UI Visual Debugging
NangoHQ/nango
A skill your agent uses when modifying or visually debugging Nango frontend UI, including packages/webapp, packages/connect-ui, browser interactions, screenshots, and visual regressions.
Launch and drive the GooeyPi desktop (Electron) app to prove user-facing behavior — sidebar navigation, Settings, and Capabilities — capturing screenshots and ARIA snapshots.
Install Verify Gooeypi
$ npx skills add am-will/gooey-pi --skill verify-gooeypi -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install am-will/gooey-pi verify-gooeypi --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/am-will/gooey-pi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/verify-gooeypi .claude/skills/verify-gooeypi && 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 "verify-gooeypi" agent skill from https://github.com/am-will/gooey-pi/tree/main/.cursor/skills/verify-gooeypi into .claude/skills/verify-gooeypi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-gooeypi", 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/am-will/gooey-pi/tree/main/.cursor/skills/verify-gooeypiType 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 am-will/gooey-pi --skill verify-gooeypi -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install am-will/gooey-pi verify-gooeypi --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/am-will/gooey-pi.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/verify-gooeypi .agents/skills/verify-gooeypi && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "verify-gooeypi" agent skill from https://github.com/am-will/gooey-pi/tree/main/.cursor/skills/verify-gooeypi into .agents/skills/verify-gooeypi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-gooeypi", 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 am-will/gooey-pi --skill verify-gooeypi -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install am-will/gooey-pi verify-gooeypi --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/am-will/gooey-pi.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/verify-gooeypi .cursor/skills/verify-gooeypi && 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 "verify-gooeypi" agent skill from https://github.com/am-will/gooey-pi/tree/main/.cursor/skills/verify-gooeypi into .cursor/skills/verify-gooeypi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-gooeypi", 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/am-will/gooey-pi.git --path .cursor/skills/verify-gooeypi--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 am-will/gooey-pi --skill verify-gooeypi -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install am-will/gooey-pi verify-gooeypi --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/am-will/gooey-pi.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/verify-gooeypi .gemini/skills/verify-gooeypi && 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 "verify-gooeypi" agent skill from https://github.com/am-will/gooey-pi/tree/main/.cursor/skills/verify-gooeypi into .gemini/skills/verify-gooeypi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-gooeypi", 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 am-will/gooey-pi verify-gooeypiInstalls 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 am-will/gooey-pi --skill verify-gooeypi -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/am-will/gooey-pi.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/verify-gooeypi .github/skills/verify-gooeypi && 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 "verify-gooeypi" agent skill from https://github.com/am-will/gooey-pi/tree/main/.cursor/skills/verify-gooeypi into .github/skills/verify-gooeypi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-gooeypi", 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 am-will/gooey-pi --skill verify-gooeypi -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install am-will/gooey-pi verify-gooeypi --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/am-will/gooey-pi.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/verify-gooeypi .opencode/skills/verify-gooeypi && 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 "verify-gooeypi" agent skill from https://github.com/am-will/gooey-pi/tree/main/.cursor/skills/verify-gooeypi into .opencode/skills/verify-gooeypi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-gooeypi", 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.
Facts
- Skill name
verify-gooeypi- GitHub stars
- 943
- Token cost
- ~1.1k tokens
- SKILL.md length
- 545 words
- Files
- 7
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- MIT
At a glance
Launch and drive the GooeyPi desktop (Electron) app to prove user-facing behavior — sidebar navigation, Settings, and Capabilities — capturing screenshots and ARIA snapshots.
- Tasks that involve Accessibility
- SKILL.md covers Launch, Doctor, Drive and Evidence, plus 2 more sections
- Runs JavaScript scripts from its folder; calls node, npm and nvm
- Tasks that involve End-to-end testing
What it does
Verify Gooeypi is an agent skill from am-will/gooey-pi. Launch and drive the GooeyPi desktop (Electron) app to prove user-facing behavior — sidebar navigation, Settings, and Capabilities — capturing screenshots and ARIA snapshots. Reach for this when verifying a GooeyPi UI change or confirming the app still works end to end.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files (for example `features/README.md`, `features/capabilities.md` and `features/navigation.md`).
It sits in Testing & QA, covering Accessibility and End-to-end testing. It works with Electron and npm. The repository describes itself as: Desktop workspace for Pi, OMP, and Prime Agent. The licence is MIT.
When your agent uses it
- Tasks that involve Accessibility
- Tasks that involve End-to-end testing
Example prompts
- “/verify-gooeypi”
Requirements
- Node.js
What it can do on your machine
Read from SKILL.md and the folder at commit 459c996. 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 script files (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
nodenpmnvmmodal
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 Gooeypi loads about 1.1k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 545 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.
