browse-diff
Open the ai-review desktop app to visually browse a diff. Use when the user wants to see changes in a visual diff viewer without a review feedback loop — just for viewing.
Best use case
browse-diff is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Open the ai-review desktop app to visually browse a diff. Use when the user wants to see changes in a visual diff viewer without a review feedback loop — just for viewing.
Teams using browse-diff should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/browse-diff/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How browse-diff Compares
| Feature / Agent | browse-diff | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Open the ai-review desktop app to visually browse a diff. Use when the user wants to see changes in a visual diff viewer without a review feedback loop — just for viewing.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
Open the ai-review desktop app (`air`) to let the human visually explore a diff. No feedback loop — the app opens and you continue working.
## Steps
1. **Determine what to show.** Check these in priority order to pick the right `air` invocation:
a. **Specific commit or range requested by the user:**
Run `air --commit <hash>` or `air --commits <range>`.
b. **Uncommitted changes exist** (staged or unstaged, check via `git status --porcelain`):
Run `air` with no flags. This shows the working directory diff.
c. **Clean tree, on a gg stack branch** — the current branch matches the `user/name` pattern (no `--` in the name part) and `.git/gg/config.json` exists:
Read the gg base branch from config (parse `defaults.base`, fall back to `main`). Run:
```
air --commits <gg-base>..HEAD
```
This shows the full stack diff, matching what ai-review displays when opening a gg stack.
d. **Clean tree, on a feature branch** (not main/master):
Determine the base branch (`main` or `master`, whichever exists). Run:
```
air --branch <base-branch>
```
e. **Clean tree, on main/master with unpushed commits:**
Run `git log origin/main..HEAD --oneline --reverse` (or `origin/master`) and take the first commit hash. Run:
```
air --commit <first-unpushed-commit-hash>
```
f. **None of the above:** Run `air` with no flags (empty diff — the app handles it).
2. **Inform the human.** Tell them you've opened ai-review so they can browse the diff. Continue working without waiting.
## Notes
- Do NOT use `--wait`. This skill is fire-and-forget.
- If `air` is not found, tell the user to install via `brew install --cask mrmans0n/tap/ai-review` (macOS) or build from source at https://github.com/mrmans0n/ai-review.
- If the diff is empty, inform the user there are no changes to view.Related Skills
show-changes
Present completed work to the human for optional review via the ai-review desktop app. Use when you've finished a task and want the human to see what you did — they can optionally leave feedback.
review-commits
Open existing commits in the ai-review desktop app for review. Use when you need to review, understand, or get feedback on specific commits, a commit range, or a branch diff — not your own recent work, but existing history.
human-review
Request human code review via the ai-review desktop app. Use when code changes are complete and ready for a final human review before committing or merging. Opens an interactive diff viewer where the human can leave inline comments, then returns their feedback.
browser-debug
Capture browser console, network, and performance logs for debugging. Auto-loads when debugging browser issues, analyzing errors, or investigating page behavior. Provides systematic log capture workflow using Chrome DevTools MCP.
browser-animation-video
Use when create browser-based motion graphics with Framer Motion, GSAP, and Tailwind.
extracting-browser-history-artifacts
从 Chrome、Firefox 和 Edge 中提取并分析浏览器历史记录、Cookie、缓存、下载记录和书签，以获取用户网络活动的取证证据。
analyzing-browser-forensics-with-hindsight
使用 Hindsight 分析基于 Chromium 的浏览器痕迹，从 Chrome、Edge、Brave 和 Opera 中提取浏览历史、下载记录、Cookie、缓存内容、自动填充数据、已保存密码和浏览器扩展，用于取证调查。
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
xero-browser
General Xero browser automation notes. Use when automating any Xero page with agent-browser — covers non-standard UI patterns, waiting, and dropdown menus.
agent-browser-viewport
Size the agent-browser Chromium window to fill its current screen, leaving a configurable bottom margin for the desktop panel. Use before any agent-browser automation that needs the full screen visible without elements overlapping or scrolling off (e.g. Xero, dense web apps).
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.