Agent skill

Verify UI Via Dev Control

by genex-games in genex-games/genex-desktop

Verify renderer, IPC, preview or startup changes through owned studio:dev profiles, or hand off the real app for manual testing.

MITAuto-check passedTesting & QA

Install Verify UI Via Dev Control

skills CLI
$ npx skills add genex-games/genex-desktop --skill verify-ui-via-dev-control -a claude-code

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

GitHub CLI
$ gh skill install genex-games/genex-desktop verify-ui-via-dev-control --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/genex-games/genex-desktop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/verify-ui-via-dev-control .claude/skills/verify-ui-via-dev-control && 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
verify-ui-via-dev-control
GitHub stars
418
Token cost
~1.3k tokens
SKILL.md length
471 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Verify renderer, IPC, preview or startup changes through owned studio:dev profiles, or hand off the real app for manual testing.

  • Tasks that involve QA and bug reports
  • SKILL.md covers Choose the session, Automated fixture loop, Requests and Evidence
  • Calls npm

What it does

Verify UI Via Dev Control is an agent skill from genex-games/genex-desktop. Verify renderer, IPC, preview or startup changes through owned studio:dev profiles, or hand off the real app for manual testing. Choose fixture or live mode from the requested task.

Its SKILL.md is about 1.3k 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 Testing & QA, covering QA and bug reports. The repository describes itself as: Desktop app for game dev with AI. macOS and Linux, Windows soon. The licence is MIT.

When your agent uses it

  • Tasks that involve QA and bug reports

Example prompts

  • “/verify-ui-via-dev-control”

What it can do on your machine

Read from SKILL.md and the folder at commit 8ea9be8. 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

    Shell commands in SKILL.md call:

    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use npm, 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

Verify UI Via Dev Control loads about 1.3k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 471 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 genex-games/genex-desktop at commit 8ea9be8, republished under its MIT licence (© genex-games). 471 words, ~1,333 tokens.

Download SKILL.mdSave it as .claude/skills/verify-ui-via-dev-control/SKILL.md (or your agent's skills folder).
name
verify-ui-via-dev-control
description
Verify renderer, IPC, preview or startup changes through owned studio:dev profiles, or hand off the real app for manual testing. Choose fixture or live mode from the requested task.

Verify UI through dev control

Choose the session

  • Automated regression: use a disposable fixture profile; it makes no provider/account calls.
  • Real app manual testing, including “no mocks”: use start --profile manual-review --providers live. That request authorizes the live launch; do not ask again. The window is visible and focusable. Isolated app data does not isolate provider accounts, Keychain, quotas or compute. Do not copy or inspect credentials, and do not perform paid generations merely to check startup. The launch drops your agent session's own variables (envStripped in the start JSON) and warns when the games root sits under a .claude folder (warnings).
  • A new user's first launch (no Claude Code, Codex or sign-in): add --fresh-machine to that live start; shell --profile <name> is that account's terminal.
  • Human review explicitly using fixture data: set STUDIO_FIXTURE_INTERACTIVE=1 on start/restart.

Inspect ownership/status before reusing a profile. Preserve active user work. Leave human testing sessions running and retain their state. The stop/clean steps below apply only to disposable sessions created for your automated check. See the field guide. Use owned profiles instead of npm start or the normal profile/~/AI Games.

CLI: scripts/studio-dev.ts (parser in scripts/studio-dev/args.ts). Operations and their limits: src/main/dev/protocol.ts. Every command prints JSON (after npm's two header lines).

Automated fixture loop

sh
npm run studio:dev -- fixtures                                   # the named fixtures
npm run studio:dev -- start --profile ui-check --fixture app-basics   # builds, waits for ready
npm run studio:dev -- snapshot --profile ui-check                # controls, state, text
npm run studio:dev -- snapshot --profile ui-check --scope '[data-stage-view]' --limit 40
npm run studio:dev -- ui --profile ui-check --json '{"method":"click","params":{"selector":"[data-stage-action=\"assets\"]"}}'
npm run studio:dev -- capture --profile ui-check --surface desktop --name after
npm run studio:dev -- logs --profile ui-check --surface desktop  # also game|core|harness|stdout|stderr
npm run studio:dev -- stop --profile ui-check
npm run studio:dev -- clean --profile ui-check                   # disposable state only

Pick the fixture that already shows the surface (app-basics, chat-history, run-controls, sidebar, build-history, game-surface, ...). Changing source makes the session stale: restart --profile ui-check rebuilds with the same fixture. start --reuse reopens a stopped one.

