ワンクリックで
ttb-skill-audit
Code audits for TTBaseUIKit apps: performance, accessibility, localization. FCR compliance scoring.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Code audits for TTBaseUIKit apps: performance, accessibility, localization. FCR compliance scoring.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Enterprise-grade iOS development workflow for TTBaseUIKit-powered apps. Cross-functional product analysis | MVVM-C Architecture | UIKit + SwiftUI | TTViewCodable | TTBaseSUI | xcodebuild CLI Verification | Zero Regression | iOS 14+
Systematic bug fixing workflow for TTBaseUIKit apps: root cause analysis, fix strategy, xcodebuild verify, zero regression.
TTBaseUIKit project initialization skill: scaffold MVVM-C folder structure, setup TTBaseUIKitConfig, configure localization, integrate TTBDebugPlus. Run BEFORE any other TTBaseUIKit skill.
Build reusable native SwiftUI UI components using 100% standard SwiftUI primitives with TTBaseUIKit design tokens, localization, chainable modifiers, and project architecture rules. NO TTBaseSUI wrappers. iOS 14+.
Refactor TTBaseUIKit code: migrate to TTViewCodable, replace raw UIKit with TTBaseUIKit, TTBaseSUI adoption, clean MVVM separation.
Shared resources for all TTBaseUIKit skills: routing, workflows, cross-functional analysis, rules, phases, references, anti-patterns, coding standards, and verification.
| name | ttb-skill-audit |
| description | Code audits for TTBaseUIKit apps: performance, accessibility, localization. FCR compliance scoring. |
| version | 2.3.0 |
| date_updated | 2026-05-30 |
| risk | safe |
| source | internal |
| loadLevel | on-demand |
| tags | ["audit","performance","accessibility","localization","fcr","routing"] |
Code audit skill set for TTBaseUIKit apps. Performance | Accessibility | Localization | FCR Compliance
Before this skill generates code, refactors, migrates, modifies files, creates architecture, updates UI/navigation, changes dependencies, updates workflows, or changes business logic, run the shared gate:
ttb-skill-shared/fragments/ttb-preflight-execution-gate.frag.mdttb-skill-shared/fragments/ttb-cross-functional-analysis-gate.frag.md when audit produces feature/update/bugfix recommendationsttb-skill-shared/templates/ttb-clarification-survey.md when confidence is below thresholdRequired phase order: Requirement Analysis -> Context Validation -> Ambiguity Detection -> Missing Information Detection -> Survey / Clarification -> Confidence Evaluation -> Execution Approval.
Execution thresholds:
| Confidence | Action |
|---|---|
90-100 | Execute directly and state key assumptions |
70-89 | Execute only with documented low-risk assumptions |
<70 | Do not execute; ask a concise survey first |
Cap confidence at 69 when target module, architecture direction, UIKit/SwiftUI choice, navigation behavior, API/business logic, localization format, state management, dependency info, or ownership is unclear. Parse English, Vietnamese, mixed-language, diacritic-free Vietnamese, and light typos before scoring.
When audit findings lead to feature updates, bug fixes, UX changes, or architecture changes, analyze recommendations as Product Owner, Business Analyst, UX/UI Designer, Solution Architect, Senior Developer, and QA. Compare options across business value, architecture, UI/UX, performance, scalability, maintainability, security, testing, and operations; ask at least 5 value-expansion questions after analysis. If requirements are ambiguous/incomplete, ask at least 6 clarification questions before design/development.
| Command | Description |
|---|---|
/ttb-audit-performance | Performance: rendering, memory, CPU, main thread |
/ttb-audit-accessibility | VoiceOver, Dynamic Type, touch targets, color contrast |
/ttb-audit-localization | Hardcoded strings, missing keys, naming violations |
input:
required: [audit_type, scope]
optional: [target_score, known_risks, files_or_modules, fix_requested]
output:
artifacts: [findings, fcr_score, prioritized_recommendations, optional_fix_plan]
completion_gate: "findings reported before fixes unless user explicitly requests fixes"
confidence:
auto_route: ">= 0.78 for audit/review/performance/accessibility/localization/FCR/compliance intents"
clarify: "0.55-0.77 when audit type or scope is unclear"
fallback:
default: "Run general FCR audit if user asks broad code audit; chain to bugfix/refactor only when fixes are requested."
