@votruongdanh/ai-agent-skills 3.2.1 → 3.3.2

package/.kiro/skills/plan/SKILL.md

@@ -1,69 +1,69 @@
----
-name: plan
-description: "Create concrete implementation plans with milestones, task breakdowns, and estimates. Use when the user wants to plan, organize work, or create a roadmap. Triggers: plan, milestone, breakdown, roadmap, estimate, kế hoạch, lên kế hoạch, phân chia công việc."
-agents: [project-planner, orchestrator]
-related-skills: [brainstorm, create, orchestrate]
----
-
-## Memory Protocol
-**START**: Read `.ai-memory.md` from project root. Check existing plans, milestones, project structure, tech stack, ongoing work, and past decisions.
-**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: plan summary, phases/tasks, key risks, and first recommended action.
-
-## Goal
-Turn a request into an actionable plan with clear phases and tasks.
-
-## Agent Routing
-- For architecture planning → read `.kiro/skills/agents/agents/project-planner.md` and apply its knowledge
-- For multi-domain coordination → read `.kiro/skills/agents/agents/orchestrator.md` and apply its knowledge
-- For technical feasibility → read the relevant specialist agent file:
-  - Backend: `.kiro/skills/agents/agents/backend-specialist.md`
-  - Frontend: `.kiro/skills/agents/agents/frontend-specialist.md`
-  - Database: `.kiro/skills/agents/agents/database-architect.md`
-
-## Socratic Gate
-Before planning, verify:
-1. What is the desired outcome? (specific deliverable)
-2. What constraints exist? (time, resources, tech stack)
-3. What is already built vs needs to be built?
-If any answer is unclear, ASK before proceeding.
-
-## Workflow
-1. **Read Memory** — Load `.ai-memory.md` for project context and history.
-2. Define the objective and acceptance criteria.
-3. Break the work into phases and tasks.
-4. Note file areas, systems, or modules likely to change.
-5. Estimate complexity and highlight risky items.
-6. End with a recommended first task.
-7. **Update Memory** — Save plan details to `.ai-memory.md`.
-
-## Output format
-- Objective
-- Acceptance criteria
-- Phases (with tasks under each)
-- File areas / modules affected
-- Risks (with mitigation)
-- Recommended first action
-
-## Checklist
-- [ ] Objective clearly stated
-- [ ] Acceptance criteria defined
-- [ ] Phases broken down
-- [ ] Tasks are specific and actionable
-- [ ] Complexity estimated per task
-- [ ] Risks identified with mitigation
-- [ ] First action recommended
-- [ ] Memory file updated
-
-## Rules
-- Plans should be specific enough to execute.
-- Prefer task sizes that can be completed and reviewed quickly.
-- Minimize blast radius: call out the smallest set of files likely to change; if scope is unclear, ASK.
-- Always read and update the memory file.
-
-## Quality Gate
-After completing, read `.kiro/skills/_scripts/checklist.md` for cross-cutting quality checks.
-
-## Related Skills
-- `/brainstorm` → read `.kiro/skills/brainstorm/SKILL.md` — Explore options before planning
-- `/create` → read `.kiro/skills/create/SKILL.md` — Execute planned tasks
-- `/orchestrate` → read `.kiro/skills/orchestrate/SKILL.md` — Coordinate complex plans across teams
+---
+name: plan
+description: "Create concrete implementation plans with milestones, task breakdowns, and estimates. Use when the user wants to plan, organize work, or create a roadmap. Triggers: plan, milestone, breakdown, roadmap, estimate, kế hoạch, lên kế hoạch, phân chia công việc."
+agents: [project-planner, orchestrator]
+related-skills: [brainstorm, create, orchestrate]
+---
+
+## Memory Protocol
+**START**: Read `.ai-memory.md` from project root. Check existing plans, milestones, project structure, tech stack, ongoing work, and past decisions.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: plan summary, phases/tasks, key risks, and first recommended action.
+
+## Goal
+Turn a request into an actionable plan with clear phases and tasks.
