agent-config
Create, update, or audit AGENTS.md (default) or CLAUDE.md agent instructions: set up, prune, add a rule, or merge CLAUDE.md or…
Build production-grade frontend interfaces with distinctive aesthetics and working code. Use for UI components, pages, or frontend features. Don't use for backend/API work or usability-only audits.
$ npx -y skills add luongnv89/skills --skill frontend-design --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/frontend-designContext preview
The summary Claude sees to decide when to auto-load this skill.
Build production-grade frontend interfaces with distinctive aesthetics and working code. Use for UI components, pages, or frontend features. Don't use for backend/API work or usability-only audits.
name: frontend-design description: "Build production-grade frontend interfaces with distinctive aesthetics and working code. Use for UI components, pages, or frontend features. Don't use for backend/API work or usability-only audits." license: MIT effort: high metadata: version: 1.4.0 author: "Luong NGUYEN <luongnv89@gmail.com>"
Create distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with deliberate aesthetic choices.
Trigger this skill when the user asks to:
1. Record the **explicit brief**: any style preference, color palette, brand kit, or style direction the user gives. If there is none, the Default Style Guide applies. 2. If the request does not state the purpose and the target audience, ask for them before writing code. 3. If the work extends an existing codebase, read its framework, CSS variables, and component patterns before proposing anything. 4. Propose an aesthetic direction (*Design Thinking*). In an existing codebase, also list the files you will create or modify. Emit the Design Thinking step report. 5. Wait for the user to approve the direction before writing code. If the user asks for changes, propose again. If the user says "just build it", state the direction in one line and continue. If the user ends the run without approving, end with a `BLOCKED` Final Report. 6. Read `references/aesthetics-guide.md` and the Quick rules in `references/usability-guide.md`. Run *Repo Sync Before Edits*. Then implement the code. Add a short comment at each non-obvious design decision (font pairing, palette mapping, motion timing). 7. Run the verification checks:
8. If a check fails, fix it and re-run that check. After the second fix cycle, stop fixing and list each remaining failure in the Final Report. 9. Emit the Implementation step report, then the Final Report.
Run this once, before the first file write in step 6. The sync target is the directory the code is written to.
1. Run `repo="$(git -C "<target dir>" rev-parse --show-toplevel)"`. If it fails, skip the sync and record `sync: skipped (not a git repo)`. 2. Run `git -C "$repo" remote get-url origin`. If it fails, skip steps 3–7 and record `sync: skipped (no origin)`. 3. Run `branch="$(git -C "$repo" rev-parse --abbrev-ref HEAD)"`. If it prints `HEAD`, skip steps 4–7 and record `sync: skipped (detached HEAD)`. 4. Run `git -C "$repo" status --porcelain`. If the output is empty, run `git -C "$repo" fetch origin && git -C "$repo" pull --rebase origin "$branch"`. 5. If the output is not empty, run `git -C "$repo" stash push -u -m "frontend-design pre-sync"`, then the same fetch and pull, then `git -C "$repo" stash pop`. 6. If `fetch` or `pull` fails before a rebase starts (network, authentication, or a missing remote branch), do not retry. Run `git -C "$repo" stash pop` when step 5 stashed, record `sync: failed (<first error line>)`, and continue. 7. If the rebase conflicts, run `git -C "$repo" rebase --abort`, then `git -C "$repo" stash pop` when step 5 stashed. If the stash pop conflicts, leave the stash in place. In both cases write no file; stop and ask the user how to continue. With no answer, the status is `BLOCKED`.
This skill commits nothing.
Before coding, identify the active style source and commit to a clear aesthetic direction:
Bold maximalism and refined minimalism both work when they fit the active style source; the key is intentionality, not intensity.
When the user gives no explicit brief, apply this style guide:
1. **Color Palette (Strictly Limited):** Use only four core colors — Black (`#000000`), White (`#FFFFFF`), Gray (`#6B7280`), and Bright Green (`#22C55E`). 2. **Aesthetic:** Maintain an elegant, clear, clean, and professional design language. 3. **Visual Depth:** Incorporate visual depth using elements like cards, lines, borders, and subtle shadows. 4. **Bright Green Usage Constraint:** The Bright Green color is strictly reserved for highlights (text,
One command drops a tested, versioned skill into your agent. No more ad-hoc prompts. The same rigorous steps run every time. Skills are independent files.
Create, update, or audit AGENTS.md (default) or CLAUDE.md agent instructions: set up, prune, add a rule, or merge CLAUDE.md or…
Find open AI engineering jobs that fit a candidate, verify location and apply links, and assess each employer's product. Use for…
Generate App Store screenshots and header/search images for iPhone, iPad and Mac from a codebase or landing page, or re-render a…
Audit iOS/macOS apps against App Store Review Guidelines before submission, with evidence-backed verdicts and fixes. Don't use…
Optimize App Store and Google Play listings via a 7-phase, plan-approval-gated ASO workflow (keyword strategy, metadata,…
Generate a commit message, stage all changes, and push to remote after scanning for secrets, large files, and protected-branch…