vibepress
AGENTS.md0 starsChanged 3 months agoMITView on GitHub
VibePress = a playbook you execute + tooling you run. The playbook lives at: Claude Code: copy that folder into your project's .claude/skills/ (or clone this repo as the project) and the skill loads automatically. Invoke with /lovable-to-elementor or just describe the task. Cursor / Windsurf / Copilot / anything else: paste SKILL.md into your rules/system prompt. It is written agent-agnostically — the only assumptions are a browser-automation tool (Playwright), shell access, and a WordPress connection (MCP bridge or WP-CLI).…
In this repositoryOne other file it gives its agents.
- lovable-to-elementorSkill
The file
Files
For AI agents
VibePress = a playbook you execute + tooling you run. The playbook lives at:
.claude/skills/lovable-to-elementor/SKILL.mdClaude Code: copy that folder into your project's .claude/skills/ (or clone this repo as the project) and the skill loads automatically. Invoke with /lovable-to-elementor or just describe the task.
Cursor / Windsurf / Copilot / anything else: paste SKILL.md into your rules/system prompt. It is written agent-agnostically — the only assumptions are a browser-automation tool (Playwright), shell access, and a WordPress connection (MCP bridge or WP-CLI). See docs/02-mcp-servers.md for the WordPress wiring.
Order of operations for a fresh conversion:
docs/02-mcp-servers.md— connect to the target WordPress siteSKILL.mdPhases 0–3 — capture the source, extract content, prepare WPscripts/build-elementor.js+scripts/apply_via_mcp.py— generate and applyscripts/qa/— loop until the screenshots matchdocs/06-migration.md— handover
Rule zero, worth repeating outside the skill: never ship a change you haven't screenshotted.
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.

