analyze-code
CommandAnalyze code quality, identify issues, and suggest improvements.
Create a visual UX mockup for a requested feature or screen.
> /plugin marketplace add nimbalyst/nimbalyst> /plugin install nimbalyst-wiki@nimbalyst
packageVersion: 1.0.0 packageId: core description: Create a visual UX mockup for a requested feature or screen.
Create a visual UX mockup for: {{arg1}}
First, determine if this is: 1. **New screen/feature** - Something that doesn't exist yet 2. **Modification to existing screen** - Changes to an existing UI in the codebase
1. **Parse the request** - Understand what UI/screen/feature the user wants to mock up
2. **Check for style guide** - Look for `nimbalyst-local/existing-screens/style-guide.mockup.html`
3. **Create mockup file** - Create `nimbalyst-local/mockups/[descriptive-name].mockup.html`
4. **Build the mockup** - Write HTML with inline CSS that matches the style guide, ensuring consistency with the existing app
5. **Verify visually** - Use the Task tool to spawn a sub-agent that will:
**CRITICAL: New screen mockups should look realistic and consistent with the existing app.**
1. **Identify the screen** - Determine which existing screen/component is being modified
2. **Check for cached replica** - Look in `nimbalyst-local/existing-screens/` for `[screen-name].mockup.html`
3. **If cached replica EXISTS**:
4. **If cached replica DOES NOT EXIST**:
5. **Copy to mockups** - Copy the existing-screen replica to `nimbalyst-local/mockups/[descriptive-name].mockup.html`
6. **Apply modifications** - Edit the copy in mockups to include the proposed changes, keeping modifications **in full color**
7. **Verify visually** - Use the Task tool to spawn a sub-agent to capture and verify the mockup
8. **If the replica was updated or created and you were not able to obtain a screenshot**, after creating the replica, prompt the user in bold: **If you are able to give me a screenshot of the existing screen I can improve the mockup**
Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks. Free, MIT-licensed desktop app for macOS, Windows, Linux, with mobile companion for iOS and Android.
Analyze code quality, identify issues, and suggest improvements.
Audit recent AI coding sessions to find repeated mistakes, speed losses, and missed Nimbalyst tool usage — then propose harness…
Triage pnpm audit findings and produce a prioritized, supply-chain-cautious package-update plan, then apply approved batches
Survey recently triaged GitHub issues, propose the ones safe to fix without a product decision, and fan the selected ones out to…
Gather details and draft an actionable bug report for developers.
Shortcut for "continue working" — pick the work in flight back up exactly where it stopped and keep going until it is done or…