How do I install the Lovable Testing skill?

Run npx skillmds@latest add 10k-digital/lovable-testing in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Lovable Testing safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Lovable Testing?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Lovable Testing free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Lovable Testing?

10k-digital (@10k-digital) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Lovable Testing by 10k-digital — Agent Skill

Name: Lovable Testing
Rating: 4.2 (5 reviews)
Author: 10k-digital

Lovable Testing

Run and maintain Lovable Preview tests from Codex, Claude Code, or another Agent Skills runtime. Use for test-plan generation, smoke/changed/all runs, test workspace migration, preview token handling, or keeping tests synchronized with changed features.

10k-digital 664b21f 1.6 KB Updated Sep 10, 2026

File contents

Lovable Preview Testing

The canonical user-project test workspace is:

.lovable-agent/
├── config.json
├── context.md
├── preview-token.local       # ignored credential, never committed
└── tests/
    ├── plans/
    ├── profiles/
    └── results/

Treat Preview as non-production. Mark destructive, paid, or irreversible steps [MANUAL].
Store only the base preview URL and token dates in config.json; store the token itself only in .lovable-agent/preview-token.local, after ensuring the path is in .gitignore.
Prefer a valid stored token, then a logged-in browser session, then a manual checklist. Never block implementation solely because browser access is unavailable.
After implementation or deployment, run the smallest affected plan set (--changed or --smoke) before offering --all.
Keep covers: paths accurate and update the last-sync commit after a successful plan sync.
Migrate .claude/lovable-claude/test/ with scripts/migrate-workspace.py; preserve the legacy path as a read-compatible alias until the user opts into cleanup.

The existing ../testing/ skill and its references remain the Claude command implementation. Read ../lovable/references/agent-config.md for the neutral config schema and migration mapping.

Frequently asked questions