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 am-will/gooey-pi at commit 459c996, republished under its MIT licence (© am-will). 545 words, ~1,125 tokens.
Download SKILL.mdSave it as
.claude/skills/verify-gooeypi/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- verify-gooeypi
- description
- Launch and drive the GooeyPi desktop (Electron) app to prove user-facing behavior — sidebar navigation, Settings, and Capabilities — capturing screenshots and ARIA snapshots. Reach for this when verifying a GooeyPi UI change or confirming the app still works end to end.
Verify GooeyPi
GooeyPi is a desktop Electron app — that window is the only surface a user
touches (there is no user-facing web page, CLI, or API). This skill launches the
built app in an isolated, disposable profile, drives one user-facing feature the
way a person would, and captures evidence. The driver mirrors the repo's own
Playwright Electron harness (tests/e2e/app.spec.ts) but runs as a standalone
controller you can invoke directly.
The maintained feature list lives in features/; read
its index before driving, then use the matching feature file as the recipe.
Launch
- Build once. The driver launches the built bundle (
package.jsonmain→out/main/index.js). If it is missing, build it:npm run build. The driver aborts with a clear message when the bundle is absent. - Toolchain.
node/npmcome fromnvm(pinned24.15.0/12.0.2). Ifnode -vis notv24.15.0, select it first:export NVM_DIR="$HOME/.nvm"; . "$NVM_DIR/nvm.sh"; nvm use >/dev/null. - Display. The app needs an X display. On a headless machine prefix every
command with
xvfb-run -a(e.g.xvfb-run -a --server-args="-screen 0 1600x1000x24" ...). - Isolation. Every drive launches its own app instance with a throwaway
HOMEand Electron--user-data-dir, so it never reads or writes your real~/.prime/~/.omp/~/.pistate and never drives an instance it did not start. Readiness is.app-shell[data-ready="true"]. A freshHOMEhas no harness installed, so the driver first dismisses theNo Pi family harness detectedmodal (that modal makes the shellinert). - Command.
xvfb-run -a node .cursor/skills/verify-gooeypi/control.mjs drive <scenario> --out <dir>
Doctor
Answer "is this instance worth driving?" before anything else, or whenever the app looks wrong:
xvfb-run -a node .cursor/skills/verify-gooeypi/control.mjs doctor --out /tmp/gooeypi-verify/doctorIt launches the app, asserts .app-shell[data-ready="true"], prints the window
title (expect GooeyPi), and screenshots. A non-zero exit means the build is
broken or the app never became ready — fix that before driving features.
Show full SKILL.md (254 more words)Show less
Drive
- Harness: Playwright's
_electrondriving the built app. Prefer stable handles over coordinates: sidebar items are buttons with accessible namesNew session,Search,Projects,Activity,Scheduled,Capabilities; each page asserts its level-1 heading; Settings opens from the.sidebar__footerSettingsbutton and lands on theGeneralheading, with sections as buttons namedAppearance,Pets,Harness, etc. - Scenarios:
node .cursor/skills/verify-gooeypi/control.mjs list→navigation,settings,capabilities. Each is one self-contained launch → drive → capture → teardown. The feature map documents these plus features (session messaging) that need the repo's hermetic fixture rather than this driver.
Evidence
- Each scenario writes PNG screenshots and
.aria.txtARIA snapshots to--out DIR(default/tmp/gooeypi-verify/<scenario>-<timestamp>) and prints aPROVEN:list of the assertions it checked. - Proof standard: drive the real user path and capture both the action and
the resulting page state (heading + ARIA), not just a final screen. For a
mutation (creating a schedule or sending a message), also verify the side
effect — a file written under the harness
HOME, or a second read-only view — not just a toast. Record the feature ID and the entry point used. - Artifacts survive teardown. Copy any you want to keep into
/opt/cursor/artifactsfor a PR walkthrough.
Cleanup
- The driver closes only the app instance it launched and removes only the
throwaway fixture
HOME/user-data-dirit created. It never deletes evidence dirs. Never kill Electron by name (pkill electron); the driver owns its own child process and tears it down.
Helpers
control.mjs(executable). Subcommands:doctor,drive <scenario>,list. Invoke exactly as shown above; run underxvfb-runon headless machines.
© am-will, 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 6 other files in .cursor/skills/verify-gooeypi of am-will/gooey-pi.
