Shell Tool · engineering · Sentinel

Deploy to Cloudflare

Ship the current /work to Pages, Workers, or Containers — then verify the live URL.

Updated today

View as MarkdownsentinelsonnetstandardMax 10 turns

Overview

Cloudflare-only deploy pipeline. Detects project shape (static HTML → Pages, single Worker script → wrangler deploy, Dockerfile → Containers). Consults cf-containers/SKILL.md for container-specific quirks (envVar timing, rollout caching). After wrangler succeeds, runs the verify-deploy skill: hits the live URL, captures status code, screenshots the homepage with ultron-screenshot, surfaces any runtime errors that wrangler couldn't catch.

When to use this

user wants to deploy to Cloudflare (Pages, Workers, or Containers)
user says 'ship this' / 'deploy this' / 'put it on Cloudflare' when the project lives in /work
user already has a wrangler.toml and just wants it deployed

When NOT to use this

user wants Vercel / Fly / Render → run their CLI via shell_exec directly
user wants to clone-and-deploy a site → use clone-website (which includes ultron-deploy)
user wants to deploy from a GitHub repo via CI → use push-to-github + wire CF Pages to it

Example prompts

deploy this to Cloudflare Pages

ship the worker in /work

push this container to Cloudflare

deploy and verify it's live

Inputs and output

Inputs

Field	Description
`target`	pages \| workers \| containers (auto-detected from project shape if omitted)
`branch`	for Pages, optional deploy branch name

Output

Live URL + verify-deploy report (status code, screenshot path, any runtime errors).

Runtime profile

What the engine commits when this skill runs.

Property	Value	Meaning
Model tier	`sonnet`	The balanced default model class. Trades quality against cost for the vast majority of skill runs.
Cost class	`standard`	The balanced default model. Right for most skills.
Turn budget	`10`	Hard cap on tool-calling iterations before the engine forces a final answer.
Execution	`synchronous`	Runs inside the live turn; result lands in the same response.

Under the hood

Tools the engine exposes to this skill and integrations it needs.

Resource	Kind
`shell_exec`	tool

Tags: engineering, deploy

Execution template

Shell tools dispatch via a command template. The model substitutes user inputs into the placeholders before firing the underlying tool.

shell_execbash

detect target from /work; wrangler deploy for Worker, wrangler pages deploy for Pages, ultron-deploy for clone-style; then follow verify-deploy/SKILL.md

Related skills

Skill	What it does
Spin up a Web App	Scaffold a fresh web app in /work, start the dev server, surface the live preview URL.
Clone a Website	Fire ultron-capture: spider the site, deploy a branded clone, surface the URL when ready.
Build an Agent	Spin up an autonomous agent on the agent-runtime satellite — try templates first, custom build only if no fit.
Push to GitHub	Initialize /work as a git repo, create the GitHub repo, push, return the URL.
Swap Page Sections	Reorder <section> blocks in a minified HTML file with byte-level safety.
Refactor Across Files	Multi-file string operations with quote and escape safety — uses bun -e, not sed.

Invoking this from an agent

Three paths reach this skill. From the chat UI, a user can type the persona slash command followed by a natural request and the discovery step resolves to this skill automatically. From the MCP server, fetch the skill detail with get_skill({id: "deploy-to-cloudflare"}) and then invoke it through the agent runtime once the authenticated tier ships. From your own code, hit /docs/skills/deploy-to-cloudflare/llm.txt for the token-efficient markdown body and feed it to your model directly.

Note

Every skill page has a canonical permalink and a markdown alternate that LLM crawlers consume via Accept: text/markdown. The full machine-readable catalog lives at /.well-known/agent-skills/index.json.