+
+## Agent Routing
+- For architecture planning → read `.kiro/skills/agents/agents/project-planner.md` and apply its knowledge
+- For multi-domain coordination → read `.kiro/skills/agents/agents/orchestrator.md` and apply its knowledge
+- For technical feasibility → read the relevant specialist agent file:
+  - Backend: `.kiro/skills/agents/agents/backend-specialist.md`
+  - Frontend: `.kiro/skills/agents/agents/frontend-specialist.md`
+  - Database: `.kiro/skills/agents/agents/database-architect.md`
+
+## Socratic Gate
+Before planning, verify:
+1. What is the desired outcome? (specific deliverable)
+2. What constraints exist? (time, resources, tech stack)
+3. What is already built vs needs to be built?
+If any answer is unclear, ASK before proceeding.
+
+## Workflow
+1. **Read Memory** — Load `.ai-memory.md` for project context and history.
+2. Define the objective and acceptance criteria.
+3. Break the work into phases and tasks.
+4. Note file areas, systems, or modules likely to change.
+5. Estimate complexity and highlight risky items.
+6. End with a recommended first task.
+7. **Update Memory** — Save plan details to `.ai-memory.md`.
+
+## Output format
+- Objective
+- Acceptance criteria
+- Phases (with tasks under each)
+- File areas / modules affected
+- Risks (with mitigation)
+- Recommended first action
+
+## Checklist
+- [ ] Objective clearly stated
+- [ ] Acceptance criteria defined
+- [ ] Phases broken down
+- [ ] Tasks are specific and actionable
+- [ ] Complexity estimated per task
+- [ ] Risks identified with mitigation
+- [ ] First action recommended
+- [ ] Memory file updated
+
+## Rules
+- Plans should be specific enough to execute.
+- Prefer task sizes that can be completed and reviewed quickly.
+- Minimize blast radius: call out the smallest set of files likely to change; if scope is unclear, ASK.
+- Always read and update the memory file.
+
+## Quality Gate
+After completing, read `.kiro/skills/_scripts/checklist.md` for cross-cutting quality checks.
+
+## Related Skills
+- `/brainstorm` → read `.kiro/skills/brainstorm/SKILL.md` — Explore options before planning
+- `/create` → read `.kiro/skills/create/SKILL.md` — Execute planned tasks
+- `/orchestrate` → read `.kiro/skills/orchestrate/SKILL.md` — Coordinate complex plans across teams

package/.kiro/skills/preview/SKILL.md

@@ -1,55 +1,55 @@
----
-name: preview
-description: "Preview expected output, UX flows, copy, interaction design, or generated content before implementing. Use when the user wants to see what something will look like. Triggers: preview, mockup, show me, xem trước, thử xem, mô phỏng."
-agents: [frontend-specialist, documentation-writer]
-related-skills: [create, ui-ux-pro-max, plan]
----
-
-## Memory Protocol
-**START**: Read `.ai-memory.md` from project root. Check UI patterns, design decisions, existing previews, brand guidelines, and user flow notes.
-**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: what was previewed, assumptions, feedback, and confirmed decisions.
-
-## Goal
-Show the user what the result will look or feel like before full implementation.
-
-## Agent Routing
-- If previewing UI/UX → read `.kiro/skills/agents/agents/frontend-specialist.md` and apply its knowledge
-- If previewing documentation → read `.kiro/skills/agents/agents/documentation-writer.md` and apply its knowledge
-- If previewing API response → read `.kiro/skills/agents/agents/backend-specialist.md` and apply its knowledge
-
-## Socratic Gate
-Before previewing, verify:
-1. What artifact is being previewed? (UI, API output, document, flow?)
-2. What level of fidelity is expected? (wireframe, mockup, full sample?)
-3. Any specific requirements or constraints?
-If any answer is unclear, ASK before proceeding.
-
-## Workflow
-1. **Read Memory** — Load `.ai-memory.md` for project context and design history.
-2. Infer the artifact being previewed: UI, API output, document, message, workflow, or report.
-3. Produce a faithful mock, sample output, walkthrough, or structured preview.
-4. Highlight assumptions behind the preview.
-5. Identify what could change during implementation.
-6. **Update Memory** — Save preview details and decisions to `.ai-memory.md`.
