quality-loop
/quality-loop
Loop UI work until quality gates pass — judge/build, test, audit, fix, repeat. Use for “rapihin sampai bagus”, polish until audit passes, fix Critical/High design findings, or /polish. Do not use for one-shot “rapihin detail”, copy-only rewrites, or “rapikan kode”.
- Author
- sukirman1901 ↗
- Repository
- frontend-expert ↗
- Licence
- MIT
- Last repository change
- 18.09.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 18.09.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Loop UI work until quality gates pass — judge/build, test, audit, fix, repeat. Use for “rapihin sampai bagus”, polish until audit passes, fix Critical/High design findings, or /polish. Do not use for one-shot “rapihin detail”, copy-only rewrites, or “rapikan kode”.
Triggers from the description
Original author description
Loop UI work until quality gates pass — judge/build, test, audit, fix, repeat. Use for “rapihin sampai bagus”, polish until audit passes, fix Critical/High design findings, or /polish. Do not use for one-shot “rapihin detail”, copy-only rewrites, or “rapikan kode”.
How it works
- Overview
- When to use
- When to skip
- Agents (orchestrate — do not nest personas forever)
- Gates (pass / fail)
- Iteration cap
- Workflow
- Output template (every cycle)
- Final output (DONE or STOP)
- Checklist
SKILL.md preview
---
name: quality-loop
description: >-
Loop UI work until quality gates pass — judge/build, test, audit, fix, repeat.
Use for “rapihin sampai bagus”, polish until audit passes, fix Critical/High
design findings, or /polish. Do not use for one-shot “rapihin detail”, copy-only
rewrites, or “rapikan kode”.
---
# UI Quality Loop
## Overview
Run a **tight quality loop** until the UI clears gates (or hit the iteration cap). This is the pack’s mini lifecycle — not full `/spec`→`/ship`, but **build → prove → audit → fix** until it’s good.
```text
JUDGE* → BUILD → TEST → AUDIT ──Critical/High──▶ FIX ──▶ TEST → AUDIT …
│
PASS → DONE
```
\* Judgment only on blank-canvas / first pass (see `design-direction` skip rules).
## When to use
- User asks “rapihin sampai bagus”, “sampai lulus audit”, keep iterating until gates pass
- `/polish` or natural language equivalent of the loop
- After a `/design`/`/audit` with Critical/High findings and user wants them cleared
## When to skip
- “Rapihin detail” / feels off → `polish` (one pass)
- Copy / “tulisan AI” → `content-design`
- “Rapikan kode” → `anti-slop-code`
- Single-line token tweak with no quality ask
- Pure audit with no fix permission (“audit saja”)
- User said stop / “cukup” / accepted remaining Medium/Low
## Agents (orchestrate — do not nest personas forever)
| Step | Agent |
|------|--------|
| Judgment + build + fix | `ui-developer` |
| Test | `test-engineer` |
| Audit | `design-reviewer` |
You (the session agent) are the **loop controller**. Personas do not call each other; you invoke their workflows in sequence.
## Gates (pass / fail)
| Gate | Pass when |
|------|-----------|
| **Anti-slop** | No Critical/High AI-aesthetic findings |
| **UI feel** | No Critical/High craft issues on touched UI (concentric radius, hit overlap, `transition: all`, broken press/enter) |
| **Control geometry** | radius follows project tokens; text/icon variants are optically balanced; pending/disabled/focus states do not shift geometry |
| **Tokens** | No Critical/High raw-hex / off-token issues; greenfield pack preset used decision tree + Token score / `(explicit)` / `(hard-gate)` / project system in Conventions check |
| **Responsive** | Conventions Responsive line present; full-width primary CTA <768; no Critical/High desktop-only layout on greenfield (320–1440) |
| **Hierarchy** | Hierarchy pass (one primary focus + one primary CTA) or waiver for tiny tweaks |
| **Typography** | One h1/page + sequential ladder (or waiver) |
| **Motion** | Shell light defaults **or** named families/patterns from `motion-families.md`; no decorative spam; reduced-motion; hand-roll (not registry default) |
| **Shell** | Theme in topbar; avatar → account menu; custom selects (or waivers) on dashboards |
| **Landing** | Marketing section stack via `marketing` (not hero-only; hand-roll) — or `n/a` for app-shell-only |
| **A11y** | No Critical keyboard/label/contrast findings (potential or measured) |
| **States** | Loading/error/empty handled for interactive surfaces touched |
| **Tests** | Planned critical cases green, or **explicit waiver** if no test runner / out of scope (document why) |
| **Perf (soft)** | No Critical obvious LCP/CLS footguns in touched UI; else note as remaining |
**Loop continues** while any **Critical** or **High** remains on touched UI.
**Medium/Low** do not block DONE unless the user asked for zero findings.
Do **not** invent a test stack just to satisfy the Tests gate — waive and list residual risk.