Multilingual aliases: audit code, performance audit, accessibility audit, localization check, kiểm tra hiệu năng, kiem tra ngon ngu, chấm điểm FCR, danh gia compliance.
Anti-patterns: do not hide findings behind summaries; do not fix before reporting audit results unless explicitly requested; do not score without stating evidence.
| Dimension | Weight | Check |
|---|---|---|
| iOS 14+ API | 15% | No iOS 15+/16+/17+ APIs |
| TTBaseUIKit Compliance | 20% | All components, no raw UIKit |
| Config Tokens | 15% | TTView/TTSize/TTFont everywhere |
| MVVM Separation | 15% | ViewModel pure, VC thin |
| Closure Safety | 15% | [weak self] everywhere |
| Localization | 10% | XText/XTextU with Localizable.strings |
| Code Quality | 10% | MARK sections, naming, style |
Score >= 85: READY
Score 70-84: NEEDS FIX
Score < 70: BLOCKED
| ❌ Issue | ✅ Fix |
|---|---|
Raw UILabel() | TTBaseUILabel |
Raw UIButton() | TTBaseUIButton |
Raw Text("...") | TTBaseSUIText or native Text with tokens |
Raw Button(...) | TTBaseSUIButton or native Button |
| ❌ Hardcoded | ✅ Token |
|---|---|
UIColor(hex: "#555") | TTView.textDefColor |
Color.blue | TTView.buttonBgDef.toColor() |
8 (padding) | TTSize.P_CONS_DEF |
16 (padding) | TTSize.P_CONS_DEF * 2 |
UIFont.systemFont(ofSize: 14) | TTFont.TITLE_H |
| ❌ Issue | ✅ Fix |
|---|---|
Missing [weak self] | [weak self] + self?. |
| Strong self in API callback | [weak self] + guard |
NotificationCenter observer without weak | { [weak self] _ in self?.reload() } |
| ❌ Issue | ✅ Fix |
|---|---|
Missing deinit | Add with removeObserver + XPrint |
Missing super.viewDidLoad() | Call super first |
Subviews on self.view | self.contentView |
| File | Purpose |
|---|---|
ttb-skill-audit-performance.prompt.md | Performance audit |
ttb-skill-audit-accessibility.prompt.md | Accessibility audit |
ttb-skill-audit-localization.prompt.md | Localization audit |
After audit fixes are applied, run Phase 6 from ttb-phase-verify.md:
Step 1 — xcodebuild Build
cd /path/to/TTBaseUIKitExample
xcodebuild -project TTBaseUIKitExample.xcodeproj \
-scheme TTBaseUIKitExample \
-destination 'platform=iOS Simulator,name=iPhone 11' \
build 2>&1 | tail -50
| Result | Action |
|---|---|
BUILD SUCCEEDED | ✅ Proceed |
BUILD FAILED | Fix errors → re-run (max 3 attempts) |
Step 2 — Output Verification Report
Report layers 1-5 from ttb-phase-verify.md. Audit is complete only when ✅ BUILD SUCCEEDED.
Version: 2.3.0 | Date: 2026-05-30 Changelog: v2.3.0 — Added cross-functional product analysis gate, option exploration, 5 value-expansion questions, and 6-question ambiguity clarification gate. v2.2.0 — Added standardized routing contract, EN/VI audit aliases, input/output schema, confidence guidance, and fallback strategy. v2.0.0 — Version bump, Iron Laws, critical token warnings, and shared resource alignment.