-
-## Checklist
-- [ ] Artifact type identified
-- [ ] Preview is realistic and faithful
-- [ ] Assumptions clearly labeled
-- [ ] Mock data marked as illustrative
-- [ ] Implementation differences noted
-- [ ] Memory file updated
-
-## Rules
-- Keep previews realistic and consistent with the current project.
-- Label illustrative content clearly when it is mock data.
-- Avoid implying broad code changes; if the preview would require major refactor, CALL IT OUT and ASK before implementation.
-- Always read and update the memory file.
-
-## Quality Gate
-After completing, read `.kiro/skills/_scripts/checklist.md` for cross-cutting quality checks.
-
-## Related Skills
-- `/create` → read `.kiro/skills/create/SKILL.md` — Implement the previewed design
-- `/ui-ux-pro-max` → read `.kiro/skills/ui-ux-pro-max/SKILL.md` — Advanced UI/UX design
-- `/plan` → read `.kiro/skills/plan/SKILL.md` — Plan implementation of previewed feature
+---
+name: preview
+description: "Preview expected output, UX flows, copy, interaction design, or generated content before implementing. Use when the user wants to see what something will look like. Triggers: preview, mockup, show me, xem trước, thử xem, mô phỏng."
+agents: [frontend-specialist, documentation-writer]
+related-skills: [create, ui-ux-pro-max, plan]
+---
+
+## Memory Protocol
+**START**: Read `.ai-memory.md` from project root. Check UI patterns, design decisions, existing previews, brand guidelines, and user flow notes.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: what was previewed, assumptions, feedback, and confirmed decisions.
+
+## Goal
+Show the user what the result will look or feel like before full implementation.
+
+## Agent Routing
+- If previewing UI/UX → read `.kiro/skills/agents/agents/frontend-specialist.md` and apply its knowledge
+- If previewing documentation → read `.kiro/skills/agents/agents/documentation-writer.md` and apply its knowledge
+- If previewing API response → read `.kiro/skills/agents/agents/backend-specialist.md` and apply its knowledge
+
+## Socratic Gate
+Before previewing, verify:
+1. What artifact is being previewed? (UI, API output, document, flow?)
+2. What level of fidelity is expected? (wireframe, mockup, full sample?)
+3. Any specific requirements or constraints?
+If any answer is unclear, ASK before proceeding.
+
+## Workflow
+1. **Read Memory** — Load `.ai-memory.md` for project context and design history.
+2. Infer the artifact being previewed: UI, API output, document, message, workflow, or report.
+3. Produce a faithful mock, sample output, walkthrough, or structured preview.
+4. Highlight assumptions behind the preview.
+5. Identify what could change during implementation.
+6. **Update Memory** — Save preview details and decisions to `.ai-memory.md`.
+
+## Checklist
+- [ ] Artifact type identified
+- [ ] Preview is realistic and faithful
+- [ ] Assumptions clearly labeled
+- [ ] Mock data marked as illustrative
+- [ ] Implementation differences noted
+- [ ] Memory file updated
+
+## Rules
+- Keep previews realistic and consistent with the current project.
+- Label illustrative content clearly when it is mock data.
+- Avoid implying broad code changes; if the preview would require major refactor, CALL IT OUT and ASK before implementation.
+- Always read and update the memory file.
+
+## Quality Gate
+After completing, read `.kiro/skills/_scripts/checklist.md` for cross-cutting quality checks.
+
+## Related Skills
+- `/create` → read `.kiro/skills/create/SKILL.md` — Implement the previewed design
+- `/ui-ux-pro-max` → read `.kiro/skills/ui-ux-pro-max/SKILL.md` — Advanced UI/UX design
+- `/plan` → read `.kiro/skills/plan/SKILL.md` — Plan implementation of previewed feature

package/.kiro/skills/status/SKILL.md

@@ -1,57 +1,57 @@
----
-name: status
-description: "Project status summary, progress snapshots, repo overview, and outstanding work tracking. Use when the user wants to know where a project stands. Triggers: status, progress, overview, what's done, dự án đang ở đâu, tiến độ, tổng quan."
-agents: [project-planner, orchestrator]
-related-skills: [plan, debug, deploy]
----
-
-## Memory Protocol
-**START**: Read `.ai-memory.md` from project root. This is the PRIMARY source for status — check all recorded history, decisions, tasks, bugs, and milestones.