## Iteration cap
- Default **max 3** full AUDIT→FIX cycles after the first build
- On cap: stop, ship best effort, list remaining findings + what would need another round
- Never infinite-loop
## Workflow
### Round 0 — Direction + build
1. Load `design-direction` if non-trivial / blank-canvas
2. After direction: (+ `prototype` if comparing/stressing) → `tokens` → (+ `marketing` if landing) → (+ `app-shell` / `data-fetching` / `forms` if needed) → `components` → (+ `design-surfaces` when radius/control geometry is implicated) → **`anti-slop-code`** → **`responsive`** → **`motion`** (light shell; marketing = families/patterns from `motion-families.md`, hand-roll) → `anti-slop-design` → `polish` → `accessibility` (+ `webgl` / `seo` if needed)
3. Produce UI + **Conventions check** (`references/compliance-gates.md`)
### Each cycle — Prove + audit + fix
1. **TEST** — `testing` via `test-engineer` (/test-ui workflow) for touched surfaces
2. **AUDIT** — `design-reviewer` scorecard (/design or /audit). Mark unevaluated honestly.
3. **DECIDE**
- All Critical/High clear → **DONE** (report scorecard + remaining Medium/Low)
- Else if iterations left → **FIX** with `ui-developer` (only findings that block gates; include `design-surfaces` when radius is implicated)
- Else → **STOP** at cap with remaining list
### Fix discipline
- Fix highest severity first
- Prefer token/system fixes over one-off hacks
- Re-run TEST for behavior you changed
- Do not expand scope to unrelated pages
## Output template (every cycle)
```markdown
## Quality loop — cycle N/3
### Test
- … pass/fail …
### Audit scorecard
| Metric | Status | Notes |
|--------|--------|-------|
| … | … | … |
### Blocking (Critical/High)
1. …
### Action
FIX … | DONE | STOP (cap)
```
## Final output (DONE or STOP)
1. What shipped / changed
2. Final scorecard
3. Remaining Medium/Low (if any)
4. Cycles used
## Checklist
- [ ] Judgment only when blank-canvas / first pass (skip rules honored)
- [ ] Build chain includes **responsive** + **motion** (+ **marketing** if landing) or waivers
- [ ] Gates table evaluated each cycle (Anti-slop, Feel, Tokens, Responsive, Hierarchy, Typography, Motion, Shell, Landing, A11y, States, Tests)
- [ ] Shell chrome: theme topbar + avatar menu + custom selects (or waivers)
- [ ] Marketing landing: section stack hand-roll (or n/a / waiver)
- [ ] Conventions check filled before DONE
- [ ] Control geometry Conventions line covers radius token, text/icon optical balance, and relevant states (or valid n/a/waiver)
- [ ] Cap ≤3 fix cycles; STOP lists remaining Critical/High if any
- [ ] No fabricated audit scores
## Depth
- Lifecycle A→Z: `references/fe-lifecycle.md`
- Judgment: `design-direction`
- Build: `tokens`, `components`, `design-surfaces` when radius is implicated, **`anti-slop-code`**, **`responsive`**, **`motion`** (`motion-families.md`), `anti-slop-design`, `polish`, `accessibility`
- Test: `testing` (+ `devtools` when measuring)
- Audit: `design-reviewer` + `references/anti-patterns.md` / `references/polish.md` / a11y / performance as needed
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · sukirman1901/frontend-expert | 100 | MIT |
| trpc-group/trpc-agent-go | 100 | Apache-2.0 |
Database snapshot: 13.11.2026 · package version ce20d8bc371f (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100visual-polish-loop
Run a recursive, evidence-driven visual polish loop on a web UI. Audit every page, theme and state against a quality bar (palette, contrast, surfaces, typography, spacing, component states, focus), prototype genuinely different directions on the real pages, implement the winner… - 100judge
Use to quality-gate a design before reporting it done — the mandatory step 5 of the handbook Loop; when the user asks for a design review, score, audit, or QA; or when a design needs remediation after a failed review. The axes, the gate, the scorecard format, and the remediation… - 90design-audit
Systematic visual UI/UX audit that produces phased, implementation-ready design plans, plus focused single-objective refinement passes ("lenses"). Use when the user asks to audit a UI, improve or polish an app's visual design, review design consistency, fix visual hierarchy, or… - 100design-polish
Final quality pass fixing alignment, spacing, consistency, interaction states, and micro-details before shipping. Executes changes (unlike design-audit and design-critique which are report-only). Triggers on polish, finishing touches, final pass, something looks off, pre-launch, good to great. - 100polish
Polish micro-details that make UI feel better — optical alignment, tabular nums, text-wrap, interruptible transitions, press feedback, hit areas, no transition:all. Use when building/reviewing UI polish, "feels off", "rapihin detail", hover/press feedback, or after… - 100gauntlet-loop-max
Two-gate quality loop for work that tests alone can't prove is good - UI, animation, dashboards, landing pages, copy, scripts, titles, thumbnails, docs, decks. Gate 1 proves it works (spec + quality review by an independent reviewer, fix rounds, severity-ranked findings). Gate 2…