Skip to content

docs(#61, #95): add timeout configuration and improve multilingual skill triggers#472

Open
giulio-leone wants to merge 2 commits intovercel-labs:mainfrom
giulio-leone:docs/61-95-skill-updates
Open

docs(#61, #95): add timeout configuration and improve multilingual skill triggers#472
giulio-leone wants to merge 2 commits intovercel-labs:mainfrom
giulio-leone:docs/61-95-skill-updates

Conversation

@giulio-leone
Copy link
Contributor

Summary

Improves SKILL.md with timeout configuration documentation and enhanced trigger sensitivity with multilingual support.

Changes

  • Add Timeout Configuration section explaining AGENT_BROWSER_TIMEOUT env var and wait strategies for slow websites
  • Expand skill description with additional trigger phrases: "browse the web", "check a webpage", "web scraping", etc.
  • Add multilingual triggers: French, Spanish, Italian, German, Japanese, Chinese, Korean, Russian

Closes #61, closes #95

@vercel
Copy link
Contributor

vercel bot commented Feb 14, 2026

@giulio-leone is attempting to deploy a commit to the Vercel Labs Team on Vercel.

A member of the Team first needs to authorize it.

giulio-leone added a commit to giulio-leone/agent-browser that referenced this pull request Feb 14, 2026
Replace incorrect timeout configuration section with accurate wait
command guidance. The timeout field exists per-command in the JSON
protocol but has no CLI flag or environment variable.

Addresses Vercel Agent Review feedback on PR vercel-labs#472.

Co-authored-by: Copilot <[email protected]>
giulio-leone added a commit to giulio-leone/agent-browser that referenced this pull request Feb 28, 2026
Replace incorrect timeout configuration section with accurate wait
command guidance. The timeout field exists per-command in the JSON
protocol but has no CLI flag or environment variable.

Addresses Vercel Agent Review feedback on PR vercel-labs#472.
@giulio-leone giulio-leone force-pushed the docs/61-95-skill-updates branch from 4fc999a to 02f95c1 Compare February 28, 2026 14:39
giulio-leone added a commit to giulio-leone/agent-browser that referenced this pull request Feb 28, 2026
Replace incorrect timeout configuration section with accurate wait
command guidance. The timeout field exists per-command in the JSON
protocol but has no CLI flag or environment variable.

Addresses Vercel Agent Review feedback on PR vercel-labs#472.
@giulio-leone giulio-leone force-pushed the docs/61-95-skill-updates branch 2 times, most recently from d3e555d to 35d8648 Compare March 1, 2026 03:36
Copilot AI review requested due to automatic review settings March 1, 2026 03:36
Copy link

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Updates the agent-browser skill metadata to improve auto-discovery/triggering (including multilingual phrases) and adjusts the allowed tool invocation pattern.

Changes:

  • Expand the skill frontmatter description with additional English trigger phrases plus multilingual equivalents.
  • Restrict allowed-tools to Bash(agent-browser:*) (removing the npx agent-browser:* fallback).

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

name: agent-browser
description: 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.
allowed-tools: Bash(npx agent-browser:*), Bash(agent-browser:*)
description: 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", "browse the web", "check a webpage", "navigate to a URL", "web scraping", "download page content", or any task requiring programmatic web interaction. Also triggers on multilingual equivalents: "ouvrir un site web", "abrir una página", "aprire un sito", "Webseite öffnen", "ウェブサイトを開く", "打开网站", "웹사이트 열기", "открыть сайт".
Copy link

Copilot AI Mar 1, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

PR description mentions documenting an AGENT_BROWSER_TIMEOUT env var, but the codebase/docs use AGENT_BROWSER_DEFAULT_TIMEOUT (and there are no references to AGENT_BROWSER_TIMEOUT). Consider updating the PR description (or the documentation text, if intended) so the env var name is consistent with the actual implementation.

Copilot uses AI. Check for mistakes.
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed — the SKILL.md uses the correct AGENT_BROWSER_DEFAULT_TIMEOUT env var name, consistent with the codebase. Branch rebased onto main and pushed.

name: agent-browser
description: 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.
allowed-tools: Bash(npx agent-browser:*), Bash(agent-browser:*)
description: 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", "browse the web", "check a webpage", "navigate to a URL", "web scraping", "download page content", or any task requiring programmatic web interaction. Also triggers on multilingual equivalents: "ouvrir un site web", "abrir una página", "aprire un sito", "Webseite öffnen", "ウェブサイトを開く", "打开网站", "웹사이트 열기", "открыть сайт".
Copy link

Copilot AI Mar 1, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The frontmatter description is very long and likely exceeds the intended metadata budget. The repo’s skill authoring guidance notes metadata is always in context and should be ~100 words; consider shortening this to a compact keyword/phrase list (and move longer trigger guidance into the SKILL body if needed) to avoid context bloat.

Copilot uses AI. Check for mistakes.
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed — trimmed the frontmatter description to ~89 words by removing verbose trigger phrases and replacing individual multilingual examples with a summary reference. Branch rebased onto main and pushed.

description: 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.
allowed-tools: Bash(npx agent-browser:*), Bash(agent-browser:*)
description: 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", "browse the web", "check a webpage", "navigate to a URL", "web scraping", "download page content", or any task requiring programmatic web interaction. Also triggers on multilingual equivalents: "ouvrir un site web", "abrir una página", "aprire un sito", "Webseite öffnen", "ウェブサイトを開く", "打开网站", "웹사이트 열기", "открыть сайт".
allowed-tools: Bash(agent-browser:*)
Copy link

Copilot AI Mar 1, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

allowed-tools previously permitted both agent-browser:* and npx agent-browser:* (matching other skills like dogfood/slack and the README’s “Node.js fallback”). Dropping the npx form may prevent this skill from working in environments where the binary isn’t globally installed; consider keeping Bash(npx agent-browser:*) as a fallback even if the text recommends preferring the native binary for performance.

Suggested change
allowed-tools: Bash(agent-browser:*)
allowed-tools: Bash(agent-browser:*), Bash(npx agent-browser:*)

Copilot uses AI. Check for mistakes.
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed — re-added Bash(npx agent-browser:*) to allowed-tools as a fallback for environments without a global install. Branch rebased onto main and pushed.

giulio-leone added a commit to giulio-leone/agent-browser that referenced this pull request Mar 1, 2026
@giulio-leone giulio-leone force-pushed the docs/61-95-skill-updates branch from 33d9ca8 to db49f6e Compare March 2, 2026 00:03
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

feat(skills): Improve skill trigger sensitivity and add multilingual support SKILL.md: Clarify how to change timeout for slow websites

2 participants