- SKILL.md
- control.mjs
- features/README.md
- features/capabilities.md
- features/navigation.md
- features/sessions-and-messaging.md
- features/settings.md
Open the folder on GitHubat commit 459c996
Compare with similar skills
Verify Gooeypi 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 |
|---|---|---|---|---|---|---|
| Verify Gooeypi this skillam-will/gooey-pi | 943 | — | ~1.1k | Automated safety check: Pass | MIT | |
| UI Visual DebuggingNangoHQ/nango | 13k | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| React Testingaffaan-m/ECC | 276k | 1 repos | ~3.3k | Automated safety check: Pass | MIT | |
| E2E Testingericrisco/rsc-harness | 180 | — | ~3.2k | Automated safety check: Pass | MIT | |
| OpenHarness End-to-End EvalsHKUDS/OpenHarness | 16k | 1 repos | ~2.1k | Automated safety check: Notes | MIT | |
| Qwen Code E2E TestingQwenLM/qwen-code | 28k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
React Testing
affaan-m/ECC
React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress…
E2E Testing
ericrisco/rsc-harness
A skill your agent uses when writing or stabilizing Playwright tests that drive a real browser through multi-step journeys — durable locators, web-first assertions, storageState auth, trace/retries…
OpenHarness End-to-End Evals
HKUDS/OpenHarness
Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution.
Qwen Code E2E Testing
QwenLM/qwen-code
Guides end-to-end testing of the Qwen Code CLI in headless mode with real model calls, MCP test servers and inspection of raw API traffic.
E2E Testing
InsForge/InsForge
A skill your agent uses when an InsForge maintainer has finished an OSS repo change and is ready to open, update, or submit the InsForge PR.
More from am-will/gooey-pi
All 8 skills in this repoGui Automation
am-will/gooey-pi
A skill your agent uses when you need to visually interact with a GUI — test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end…
Setup Pstack
am-will/gooey-pi
Configure which models pstack uses per role. An agent skill from am-will/gooey-pi.
Prime Work Browser
am-will/gooey-pi
Drive the GooeyPi in-app browser for this thread with the browser tools - open tabs, navigate, read pages, click, type, scroll, screenshot, and extract data.
Prime Work Schedules
am-will/gooey-pi
Create, inspect, edit, pause, resume, run, and delete durable GooeyPi scheduled tasks.
Supabase
am-will/gooey-pi
Work with Supabase projects through Supabase's official hosted MCP server.
Gooeypi Computer Use
am-will/gooey-pi
Drive native applications on macOS, Windows, or Linux through the separately installed TryCUA driver CLI.
Related
Categories
Questions about Verify Gooeypi
What does Verify Gooeypi do?
Launch and drive the GooeyPi desktop (Electron) app to prove user-facing behavior — sidebar navigation, Settings, and Capabilities — capturing screenshots and ARIA snapshots. Verify Gooeypi is an agent skill from am-will/gooey-pi. Launch and drive the GooeyPi desktop (Electron) app to prove user-facing behavior — sidebar navigation, Settings, and Capabilities — capturing screenshots and ARIA snapshots.
When should I use Verify Gooeypi?
Verify Gooeypi fits situations like: tasks that involve Accessibility; tasks that involve End-to-end testing.
How do I install Verify Gooeypi in Claude Code?
Run `npx skills add am-will/gooey-pi --skill verify-gooeypi -a claude-code`. Or copy the skill folder (.cursor/skills/verify-gooeypi in am-will/gooey-pi) into .claude/skills/verify-gooeypi in your project. Claude Code loads it when a task matches its description.
How do I install Verify Gooeypi in Codex?
Run `npx skills add am-will/gooey-pi --skill verify-gooeypi -a codex`. Or copy the skill folder (.cursor/skills/verify-gooeypi in am-will/gooey-pi) into .agents/skills/verify-gooeypi in your project. Codex loads it when a task matches its description.
Can I use Verify Gooeypi 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 am-will/gooey-pi --skill verify-gooeypi -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-gooeypi, .gemini/skills/verify-gooeypi, .github/skills/verify-gooeypi and .opencode/skills/verify-gooeypi in your project.
What does Verify Gooeypi need to run?
Going by SKILL.md and its folder, Verify Gooeypi needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node, npm, nvm and modal). Our summary lists: Node.js.
Does Verify Gooeypi 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 Gooeypi 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 Gooeypi use?
Verify Gooeypi 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 Gooeypi use?
About 1.1k tokens (SKILL.md is roughly 4.5k 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 Gooeypi?
Skills that share tags, products or a category with Verify Gooeypi: UI Visual Debugging (NangoHQ/nango, 13k stars), React Testing (affaan-m/ECC, 276k stars), E2E Testing (ericrisco/rsc-harness, 180 stars) and OpenHarness End-to-End Evals (HKUDS/OpenHarness, 16k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Verify Gooeypi?
am-will (a GitHub user) maintains it in am-will/gooey-pi, which has 943 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 9, 2026.
Source: am-will/gooey-pi on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.