standard as the baseline explorers and call out anything that looks broken, rough, misaligned, confusing, or unexpectedly error-prone.
- If the assigned branch is not reachable, capture the closest relevant screen, report why it was unreachable, and do not silently substitute a different branch.
- If the assigned branch reveals another interesting alternate path, record it as a later-run suggestion rather than recursively launching more agents yourself.
Final report additions:
- Repeat the exact branch assignment you attempted in concise non-sensitive terms.
- State whether it was reachable, completed, blocked, or not applicable.
- Compare the branch outcome against the likely baseline behavior when that comparison is visible from the UI.The run is successful when:
ONBOARDING_AGENT_FTUE_REFRESH_TOKEN and reached a usable terminal in the authenticated FTUE path.echo command.warp-terminal fails because of display setup, inspect the cloud environment's display variables and try launching from the desktop/app launcher if computer use provides one.© warpdotdev, AGPL-3.0. 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 .agents/skills/gui-onboarding-verification-skill of warpdotdev/warp.
Open the folder on GitHubat commit 325d4d4
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in warpdotdev/warp, which our catalogue first saw on October 7, 2026.
Gui Onboarding Verification Skill 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 |
|---|---|---|---|---|---|---|
| Gui Onboarding Verification Skill this skillwarpdotdev/warp | 65k | 1 repos | ~6.2k | Automated safety check: Pass | AGPL-3.0 | |
| Cloud Computer Usedavidondrej/cloudroom-core | 272 | — | ~881 | Automated safety check: Notes | Apache-2.0 | |
| Open Computer UseiFurySt/open-codex-computer-use | 2.4k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Waku Computer Useegoist/waku | 1.6k | — | ~3.6k | Automated safety check: Pass | GPL-3.0 | |
| Linux Desktop Controlagent-sh/computer-use-linux | 663 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Browser MCP Agentantibrow/anti-detect-browser-skills | 932 | 1 repos | ~4.2k | Automated safety check: Warn | MIT |
davidondrej/cloudroom-core
See and control desktop apps on this Cloud sandbox’s virtual Linux screen with cloudroom computer-use: launch GUI apps you build or install, read their UI, click, type, and take screenshots.
iFurySt/open-codex-computer-use
Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows.
egoist/waku
Control local macOS, Windows, and Linux apps through Waku Computer Use.
agent-sh/computer-use-linux
Lets an agent observe and operate a local Linux desktop through the computer-use-linux MCP server or Pi tools: accessibility trees, screenshots, windows and input.
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…
agent-sh/agent-workspace-linux
Drives a hidden, agent-owned Linux desktop and browser over MCP for GUI testing and web automation without touching the user's real desktop.
warpdotdev/warp
Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.
warpdotdev/warp
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
warpdotdev/warp
Authors and edits file-based Warp software factory definitions rooted at factory.yaml, covering agents, automations, scorers and webhooks, and validates them before a pull request.
warpdotdev/warp
Turns a Figma frame or component into production code that matches the design, using the Figma MCP server and the project's own design system.
warpdotdev/warp
Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.
warpdotdev/warp
Creates project-specific design system rules from your codebase so coding agents implement Figma designs with your components, naming and tokens.
Works with
Categories
GUI desktop app only. An agent skill from warpdotdev/warp. Gui Onboarding Verification Skill is an agent skill from warpdotdev/warp. GUI desktop app only.
Gui Onboarding Verification Skill fits situations like: download and install the latest stable Linux Warp build; capture screenshots while walking through first-time onboarding in both logged-out and logged-in states; then selectively fan out follow-up cloud agents for distinct onboarding branches proposed by those initial explorers; walk through the Warp first-time install/onboarding experience in a cloud Linux environment.
Run `npx skills add warpdotdev/warp --skill gui-onboarding-verification-skill -a claude-code`. Or copy the skill folder (.agents/skills/gui-onboarding-verification-skill in warpdotdev/warp) into .claude/skills/gui-onboarding-verification-skill in your project. Claude Code loads it when a task matches its description.
Run `npx skills add warpdotdev/warp --skill gui-onboarding-verification-skill -a codex`. Or copy the skill folder (.agents/skills/gui-onboarding-verification-skill in warpdotdev/warp) into .agents/skills/gui-onboarding-verification-skill 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 warpdotdev/warp --skill gui-onboarding-verification-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gui-onboarding-verification-skill, .gemini/skills/gui-onboarding-verification-skill, .github/skills/gui-onboarding-verification-skill and .opencode/skills/gui-onboarding-verification-skill in your project.
Going by SKILL.md and its folder, Gui Onboarding Verification Skill needs credentials named ONBOARDING_AGENT_FTUE_REFRESH_TOKEN. Our summary lists: A credential in ONBOARDING_AGENT_FTUE_REFRESH_TOKEN.
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.
Gui Onboarding Verification Skill is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 6.2k tokens (SKILL.md is roughly 25k 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 Gui Onboarding Verification Skill: Cloud Computer Use (davidondrej/cloudroom-core, 272 stars), Open Computer Use (iFurySt/open-codex-computer-use, 2.4k stars), Waku Computer Use (egoist/waku, 1.6k stars) and Linux Desktop Control (agent-sh/computer-use-linux, 663 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
warpdotdev (a GitHub organization) maintains it in warpdotdev/warp, which has 65,395 GitHub stars. The repository holds 46 skills in this directory. The repository was last updated on October 8, 2026.
Source: warpdotdev/warp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.