Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/memoire-design-tooling
Use when a task spans interface understanding, design-system memory, UI audits, design CI, Figma, shadcn or Tailwind code generation, research, or agent design workflows and needs the correct Memi capability selected.
Passed 16 of 19 test cases with the skill, and 7 of 19 without it.
and 10 more in the full report
10 fixed8 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
We want to add the frontend audit skill to our project using npx without installing global daemons or full suites. What command installs this single focused skill?
| Checked | Without skill | With skill |
|---|---|---|
| Executes npx skills add memi-design/memi --skill audit-frontend-design. | Missed | Passed |
The instructions your model reads when the skill loads.
Memi gives coding agents repository-specific interface evidence before they edit UI. Start with the smallest workflow that answers the task; Figma, global installation, and a daemon are optional.
audit-frontend-design.remember-design-system.enforce-design-ci.build-swiftui-interface.Install one focused skill directly:
npx skills add memi-design/memi --skill audit-frontend-design
npx -y @memi-design/[email protected] agent brief . --intent "<interface task>" --detail compact --json
Use --detail standard only when the compact brief lacks evidence needed for the edit.
memi agent install --dry-run --json
memi scaffold component EvidenceCard --level organism --json
memi ios brief --intent "<SwiftUI task>" --detail compact --json
memi ios scaffold FeatureName --kind screen --module AppModule --json
memi research design --intent "<task>" --json
memi shadcn export --out public/r --json
memi mcp start --no-figma
Review dry-run output before writes. Every created component must state its Atomic Design level, reuse local or shadcn primitives, and use semantic tokens instead of raw hex values.
test cases passed, vs 7 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.