Agent skill

Window Simulator

by naveedharri in naveedharri/baalda

Run Baalda's real desktop UI in a local browser with synthetic vault data to preview Windows or macOS layouts, investigate visual bugs, and capture screenshots from a Mac.

Apache-2.0Auto-check passedKnowledge Management

Install Window Simulator

skills CLI
$ npx skills add naveedharri/baalda --skill window-simulator -a claude-code

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

GitHub CLI
$ gh skill install naveedharri/baalda window-simulator --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/naveedharri/baalda.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/window-simulator .claude/skills/window-simulator && 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
window-simulator
GitHub stars
154
Token cost
~1.2k tokens
SKILL.md length
614 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

Run Baalda's real desktop UI in a local browser with synthetic vault data to preview Windows or macOS layouts, investigate visual bugs, and capture screenshots from a Mac.

  • Browser UI simulation
  • SKILL.md covers Start on a Mac, Preview and investigate and Verify and hand off
  • Calls pnpm and cargo
  • Native window behavior still requires the target OS

What it does

Window Simulator is an agent skill from naveedharri/baalda. Run Baalda's real desktop UI in a local browser with synthetic vault data to preview Windows or macOS layouts, investigate visual bugs, and capture screenshots from a Mac. Use for browser UI simulation; native window behavior still requires the target OS.

Its SKILL.md is about 1.2k 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 Knowledge Management, covering Second brain. It works with macOS. The repository describes itself as: The team second brain. Plain Markdown files on your disk, edited together in real time, and read and written by your AI like a teammate. The licence is Apache-2.0.

When your agent uses it

  • Browser UI simulation
  • Native window behavior still requires the target OS

Example prompts

  • “/window-simulator”

What it can do on your machine

Read from SKILL.md and the folder at commit 2e988ad. 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:

    • pnpm
    • cargo

    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

Window Simulator loads about 1.2k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 614 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 naveedharri/baalda at commit 2e988ad, republished under its Apache-2.0 licence (© naveedharri). 614 words, ~1,210 tokens.

Download SKILL.mdSave it as .claude/skills/window-simulator/SKILL.md (or your agent's skills folder).
name
window-simulator
description
Run Baalda's real desktop UI in a local browser with synthetic vault data to preview Windows or macOS layouts, investigate visual bugs, and capture screenshots from a Mac. Use for browser UI simulation; native window behavior still requires the target OS.

Window simulator

Use the tracked harness in app/apps/desktop/dev/window-simulator/. It imports the real React app, styles, and editor after installing Tauri IPC and server mocks. Both platform modes use the same synthetic vault and members so missing fixture data cannot masquerade as a platform difference.

Start on a Mac

Resolve paths from this Baalda checkout. Read AGENTS.md and CLAUDE.md before changing product code. Install dependencies with pnpm install in app/ if needed.

From app/apps/desktop/:

bash
pnpm run simulate:windows
# Or, for the macOS layout:
pnpm run simulate:macos

The simulator uses port 1425, separate from Tauri development on 1420. Once the server is running, reuse it for both URLs:

  • Windows: http://localhost:1425/dev/window-simulator/?platform=windows
  • macOS: http://localhost:1425/dev/window-simulator/?platform=macos
  • Add &theme=dark or &sidebarHidden=true for those states.

Keep the Vite process/session handle for logs and cleanup. If the port is busy, check whether this checkout's simulator is already serving there; do not stop an unrelated process or launch a second server needlessly. A browser reload resets the fixture's in-memory changes.

Preview and investigate

Use available browser tooling to open the real simulator URL. For a large review screenshot use a 1600×1000 viewport; also inspect 720×600 when changing window chrome or panel layout. Compare Windows and macOS with the same theme, viewport, sidebar state, and selected note. A macOS browser simulation cannot draw the operating system's actual traffic lights. The platform parameter selects the app's platform branch; it does not change the browser engine into WebView2 or WKWebView.

Navigate the surfaces affected by the change. For titlebar work, include the sidebar shown/hidden, the Activity/Versions panel, graph, welcome screen, and settings overlays. On Windows, opening the Activity/Versions panel hides the window caption controls; its own close button stays at the top edge. Closing the panel restores the caption controls. For avatars, inspect a vault icon and several character avatars in the same document: shared SVG resource IDs can fail in the full app even when an isolated gallery renders correctly.

If a panel is unexpectedly empty or an action is missing, inspect the mock response and the consuming API type before blaming the platform. The harness must return complete, correctly shaped data for the surface being reviewed. For example, /api/auth-methods controls the bug-report button, member roles control manager actions, and a public link requires a real-shaped url field. Add missing synthetic responses in the harness rather than changing production authorization or visibility rules to make a preview appear populated. Keep the fake API session and UI store in agreement: profile saves re-read the session, and seeding only the visible signed-in state produces a false sign-out when the client has no demo token.

Show full SKILL.md (196 more words)Show less

The harness is development-only. Keep sample identities, links, and credentials obviously synthetic. Preserve mocked IPC/network boundaries; do not connect the simulator to a real vault, account, database, or model provider. Preview actions must not send email, publish notes, change access on a real server, or make payments. Do not save real credentials in fixtures or screenshots.

Verify and hand off

Follow the current task's testing arrangement. If the user wants visual review before a single final testing pass, finish the preview edits and wait for that review before starting the pass. Relevant product tests, type checking, and a Windows-target frontend build remain separate from the browser simulation:

bash
# From app/apps/desktop; select tests appropriate to the actual change.
pnpm exec vitest run <test-files>
pnpm exec tsc --noEmit
TAURI_ENV_PLATFORM=windows pnpm run build

Save screenshots in an ignored artifacts.local/ directory or an OS temporary directory, never alongside tracked fixtures. Show the user the screenshot and the live URL, and leave the simulator running when it is the requested preview. Keep the user's latest reviewed layout in the deliverable tab.