-**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: status snapshot, what's working, gaps, risks, and priorities.
-
-## Goal
-Summarize where things stand right now, leveraging the memory file for deep context.
-
-## Agent Routing
-- For project health overview → read `.kiro/skills/agents/agents/project-planner.md` and apply its knowledge
-- For multi-workstream status → read `.kiro/skills/agents/agents/orchestrator.md` and apply its knowledge
-- For technical debt assessment → read the relevant specialist agent file based on domain
-
-## Workflow
-1. **Read Memory** — Load `.ai-memory.md` as the primary context source.
-2. Inspect the repository, relevant files, and any recent context from the chat.
-3. Summarize what already exists.
-4. Identify gaps, risks, TODOs, and likely next priorities.
-5. Present a concise health/status view.
-6. **Update Memory** — Save current status snapshot to `.ai-memory.md`.
-
-## Output format
-- Current state (from memory + repo scan)
-- What is working
-- What is incomplete
-- Risks or blockers
-- Recent changes (from memory)
-- Recommended next step
-
-## Checklist
-- [ ] Memory file read for historical context
-- [ ] Repository scanned for current state
-- [ ] Working features identified
-- [ ] Gaps and incomplete items listed
-- [ ] Risks or blockers flagged
-- [ ] Next priority recommended
-- [ ] Memory file updated with status snapshot
-
-## Rules
-- Be specific and evidence-based.
-- Separate facts from inference.
-- Do not recommend broad refactors without confirming scope; ASK if the fix would touch many areas.
-- Always read and update the memory file.
-
-## Quality Gate
-After completing, read `.kiro/skills/_scripts/verify-all.md` for full project verification checklist.
-
-## Related Skills
-- `/plan` → read `.kiro/skills/plan/SKILL.md` — Create plan for incomplete items
-- `/debug` → read `.kiro/skills/debug/SKILL.md` — Investigate flagged risks
-- `/deploy` → read `.kiro/skills/deploy/SKILL.md` — Deploy when ready
+---
+name: status
+description: "Project status summary, progress snapshots, repo overview, and outstanding work tracking. Use when the user wants to know where a project stands. Triggers: status, progress, overview, what's done, dự án đang ở đâu, tiến độ, tổng quan."
+agents: [project-planner, orchestrator]
+related-skills: [plan, debug, deploy]
+---
+
+## Memory Protocol
+**START**: Read `.ai-memory.md` from project root. This is the PRIMARY source for status — check all recorded history, decisions, tasks, bugs, and milestones.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: status snapshot, what's working, gaps, risks, and priorities.
+
+## Goal
+Summarize where things stand right now, leveraging the memory file for deep context.
+
+## Agent Routing
+- For project health overview → read `.kiro/skills/agents/agents/project-planner.md` and apply its knowledge
+- For multi-workstream status → read `.kiro/skills/agents/agents/orchestrator.md` and apply its knowledge
+- For technical debt assessment → read the relevant specialist agent file based on domain
+
+## Workflow
+1. **Read Memory** — Load `.ai-memory.md` as the primary context source.
+2. Inspect the repository, relevant files, and any recent context from the chat.
+3. Summarize what already exists.
+4. Identify gaps, risks, TODOs, and likely next priorities.
+5. Present a concise health/status view.
+6. **Update Memory** — Save current status snapshot to `.ai-memory.md`.
+
+## Output format
+- Current state (from memory + repo scan)
+- What is working
+- What is incomplete
+- Risks or blockers
+- Recent changes (from memory)
+- Recommended next step
+
+## Checklist
+- [ ] Memory file read for historical context
+- [ ] Repository scanned for current state
+- [ ] Working features identified
+- [ ] Gaps and incomplete items listed
+- [ ] Risks or blockers flagged
+- [ ] Next priority recommended
+- [ ] Memory file updated with status snapshot
+
+## Rules
+- Be specific and evidence-based.
+- Separate facts from inference.
+- Do not recommend broad refactors without confirming scope; ASK if the fix would touch many areas.
+- Always read and update the memory file.
+
+## Quality Gate
+After completing, read `.kiro/skills/_scripts/verify-all.md` for full project verification checklist.
