skills/browser-dev/SKILL.md
Lightweight browser automation via custom scripts. Use when Playwright MCP or Claude-in-Chrome is unavailable, or for building reusable browser check flows.
npx skillsauth add RonanCodes/ronan-skills browser-devInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Write and run Node.js browser automation scripts using Playwright as a library. No MCP required. Scripts are saved for reuse.
/browser-dev http://localhost:3000 --screenshot
/browser-dev http://localhost:3000 --check
/browser-dev --script .browser-dev/login-flow.js
/browser-dev http://localhost:3000 --flow "click Sign In, fill email, fill password, submit, check dashboard loads"
Before running, detect the automation library:
node -e "require('playwright')" 2>/dev/null && echo "playwright" || \
node -e "require('puppeteer')" 2>/dev/null && echo "puppeteer" || echo "none"
If none: tell the user to install one — npm install -D playwright && npx playwright install chromium. Prefer Playwright (cross-browser, auto-waiting, better API). Do NOT proceed without a library installed.
| Flag | Action |
|------|--------|
| --screenshot <url> | Full-page screenshot, saved to .browser-dev/screenshots/<timestamp>.png |
| --check <url> | Verify page loads (200), no console errors, no uncaught exceptions. Pass/fail table. Exit 1 on fail |
| --script <path> | Run an existing script: node <path> [args]. No generation needed |
| --flow "desc" | Generate a custom script from natural-language description, save to .browser-dev/flows/<slug>.js, run it |
All generated scripts follow this pattern:
const { chromium } = require('playwright');
(async () => {
const browser = await chromium.launch({ headless: true });
const context = await browser.newContext({ viewport: { width: 1280, height: 720 } });
const page = await context.newPage();
const errors = [];
page.on('pageerror', err => errors.push(err.message));
page.on('console', msg => { if (msg.type() === 'error') errors.push(msg.text()); });
// --- flow logic here ---
await browser.close();
if (errors.length) { console.error('Errors:', errors); process.exit(1); }
})();
.browser-dev/
├── screenshots/ # --screenshot output
├── flows/ # saved --flow scripts
└── scripts/ # user's custom scripts
Add .browser-dev/ to .gitignore if not already present.
playwright or puppeteer before generating scripts — adapt require() to whichever is installedheadless: true unless the user explicitly asks for headed mode--scriptwaitUntil: 'networkidle' for page loads by defaulttesting
--- name: linear-pipeline description: The Fable orchestrator for a single dispatched Linear ticket. Holds almost no context itself; it receives `--issue <ID> --detached`, decides the stage sequence, and fans out a sub-agent per stage, passing forward only each stage's artifact (never re-derived, never inlined into its own context). Step zero, before any planning or stage routing, is a boundary triage against `canon/security-boundary.md` (#199): a match tags Ronan Connolly and stops the run, no
development
--- name: in-your-face description: Capture a chat-only answer into a durable artifact (markdown + HTML, PDF when cheap) and launch it automatically so the user cannot miss it. Use when user says "in your face", "don't let me lose this", "save that answer", "make that durable", or right after answering a substantive side question (a recipe, comparison, how-to, or generated prompt) that would otherwise die with the context. category: workflow argument-hint: [--no-open] [--vault <short>] [hint of
tools
One-shot headless OpenAI Codex CLI calls for background/admin AI tasks — summaries, classification, extraction, admin glue. The default engine for anything that runs AI constantly in the background (daemon-driven, per-event), because it bills the flat ChatGPT subscription instead of Claude usage or per-token API spend, and it keeps working while Claude is rate-limited. NEVER for coding — coding stays Claude. Use when a skill or daemon needs a cheap always-on AI call, when the user says "use codex", "ask codex", "codex as backup", or when building a background summarizer/classifier into a listener or loop. Reads auth from ~/.codex/auth.json (ChatGPT account, no API key).
research
Turn a warranty rejection, repair quote, or RMA email into a cited decision brief — legal read (NL/EU consumer law), is the part user-serviceable, live part and new-unit prices, repair-vs-DIY-vs-new economics, before-you-send-it checklist, deadlines. Use when the user pastes or screenshots a repair quote, warranty rejection, "not covered" email, onderzoekskosten fee, or asks "should I repair or replace this".