Generate complete user documentation for a web app with screenshots. Browses the app via browser automation, screenshots every screen, and produces a structured user guide with step-by-step instructions, annotated screenshots, workflow diagrams, and reference tables. Supports quick (key screens), standard (all pages), thorough (every state and flow), and exhaustive (publishable documentation suite). Triggers: 'document the app', 'user guide', 'app documentation', 'screenshot docs', 'generate user docs', 'help docs', 'how-to guide', 'write the docs'.
npx skills add https://github.com/jezweb/claude-skills --skill app-docs
Browse a running web app, screenshot every screen, and produce documentation good enough to publish. Not a screenshot dump — a structured guide that teaches someone how to use the app.
Same as ux-audit — Chrome MCP, Playwright MCP, or playwright-cli.
Same as ux-audit — prefer deployed/live URL over localhost.
| Depth | Screenshots | What it produces | Duration |
|-------|------------|-----------------|----------|
| quick | ~10 | Single-page quick-start guide. Key screens, happy path only. | 10-15 min |
| standard | ~30 | Full user guide. All pages, primary workflows, reference tables. | 30-60 min |
| thorough | ~80+ | Comprehensive guide. All states, mobile views, every CRUD flow, troubleshooting. | 1-3 hours |
| exhaustive | ~150+ | Publishable documentation suite. Everything in thorough plus: getting started tutorial, feature-by-feature deep dives, admin guide, keyboard shortcut reference, FAQ, and HTML version. | 3-6 hours |
Default: standard
Ask the user:
Navigate the app and build a complete page inventory:
Create a task list to track documentation progress.
For each page in the inventory:
docs/screenshots/ with descriptive namesFor each page, write:
## [Page Name]
[One sentence: what this page is for and when you'd use it]

### What You'll See
[Describe the key elements: sidebar shows X, main area shows Y, toolbar has Z]
### What You Can Do
[List the actions available, each as a brief description]
### How To: [Primary Action]
1. [Step with screenshot reference]
2. [Step]
3. [Step — screenshot the result]
> **Tip:** [Helpful shortcut or non-obvious feature]
For interactive pages, document step-by-step with screenshots at each significant step:
### How To: Add a New Client
1. Click the **"Add Client"** button in the top right

2. Fill in the required fields — Name and Email are required, everything else is optional

3. Click **"Save"** — you'll be taken to the new client's detail page

> **Tip:** You can also press **Cmd+N** from anywhere to create a new client.
| Extra | quick | standard | thorough | exhaustive |
|-------|-------|----------|----------|-----------|
| Empty states | Skip | Note | Screenshot + document | Screenshot + suggest improvements |
| Error states | Skip | Note | Trigger + screenshot | Every validation error documented |
| Dark mode | Skip | Skip | Screenshot key pages | Screenshot every page |
| Mobile (375px) | Skip | Skip | Screenshot key pages | Screenshot every page |
| All CRUD | Skip | Primary only | Every operation | Every operation + edge cases |
| Settings/config | Skip | List options | Document each | Document each with examples |
| Keyboard shortcuts | Skip | List if visible | Full reference table | Dedicated section |
| Search/filters | Skip | Mention | Document each filter | Document every combination |
| Permissions/roles | Skip | Skip | Note differences | Separate section per role |
| API/integrations | Skip | Skip | Mention if present | Document endpoints + examples |
Beyond per-page documentation:
Getting Started (all depths):
## Getting Started
### Accessing [App Name]
- URL: [production URL]
- Supported browsers: Chrome, Firefox, Safari, Edge
- Mobile: [responsive / PWA / not supported]
### Logging In
[Screenshot of login page + steps]
### Your First 5 Minutes
1. [First thing to do after logging in]
2. [Second thing — the quick win]
3. [Third thing — explore the main feature]
Navigation Guide (standard+):
## Navigation
### Sidebar
[Screenshot with annotations describing each section]
### Quick Actions
- **Cmd+K**: Quick switcher — jump to any page or record
- **Cmd+N**: Create new [item]
[Other shortcuts]
### Breadcrumbs / Back Navigation
[How to navigate back, where breadcrumbs appear]
Keyboard Shortcuts Reference (thorough+):
## Keyboard Shortcuts
| Shortcut | Action |
|----------|--------|
| Cmd+K | Quick switcher |
| Cmd+N | New [item] |
| Cmd+S | Save |
| Escape | Close dialog / cancel |
Troubleshooting (thorough+):
## Troubleshooting
### [Error message or symptom]
**What it means**: [explanation]
**How to fix**: [steps]
### Common Questions
[FAQ generated from what would confuse a new user — based on the documentation process itself]
Admin Guide (exhaustive):
## Admin Guide
### User Management
[How to invite users, set roles, remove access]
### Settings Reference
| Setting | What it does | Default | Recommendation |
[Every setting documented]
### Data Management
[Export, import, backup, delete account]
Markdown (default): docs/USER_GUIDE.md
!altHTML (exhaustive depth, or on request): docs/user-guide.html
@media print)Screenshot naming: docs/screenshots/NN-section-description.png
01-, 02-, 03-01-dashboard-, 05-clients-, 12-settings--overview.png, -add-form.png, -saved-confirmation.pngMix screenshots with diagrams where it helps understanding:
Workflow diagrams (text-based, no external tools):
### How a Client Moves Through the System
New Enquiry → Create Client → Add Policy → Send Renewal → Archive
↓ ↓ ↓ ↓ ↓
[Email] [Client Page] [Policy Page] [Email Outbox] [Archive]
Annotated screenshots: When a screenshot needs callouts, describe them in the text:

The dashboard shows:
- **A** (top left): Your client count and active policies
- **B** (centre): Items needing attention today
- **C** (right): Recent activity feed
UI element reference: For complex pages, a labelled diagram helps:
### Editor Layout
| Area | What it does |
|------|-------------|
| Left panel | Folder tree — organise your notes |
| Centre panel | Note list — shows notes in the selected folder |
| Right panel | Editor — write and preview your note |
| Top bar | Navigation, search (Cmd+K), and view toggles |
The documentation should be good enough that:
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
| 所有联网操作必须通过此 skill 处理,包括:搜索、网页抓取、登录后操作、动态页面交互等。 触发场景:用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容(小红书、微博、推特等)、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。
Take jezweb/app-docs from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.