+
+## Related Skills
+- `/plan` → read `.kiro/skills/plan/SKILL.md` — Create plan for incomplete items
+- `/debug` → read `.kiro/skills/debug/SKILL.md` — Investigate flagged risks
+- `/deploy` → read `.kiro/skills/deploy/SKILL.md` — Deploy when ready

package/.kiro/skills/test/SKILL.md

@@ -1,58 +1,58 @@
----
-name: test
-description: "Write tests, improve coverage, define test strategy, and add validation. Use when the user wants to test code, add unit/integration/e2e tests, or check coverage. Triggers: test, coverage, jest, vitest, playwright, spec, kiểm thử, viết test."
-agents: [test-engineer, debugger]
-related-skills: [debug, create, enhance]
----
-
-## Memory Protocol
-**START**: Read `.ai-memory.md` from project root. Check test framework in use, existing test coverage, known failing tests, testing patterns, and CI/CD test configuration.
-**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: tests changed, coverage deltas (if known), patterns established, and gaps.
-
-## Goal
-Improve confidence in the system through targeted testing.
-
-## Agent Routing
-- Primary → read `.kiro/skills/agents/agents/test-engineer.md` and apply its knowledge
-- If testing reveals bugs → read `.kiro/skills/agents/agents/debugger.md` and apply its knowledge
-- For E2E/integration tests with UI → read `.kiro/skills/agents/agents/frontend-specialist.md` and apply its knowledge
-- For API/backend tests → read `.kiro/skills/agents/agents/backend-specialist.md` and apply its knowledge
-- For security testing → read `.kiro/skills/agents/agents/security-auditor.md` and apply its knowledge
-
-## Socratic Gate
-Before writing tests, verify:
-1. What is the test scope? (unit, integration, E2E, API?)
-2. Does a test framework already exist in the project?
-3. What are the critical paths that must be tested?
-If any answer is unclear, ASK before proceeding.
-
-## Workflow
-1. **Read Memory** — Load `.ai-memory.md` for testing history and patterns.
-2. Identify the unit, integration, API, UI, or regression scope.
-3. Enumerate critical paths, edge cases, and failure modes.
-4. Add or propose tests that cover the most important risks first.
-5. Explain how to run the tests and what passing means.
-6. **Quality Gate** — Read `.kiro/skills/_scripts/checklist.md` and run test suite after writing tests.
-7. **Update Memory** — Save test details and coverage notes to `.ai-memory.md`.
-
-## Checklist
-- [ ] Test scope identified
-- [ ] Test framework confirmed/proposed
-- [ ] Critical paths covered
-- [ ] Edge cases included
-- [ ] Failure modes tested
-- [ ] Tests are stable (not brittle)
-- [ ] Run instructions provided
-- [ ] Memory file updated
-
-## Rules
-- Prefer stable tests over brittle tests.
-- Cover both happy path and key edge cases.
-- If no test framework exists, propose the lightest practical option.
-- Avoid changing unrelated production code; if tests require refactors, ASK before widening scope.
-- Always read and update the memory file.
-
-## Related Skills
-- `/debug` → read `.kiro/skills/debug/SKILL.md` — Fix failing tests or bugs found
-- `/create` → read `.kiro/skills/create/SKILL.md` — Create test fixtures or helpers
-- `/enhance` → read `.kiro/skills/enhance/SKILL.md` — Improve test quality and coverage
+---
+name: test
+description: "Write tests, improve coverage, define test strategy, and add validation. Use when the user wants to test code, add unit/integration/e2e tests, or check coverage. Triggers: test, coverage, jest, vitest, playwright, spec, kiểm thử, viết test."
+agents: [test-engineer, debugger]
+related-skills: [debug, create, enhance]
+---
+
+## Memory Protocol
+**START**: Read `.ai-memory.md` from project root. Check test framework in use, existing test coverage, known failing tests, testing patterns, and CI/CD test configuration.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: tests changed, coverage deltas (if known), patterns established, and gaps.
+
+## Goal
+Improve confidence in the system through targeted testing.