Show full SKILL.md (230 more words)Show less

Requests

Target elements by data-* hooks or aria-label, never by class names or visible copy. A selector must match exactly one visible, enabled, unobscured element (scope narrows it). Longer requests go through stdin, which avoids shell quoting:

sh
npm run studio:dev -- ui --profile ui-check --request - <<'JSON'
{"method":"type","params":{"selector":"[data-promptbar] textarea[aria-label=\"Prompt\"]","text":"Make it rain","replace":true}}
JSON

Templates (one per request; --request FILE also works):

json
{"method":"click","params":{"selector":"button[aria-label=\"Hide sidebar\"]"}}
{"method":"key","params":{"surface":"desktop","key":"Enter","code":"Enter"}}
{"method":"select","params":{"selector":"select[aria-label=\"Build history\"]","value":"<runId from snapshot>"}}
{"method":"scroll","params":{"surface":"desktop","deltaX":0,"deltaY":600,"selector":"[data-chat-scroll]"}}
{"method":"game.input","params":{"actions":[{"type":"tap","keys":["ArrowRight"]},{"type":"wait","ms":300}]}}
{"method":"game.state","params":{}}

Hooks for the controls an unattended operator presses: [data-run-resume="<runId>"] (Resume on the result card and on the chat's paused line), [data-onboarding-action="next|skip|start"] (the welcome). key sends Arrow keys (all four), PageUp/PageDown, Home/End with real key codes, so sliders and segment groups move as they do under a keyboard. runs --profile P lists each open run and the open chat's newest (state, phase, clock, last record, stop reason, resumable); it reads the profile's records, asks the window which chat is open, and answers on a stale build or with the harness down.

Evidence

  • Assert on the snapshot JSON (state, stage, controls[].label, text), not only images.
  • capture returns the PNG path (under .studio-dev/evidence/); open it and look at it.
  • Report source revision, build ID, profile and provider mode from start/status; include the fixture name when applicable. Say whether the session remains running for manual testing.
  • Errors come back as {ok:false,error}: target-not-visible, ambiguous-selector, stale-build (restart), unsupported-in-fixture (native action; not a UI bug).
  • For your disposable automated fixture only, stop then clean, including after failure; evidence is kept. Do not clean retained live profiles or stop a human testing session.

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

Files

Just SKILL.md in .agents/skills/verify-ui-via-dev-control of genex-games/genex-desktop.

Open the folder on GitHubat commit 8ea9be8

Compare with similar skills

Verify UI Via Dev Control 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.

Verify UI Via Dev Control compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verify UI Via Dev Control this skillgenex-games/genex-desktop418—~1.3kAutomated safety check: PassMIT
Reproduce Chat Statesdifferent-ai/openwork24k—~673Automated safety check: PassCustom licence
Dynamo Jira TicketDynamoDS/Dynamo2k—~1.1kAutomated safety check: PassApache-2.0
Minimal Run And Auditlllllllama/RigorPilot-Skills4972 repos~691Automated safety check: PassMIT
Moav E2EMotherofallVPNs/MoaV448—~1.9kAutomated safety check: NotesMIT
Anchor Reprolynxlangya/techne1051 repos~1.2kAutomated safety check: PassMIT

Similar skills

  • 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
    Testing & QAAuto-check passed
  • Dynamo Jira Ticket

    DynamoDS/Dynamo

    Create structured Jira tickets for Dynamo from bug reports, failing tests, or feature requests.

    2k GitHub stars~1.1k tokensUpdated today
    Testing & QAAuto-check passed
  • Minimal Run And Audit

    lllllllama/RigorPilot-Skills

    Rigor Run skill for README-first deep learning repo reproduction.

    497 GitHub starsUsed in 2 repos~691 tokens
    Testing & QAAuto-check passed
  • Moav E2E

    MotherofallVPNs/MoaV

    Run and debug MoaV's end-to-end tests — real protocol connectivity (client-test.sh) and the moav CLI smoke test — against a LIVE server, via the self-hosted e2e workflow or a local test VPS.

    448 GitHub stars~1.9k tokensUpdated yesterday
    Testing & QAAuto-check: notes
  • Anchor Repro

    lynxlangya/techne

    Reproduce a behavioral bug before fixing it, record the failing probe, and verify the fix with the same probe.

