Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/enforce-design-ci
Use when a repository needs deterministic pull-request checks for new accessibility, design-token, component-structure, responsive, and UI-state regressions with file-level evidence.
Passed 15 of 19 test cases with the skill, and 6 of 19 without it.
and 13 more in the full report
11 fixed7 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
When running the CLI init command, we are prompted to select a framework kit (e.g., react, vue, universal). Which kit parameter should be specified for standard agent skill integration?
| Checked | Without skill | With skill |
|---|---|---|
| Passes --kit universal to the init command. | Missed | Passed |
The instructions your model reads when the skill loads.
Add a reviewable design-quality gate that runs without an LLM. Memi writes a policy, baseline, universal agent skill, SARIF, and human-readable report artifacts.
Inspect the worktree first. When the task authorizes setup, run:
npx -y @memi-design/[email protected] init --team --kit universal --json
Review the generated policy and baseline before committing them. Existing debt remains visible but does not block unrelated pull requests.
npx -y @memi-design/[email protected] ci . --no-scope --report --json
The command may exit nonzero when findings exceed the configured gate. Treat that as a quality result, not a tool crash.
Use the pinned major action in .github/workflows/design.yml:
name: Design CI
on: [pull_request]
jobs:
design:
runs-on: ubuntu-latest
permissions:
contents: read
security-events: write
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- uses: memi-design/memi@v2
test cases passed, vs 6 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.