+
+## Agent Routing
+- Primary → read `.kiro/skills/agents/agents/test-engineer.md` and apply its knowledge
+- If testing reveals bugs → read `.kiro/skills/agents/agents/debugger.md` and apply its knowledge
+- For E2E/integration tests with UI → read `.kiro/skills/agents/agents/frontend-specialist.md` and apply its knowledge
+- For API/backend tests → read `.kiro/skills/agents/agents/backend-specialist.md` and apply its knowledge
+- For security testing → read `.kiro/skills/agents/agents/security-auditor.md` and apply its knowledge
+
+## Socratic Gate
+Before writing tests, verify:
+1. What is the test scope? (unit, integration, E2E, API?)
+2. Does a test framework already exist in the project?
+3. What are the critical paths that must be tested?
+If any answer is unclear, ASK before proceeding.
+
+## Workflow
+1. **Read Memory** — Load `.ai-memory.md` for testing history and patterns.
+2. Identify the unit, integration, API, UI, or regression scope.
+3. Enumerate critical paths, edge cases, and failure modes.
+4. Add or propose tests that cover the most important risks first.
+5. Explain how to run the tests and what passing means.
+6. **Quality Gate** — Read `.kiro/skills/_scripts/checklist.md` and run test suite after writing tests.
+7. **Update Memory** — Save test details and coverage notes to `.ai-memory.md`.
+
+## Checklist
+- [ ] Test scope identified
+- [ ] Test framework confirmed/proposed
+- [ ] Critical paths covered
+- [ ] Edge cases included
+- [ ] Failure modes tested
+- [ ] Tests are stable (not brittle)
+- [ ] Run instructions provided
+- [ ] Memory file updated
+
+## Rules
+- Prefer stable tests over brittle tests.
+- Cover both happy path and key edge cases.
+- If no test framework exists, propose the lightest practical option.
+- Avoid changing unrelated production code; if tests require refactors, ASK before widening scope.
+- Always read and update the memory file.
+
+## Related Skills
+- `/debug` → read `.kiro/skills/debug/SKILL.md` — Fix failing tests or bugs found
+- `/create` → read `.kiro/skills/create/SKILL.md` — Create test fixtures or helpers
+- `/enhance` → read `.kiro/skills/enhance/SKILL.md` — Improve test quality and coverage

package/.kiro/skills/ui-ux-pro-max/SKILL.md

@@ -1,65 +1,65 @@
----
-name: ui-ux-pro-max
-description: "Advanced UI/UX improvements — layout, design critique, copy refinement, interaction design, accessibility, and responsive patterns. Use when the user wants professional-grade UI/UX upgrades. Triggers: ui, ux, design, layout, responsive, giao diện, thiết kế, cải thiện UI."
-agents: [frontend-specialist, performance-optimizer]
-related-skills: [create, preview, enhance]
----
-
-## Memory Protocol
-**START**: Read `.ai-memory.md` from project root. Check design system, brand guidelines, component library, past UI decisions, accessibility notes, and responsive design patterns.
-**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: UI/UX changes, patterns used, a11y improvements, and brand consistency notes.
-
-## Goal
-Upgrade the product experience with clear, practical UI/UX improvements.
-
-## Agent Routing
-- Primary → read `.kiro/skills/agents/agents/frontend-specialist.md` and apply its knowledge
-- For performance of UI (load time, animations) → read `.kiro/skills/agents/agents/performance-optimizer.md` and apply its knowledge
-- For accessibility compliance → apply WCAG knowledge from frontend-specialist
-- For mobile responsiveness → apply mobile patterns from frontend-specialist
-
-## Socratic Gate
-Before improving UI/UX, verify:
-1. What screen, flow, or component is being improved?
-2. What is the current pain point? (visual, usability, accessibility, performance?)
-3. Are there existing design guidelines or component library?
-If any answer is unclear, ASK before proceeding.
-
-## Workflow
-1. **Read Memory** — Load `.ai-memory.md` for design history and UI patterns.
-2. Identify the screen, flow, or component being improved.
-3. Evaluate hierarchy, spacing, clarity, accessibility, states, feedback, and conversion friction.
-4. Recommend concrete improvements with rationale.
-5. When asked to implement, favor polished but maintainable UI.