    105 GitHub starsUsed in 1 repo~1.2k tokens
    Testing & QAAuto-check passed
  • Creating A Coral Task

    Human-Agent-Society/CORAL

    Author a new CORAL task — the three pieces that must line up (task.yaml, seed/, a packaged grader/), the coral init → coral validate → smoke-test loop, and how to pick a grader pattern (stdout…

    1k GitHub stars~2.2k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

More from genex-games/genex-desktop

  • Add Event Type

    genex-games/genex-desktop

    Add a new persisted event (custom eventtype in the append-only log) or a transient UI event, with its producer, readers and tests.

    418 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Add Ipc Channel

    genex-games/genex-desktop

    Add or change a renderer-to-main IPC channel (a new window.studio call) end to end - main handler, preload, typed API, fixture classification and tests.

    418 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Add Plugin Tool

    genex-games/genex-desktop

    Add or change an agent-callable tool contributed by a Studio plugin (manifest declaration, backend handler, consent, docs and tests).

    418 GitHub stars~841 tokensUpdated yesterday
    Auto-check passed
  • Harness Incident Fix

    genex-games/genex-desktop

    Fix a bug in the in-app harness loop (src/harness-seed/) test-first - write the incident row that reproduces it, see it fail, fix, then run the harness gate.

    418 GitHub stars~843 tokensUpdated yesterday
    Auto-check passed
  • Run Area Tests

    genex-games/genex-desktop

    Pick and run only the tests a change can affect - the affected-tests selector, one knowledge-map area, or named files - instead of the full suite.

    418 GitHub stars~698 tokensUpdated yesterday
    Auto-check passed
  • Break

    genex-games/genex-desktop

    Renders a component you choose in every state and scenario on a temporary page and stress tests it.

    418 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed

Categories

Questions about Verify UI Via Dev Control

What does Verify UI Via Dev Control do?

Verify renderer, IPC, preview or startup changes through owned studio:dev profiles, or hand off the real app for manual testing. Verify UI Via Dev Control is an agent skill from genex-games/genex-desktop. Verify renderer, IPC, preview or startup changes through owned studio:dev profiles, or hand off the real app for manual testing.

When should I use Verify UI Via Dev Control?

Verify UI Via Dev Control fits situations like: tasks that involve QA and bug reports.

How do I install Verify UI Via Dev Control in Claude Code?

Run `npx skills add genex-games/genex-desktop --skill verify-ui-via-dev-control -a claude-code`. Or copy the skill folder (.agents/skills/verify-ui-via-dev-control in genex-games/genex-desktop) into .claude/skills/verify-ui-via-dev-control in your project. Claude Code loads it when a task matches its description.

How do I install Verify UI Via Dev Control in Codex?

Run `npx skills add genex-games/genex-desktop --skill verify-ui-via-dev-control -a codex`. Or copy the skill folder (.agents/skills/verify-ui-via-dev-control in genex-games/genex-desktop) into .agents/skills/verify-ui-via-dev-control in your project. Codex loads it when a task matches its description.

Can I use Verify UI Via Dev Control 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 genex-games/genex-desktop --skill verify-ui-via-dev-control -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify-ui-via-dev-control, .gemini/skills/verify-ui-via-dev-control, .github/skills/verify-ui-via-dev-control and .opencode/skills/verify-ui-via-dev-control in your project.

What does Verify UI Via Dev Control need to run?

Going by SKILL.md and its folder, Verify UI Via Dev Control needs the command-line tools its instructions call (npm).

Does Verify UI Via Dev Control access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Verify UI Via Dev Control 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 Verify UI Via Dev Control use?

Verify UI Via Dev Control 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 Verify UI Via Dev Control use?

About 1.3k tokens (SKILL.md is roughly 5.3k 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 Verify UI Via Dev Control?

Skills that share tags, products or a category with Verify UI Via Dev Control: Reproduce Chat States (different-ai/openwork, 24k stars), Dynamo Jira Ticket (DynamoDS/Dynamo, 2k stars), Minimal Run And Audit (lllllllama/RigorPilot-Skills, 497 stars) and Moav E2E (MotherofallVPNs/MoaV, 448 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verify UI Via Dev Control?

genex-games (a GitHub organization) maintains it in genex-games/genex-desktop, which has 418 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

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