Report browser checks as simulation checks. Native Windows drag, resize, Snap, DPI scaling, WebView2-specific behavior, caption commands, and packaged CSP need appropriate native validation; macOS cargo check does not compile Windows-only Rust branches. This workflow needs neither a backend nor destructive server tests.

© naveedharri, Apache-2.0. 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/window-simulator of naveedharri/baalda.

Open the folder on GitHubat commit 2e988ad

Compare with similar skills

Window Simulator 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.

Window Simulator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Window Simulator this skillnaveedharri/baalda154—~1.2kAutomated safety check: PassApache-2.0
Greenbubbles Personal Memorybojieli/greenbubbles352—~669Automated safety check: PassMIT
Second BrainNicholasSpisak/second-brain7361 repos~1.5kAutomated safety check: NotesNone
3D Brainnateherkai/AIS-OS1.6k—~2.1kAutomated safety check: PassCustom licence
Obsidian Canvas BoardsAgriciDaniel/claude-obsidian15k—~1.4kAutomated safety check: PassMIT
Icm ArchitectRinDig/icm-architect1.8k—~3.2kAutomated safety check: PassMIT

Similar skills

  • Greenbubbles Personal Memory

    bojieli/greenbubbles

    Build or revise private, cited Markdown notes from the user's WeChat history in the current agent session.

    352 GitHub stars~669 tokensUpdated 5 days ago
    Knowledge ManagementAuto-check passed
  • Second Brain

    NicholasSpisak/second-brain

    Set up a new Obsidian knowledge base with the LLM Wiki pattern.

    736 GitHub starsUsed in 1 repo~1.5k tokens
    Knowledge ManagementAuto-check: notes
  • 3D Brain

    nateherkai/AIS-OS

    A skill your agent uses when someone asks to build a 3D brain, visualize their AIOS or second brain, turn their knowledge into an interactive graph, or run /3d-brain or /3D brain.

    1.6k GitHub stars~2.1k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • Obsidian Canvas Boards

    AgriciDaniel/claude-obsidian

    Creates, inspects and updates Obsidian JSON Canvas boards in a vault, with text, file, link, group and edge nodes, using safe recoverable edits.

    15k GitHub stars~1.4k tokensUpdated 27 days ago
    Knowledge ManagementAuto-check passed
  • Icm Architect

    RinDig/icm-architect

    Design any process, idea, problem, or body of knowledge into an ICM (Interpretable Context Methodology) workspace — folder structure as agent architecture — or restructure an existing folder, repo…

    1.8k GitHub stars~3.2k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • Obsidian CLI Read Transport

    AgriciDaniel/claude-obsidian

    Detects and uses the official Obsidian command-line interface for read-only vault access, falling back to direct file reads, while all mutations stay on a separate transaction core.

    15k GitHub starsUsed in 1 repo~762 tokens
    Knowledge ManagementAuto-check passed

More from naveedharri/baalda

  • Baalda Guide

    naveedharri/baalda

    Answer any question about Baalda (the team second-brain app at baalda.com) in plain, non-technical language — what it is, what it can and cannot do, which file formats it supports (Markdown, images…

    154 GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Relaunch

    naveedharri/baalda

    Kill the running Baalda desktop (Tauri) dev instance AND the backend server, then launch fresh instances of both.

    154 GitHub stars~870 tokensUpdated today
    Auto-check passed

Works with

Questions about Window Simulator

What does Window Simulator do?

Run Baalda's real desktop UI in a local browser with synthetic vault data to preview Windows or macOS layouts, investigate visual bugs, and capture screenshots from a Mac. Window Simulator is an agent skill from naveedharri/baalda. Run Baalda's real desktop UI in a local browser with synthetic vault data to preview Windows or macOS layouts, investigate visual bugs, and capture screenshots from a Mac.

When should I use Window Simulator?

Window Simulator fits situations like: browser UI simulation; native window behavior still requires the target OS.

How do I install Window Simulator in Claude Code?

Run `npx skills add naveedharri/baalda --skill window-simulator -a claude-code`. Or copy the skill folder (.agents/skills/window-simulator in naveedharri/baalda) into .claude/skills/window-simulator in your project. Claude Code loads it when a task matches its description.

How do I install Window Simulator in Codex?

Run `npx skills add naveedharri/baalda --skill window-simulator -a codex`. Or copy the skill folder (.agents/skills/window-simulator in naveedharri/baalda) into .agents/skills/window-simulator in your project. Codex loads it when a task matches its description.

Can I use Window Simulator 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 naveedharri/baalda --skill window-simulator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/window-simulator, .gemini/skills/window-simulator, .github/skills/window-simulator and .opencode/skills/window-simulator in your project.

What does Window Simulator need to run?

Going by SKILL.md and its folder, Window Simulator needs the command-line tools its instructions call (pnpm and cargo).

Does Window Simulator 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 Window Simulator 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 Window Simulator use?

Window Simulator is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Window Simulator use?

About 1.2k tokens (SKILL.md is roughly 4.8k 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 Window Simulator?

Skills that share tags, products or a category with Window Simulator: Greenbubbles Personal Memory (bojieli/greenbubbles, 352 stars), Second Brain (NicholasSpisak/second-brain, 736 stars), 3D Brain (nateherkai/AIS-OS, 1.6k stars) and Obsidian Canvas Boards (AgriciDaniel/claude-obsidian, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Window Simulator?

naveedharri (a GitHub user) maintains it in naveedharri/baalda, which has 154 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.

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