Install
$ agentstack add skill-evan-kim2028-agent-skills-frontend-design ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Frontend design — implement hub
Build the feature. Engineering path for product UI in the codebase.
Craft specialists (product-ui-craft, mobile-product-ux, design-system, web-quality, ui-explore, tufte) are owned primarily by product-design. This hub still lists them for one-shot implement pipelines, but if the ask is only craft/UX, load product-design instead.
Route first → open 1–3 specialists.
Routing table
| Your task | Skill | Notes | |-----------|--------|--------| | React waterfalls, bundles, jank, code-split | react-performance | Primary FE-engineering specialist | | Signed-off mockup → production code | mockup-implement | Fidelity implement (craft after via product-design) | | Prove UI after implement | browser-verify or quality-check | Prefer quality-check if full QA path | | Tokens / craft / mobile / a11y / explore / charts | product-design → its table | Prefer that hub for craft-only work | | Unclear multi-step implement | start here | Default for “build the page” |
Aliases still resolve: html-design/prototype → ui-explore; visual-verify/browser-testing-with-devtools → browser-verify.
Multi-step implement pipeline
- If design unsigned → product-design → ui-explore
- mockup-implement when signed off
- Implement structure with design-system constraints (via product-design if craft-heavy)
- react-performance if data/chart-heavy
- Craft pass: product-design specialists as needed
- quality-check / browser-verify before done
Build vs craft vs prove
| Phase | Hub | |-------|-----| | Implement product UI (full FE path) | frontend-design (this hub) | | Craft / mobile UX / density / “feels off” | product-design | | Prove / regression / e2e / ship | quality-check |
Shared principles (implement)
- Project design system wins — no freestyle brand.
- Reuse kit primitives — no one-off hex/
p-[13px]. - States in the PR — loading/empty/error with the feature.
- Mobile if touch-reachable — or route product-design.
- Perf is part of ship — react-performance.
- Prove pixels — browser-verify / quality-check.
Sources (attribution)
- Hub synthesis: Evan-Kim2028/agent-skills
- Specialist lineages: see [ATTRIBUTION.md](../../../ATTRIBUTION.md) and each skill’s Sources section
- Prefer this hub over mega frontend-ui-engineering packs
When not to use this hub
| Task | Use instead | |------|-------------| | Pure craft / mobile UX / density | product-design | | Pure QA / e2e / ship | quality-check | | Marketing | marketing | | Data pipelines | data |
Done criteria
- [ ] Implement path used the right engineering specialist(s)
- [ ] Craft-only work was routed to product-design when appropriate
- [ ] Design-system constraints respected
- [ ] Perf considered if data/chart-heavy
- [ ] Browser proof when layout/gesture risk is non-trivial
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Evan-Kim2028
- Source: Evan-Kim2028/agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.