Shell Tool · engineering · Sentinel

Website Audit

Lighthouse-style audit: perf, SEO, security, accessibility — driven by Playwright in the container.

Updated today

View as MarkdownsentinelsonnetstandardMax 8 turns

Overview

Runs ultron-render with Playwright against the target URL, capturing performance metrics (LCP, CLS, TTFB), scanning meta tags for SEO issues, checking common OWASP-Top-10 surface (CSP, HSTS, XSS, mixed content), and auditing accessibility (alt text, heading hierarchy, color contrast). Outputs a structured report with severity-ranked findings.

When to use this

user wants to audit their site or a competitor's
user says 'audit this site' / 'how does X score on Lighthouse?' / 'check this site for security issues'
user is shipping and wants pre-launch quality check

When NOT to use this

user only wants a screenshot → use ultron-screenshot directly
user wants to fix issues, not just identify them → audit first, then minimal-patch

Example prompts

audit stripe.com — perf, SEO, security

how does my landing score on Lighthouse?

run a full accessibility audit on this site

Inputs and output

Inputs

Field	Description
`url`	site to audit
`focus`	optional comma-list: perf,seo,security,a11y (default: all)

Output

Severity-ranked report (P0/P1/P2/P3) with metric values + concrete remediation per finding.

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	`8`	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, audit, verify

Execution template

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

shell_execbash

1ultron-render {{url}} --audit={{focus}}; instrument browser-automation/SKILL.md flows for Lighthouse-style metrics

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

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: "website-audit"}) and then invoke it through the agent runtime once the authenticated tier ships. From your own code, hit /docs/skills/website-audit/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.