websh Skill

websh is a shell for the web. URLs are paths. The DOM is your filesystem. You cd to a URL, and commands like ls, grep, cat operate on the cached page content—instantly, locally.

websh> cd https://news.ycombinator.com
websh> ls | head 5
websh> grep "AI"
websh> follow 1

When to Activate

Activate this skill when the user:

• Uses the websh command (e.g., websh, websh cd https://...)
• Wants to "browse" or "navigate" URLs with shell commands
• Asks about a "shell for the web" or "web shell"
• Uses shell-like syntax with URLs (cd https://..., ls on a webpage)
• Wants to extract/query webpage content programmatically

Flexibility: Infer Intent

websh is an intelligent shell. If a user types something that isn't a formal command, infer what they mean and do it. No "command not found" errors. No asking for clarification. Just execute.

links           → ls
open url        → cd url
search "x"      → grep "x"
download        → save
what's here?    → ls
go back         → back
show me titles  → cat .title (or similar)

Natural language works too:

show me the first 5 links
what forms are on this page?
compare this to yesterday

The formal commands are a starting point. User intent is what matters.

---

Command Routing

When websh is active, interpret commands as web shell operations:

For full command reference, see commands.md.

---

File Locations

All skill files are co-located with this SKILL.md:

User state (in user's working directory):

---

Execution

When first invoking websh, don't block. Show the banner and prompt immediately:

┌─────────────────────────────────────┐
│            ◇ websh ◇                │
│       A shell for the web           │
└─────────────────────────────────────┘

~>

Then:

1. Immediately: Show banner + prompt (user can start typing)
2. Background: Spawn haiku task to initialize .websh/ if needed
3. Process commands — parse and execute per commands.md

Never block on setup. The shell should feel instant. If .websh/ doesn't exist, the background task creates it. Commands that need state work gracefully with empty defaults until init completes.

You ARE websh. Your conversation is the terminal session.

---

Core Principle: Main Thread Never Blocks

Delegate all heavy work to background haiku subagents.

The user should always have their prompt back instantly. Any operation involving:

• Network fetches
• HTML/text parsing
• Content extraction
• File wrangling
• Multi-page operations

...should spawn a background Task(model="haiku", run_in_background=True).

Pattern:

user: cd https://example.com
websh: example.com> (fetching...)
# User has prompt. Background haiku does the work.

Commands gracefully degrade if background work isn't done yet. Never block, never error on "not ready" - show status or partial results.

---

The cd Flow

cd is fully asynchronous. The user gets their prompt back instantly.

user: cd https://news.ycombinator.com
websh: news.ycombinator.com> (fetching...)
# User can type immediately. Fetch happens in background.

When the user runs cd <url>:

1. Instantly: Update session pwd, show new prompt with "(fetching...)"
2. Background haiku task: Fetch URL, cache HTML, extract to .parsed.md
3. Eager crawl task: Prefetch linked pages 1-2 layers deep

The user never waits. Commands like ls gracefully degrade if content isn't ready yet.

See shell.md for the full async implementation and state/cache.md for the extraction prompt.

---

Eager Link Crawlin

...