AB lovable-mcp
Use Lovable's MCP server to create, iterate on, and deploy full-stack web apps from natural-language prompts. Trigger this skill whenever the user wants to build a web app, dashboard, internal tool, prototype, landing page, or any frontend/full-stack project using Lovable — whether they say "Lovable" explicitly or just need a working app built and deployed fast. Also trigger when the user wants to manage Lovable projects programmatically: listing workspace projects, auditing edit history, reviewing diffs, reading project files, checking deployment status, managing databases, or setting AI governance policies. If the user mentions "Lovable," "lovable project," "lovable app," or asks to build/ship/deploy a web app and Lovable is available as a connected MCP, use this skill. Even if they just say "make me an app" or "build a dashboard for X" — if the Lovable MCP is connected, this skill applies. Covers the full lifecycle: create → iterate → review → deploy.
As a process B 68/100 · Nearly there — weak spots: result and completion, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 68/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 38 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2810 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 968: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 35 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.