web-browsing
Skill0 starsChanged 9 months agoMITView on GitHub
Use before any web browsing task — navigating sites, filling forms, clicking buttons, or extracting data. Routes to site-specific skills; universal protocol as fallback.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- shino369/claude-code-personal-workspacetheir own version, first seen Nov 8, 2026
- chenwei791129/agent-skillstheir own version, first seen Oct 19, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- shino369/claude-code-personal-workspace★ 4same name
- chenwei791129/agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- caniuseSkill
- crates-ioSkill
- news-ycombinatorSkill
- mdn-web-docsSkill
- pub-devSkill
- pypiSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Before opening a browser, check whether a skill exists for the target domain:
- Distinctive: line 61
Use this priority order (fastest to slowest):
- Very specific: line 95
Detect page load without guessing: Use read_page — if it returns content, the page is ready.
- Distinctive: line 116
Never silently fail or loop.
- Very specific: line 137
Use get_page_text before screenshots for text extraction.
- Very specific: line 138
Use find before read_page before screenshots — escalate from fast to slow.
- Distinctive: line 139
Never wait "just in case" — check if the page is ready, don't assume it isn't.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Web Browsing — Master Router
Invoke this skill before any browser task. It routes you to a site-specific skill when one is installed, and provides universal fallback navigation for everything else.
Step 1: Check for a Site-Specific Skill
Before opening a browser, check whether a skill exists for the target domain:
| Domain | Skill | Covers |
caniuse.com | caniuse | Browser compat data — programmatic path via GitHub raw, shadow DOM gotchas |
pub.dev | pub-dev | Dart/Flutter packages — REST API, search, score, advisories |
developer.mozilla.org | mdn-web-docs | MDN search API, article navigation, reference lookup |
crates.io | crates-io | Rust crates — REST API, search, versions, dependencies |
pypi.org | pypi | Python packages — JSON API, search, release data |
news.ycombinator.com | hacker-news | HN feed, comments, search via Algolia API |
If the target domain is in this table: Invoke the matching skill immediately. Do not open a browser until you have read it.
If the target domain is not in this table: Continue to Step 2.
Step 2: Universal Navigation Protocol
For sites without a specific skill, follow this protocol to navigate efficiently with minimum screenshots.
Reconnaissance (1 screenshot max)
1. Navigate to the URL
2. Take ONE screenshot
3. Use read_page with filter="interactive" to get all clickable/input elements
4. From this single pass, identify:
- Navigation structure (top bar, sidebar, hamburger)
- Search capability
- Auth state (login buttons vs user avatar)
- Blocking overlays (cookie banners, modals, paywalls)Clear Obstacles First
Handle these BEFORE your actual task — they block everything:
| Obstacle | Action |
| Cookie banner | Click "Reject All" or most privacy-preserving option |
| Login wall | Stop — tell the user; never guess credentials |
| Newsletter popup | Find X/close button; if none, press Escape |
| CAPTCHA | Stop — tell the user; do not attempt to solve |
| "Accept terms" modal | Stop — ask user permission before accepting |
| Paywall | Stop — tell the user the content is paywalled |
Navigate to Target
Use this priority order (fastest to slowest):
- Direct URL — Construct and navigate directly if possible. Zero wasted clicks.
- Search — Type query into site's search field, submit, scan results.
- Navigation menu — Use
read_pageorfindtool to locate nav links. - Scroll and scan — Last resort. Scroll methodically, screenshot to orient.
Element Finding (fastest to slowest)
| Tier | Method | Use When |
| 1 | find tool with natural language | Buttons, links, labeled elements |
| 2 | read_page filter="interactive" | Full page inventory, forms with many fields |
| 3 | javascript_tool with CSS selector | Known selectors, dynamic/hidden elements |
| 4 | Screenshot + analyze coordinates | Last resort — element unreachable programmatically |
Anti-patterns:
- Taking a screenshot to find a button you could
findby label - Clicking by coordinate when you have a ref_id
- Taking multiple screenshots to "make sure" (
read_pageconfirming an element is enough)
Timing and Waiting
| Situation | Wait | Duration |
| After link click (navigation) | wait | 1–2s |
| After form submit | wait | 2–3s |
| After AJAX / dynamic content | wait | 1–2s |
| SPA / dashboard initial load | wait | 3–5s |
| Between form field fills | none | — |
| After tab/accordion on same page | none | — |
Detect page load without guessing: Use read_page — if it returns content, the page is ready. Check document.readyState === 'complete' via javascript_tool for heavy SPAs.
Data Extraction
| Data type | Method |
| Article / documentation text | get_page_text — order of magnitude faster than screenshots |
| Tables and lists | javascript_tool → query table/list elements |
| Visual layout or positioning | Screenshot → analyze |
| Paginated data | Extract page → find "Next" → loop |
Error Recovery
- Retry once — Click didn't register? Try again. Page didn't load? Wait 2s, check again.
- Alternative path — Button not clickable? Try keyboard shortcut. Navigation broken? Try direct URL.
- Tell the user — Auth required, CAPTCHA blocking, site down, element truly missing.
Never silently fail or loop. Three attempts max, then escalate to the user.
Common Site Patterns
SPA (React/Vue/Angular): URL changes may not trigger real page loads. Wait for dynamic content, not just document.readyState. Use read_network_requests to detect when API calls finish.
Dashboard/Admin: Left sidebar navigation, breadcrumbs for orientation, settings under gear icon or bottom of sidebar.
E-Commerce: Products at /product/, /p/, or /dp/. Cart at /cart. Search via ?q= or ?search= parameter. Account at /account.
API-backed sites: Try site.com/api/ or check for OpenAPI spec at /openapi.json, /swagger.json, /api/docs. Programmatic API calls are always faster than browser navigation when available.
Performance Rules
- One screenshot to orient, then use programmatic tools.
- Construct URLs directly when possible — avoids clicking through menus.
- Batch form inputs — read all fields once, fill all in sequence, no screenshots between.
- Use
get_page_textbefore screenshots for text extraction. - Use
findbeforeread_pagebefore screenshots — escalate from fast to slow. - Never wait "just in case" — check if the page is ready, don't assume it isn't.
- Tell the user what's happening if something is slow or broken.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