-6. **Quality Gate** — Read `.kiro/skills/_scripts/checklist.md` and verify all states and accessibility.
-7. **Update Memory** — Save UI/UX decisions and patterns to `.ai-memory.md`.
-
-## Output format
-- UX issues found
-- Visual issues found
-- Recommended changes (prioritized)
-- Accessibility notes (WCAG compliance)
-- Implementation priorities
-- Component states covered (empty, loading, error, success)
-
-## Checklist
-- [ ] Target screen/component identified
-- [ ] Hierarchy and spacing evaluated
-- [ ] Accessibility checked (WCAG)
-- [ ] All states covered (empty, loading, error, success)
-- [ ] Mobile responsiveness considered
-- [ ] Performance impact assessed
-- [ ] Brand consistency maintained
-- [ ] Memory file updated
-
-## Rules
-- Optimize for clarity before decoration.
-- Respect existing brand and component patterns when present.
-- Include empty, loading, error, and success states when relevant.
-- Avoid widespread redesigns unless asked; prioritize small, safe diffs and ASK before large UI rewrites.
-- Always read and update the memory file.
-
-## Related Skills
-- `/create` → read `.kiro/skills/create/SKILL.md` — Implement UI components
-- `/preview` → read `.kiro/skills/preview/SKILL.md` — Preview design before implementation
-- `/enhance` → read `.kiro/skills/enhance/SKILL.md` — Improve existing UI code
+---
+name: ui-ux-pro-max
+description: "Advanced UI/UX improvements — layout, design critique, copy refinement, interaction design, accessibility, and responsive patterns. Use when the user wants professional-grade UI/UX upgrades. Triggers: ui, ux, design, layout, responsive, giao diện, thiết kế, cải thiện UI."
+agents: [frontend-specialist, performance-optimizer]
+related-skills: [create, preview, enhance]
+---
+
+## Memory Protocol
+**START**: Read `.ai-memory.md` from project root. Check design system, brand guidelines, component library, past UI decisions, accessibility notes, and responsive design patterns.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: UI/UX changes, patterns used, a11y improvements, and brand consistency notes.
+
+## Goal
+Upgrade the product experience with clear, practical UI/UX improvements.
+
+## Agent Routing
+- Primary → read `.kiro/skills/agents/agents/frontend-specialist.md` and apply its knowledge
+- For performance of UI (load time, animations) → read `.kiro/skills/agents/agents/performance-optimizer.md` and apply its knowledge
+- For accessibility compliance → apply WCAG knowledge from frontend-specialist
+- For mobile responsiveness → apply mobile patterns from frontend-specialist
+
+## Socratic Gate
+Before improving UI/UX, verify:
+1. What screen, flow, or component is being improved?
+2. What is the current pain point? (visual, usability, accessibility, performance?)
+3. Are there existing design guidelines or component library?
+If any answer is unclear, ASK before proceeding.
+
+## Workflow
+1. **Read Memory** — Load `.ai-memory.md` for design history and UI patterns.
+2. Identify the screen, flow, or component being improved.
+3. Evaluate hierarchy, spacing, clarity, accessibility, states, feedback, and conversion friction.
+4. Recommend concrete improvements with rationale.
+5. When asked to implement, favor polished but maintainable UI.
+6. **Quality Gate** — Read `.kiro/skills/_scripts/checklist.md` and verify all states and accessibility.
+7. **Update Memory** — Save UI/UX decisions and patterns to `.ai-memory.md`.
+
+## Output format
+- UX issues found
+- Visual issues found
+- Recommended changes (prioritized)
+- Accessibility notes (WCAG compliance)
+- Implementation priorities
+- Component states covered (empty, loading, error, success)
+
+## Checklist
+- [ ] Target screen/component identified
+- [ ] Hierarchy and spacing evaluated
+- [ ] Accessibility checked (WCAG)
+- [ ] All states covered (empty, loading, error, success)
+- [ ] Mobile responsiveness considered
+- [ ] Performance impact assessed
+- [ ] Brand consistency maintained
+- [ ] Memory file updated
+
+## Rules
+- Optimize for clarity before decoration.
+- Respect existing brand and component patterns when present.
+- Include empty, loading, error, and success states when relevant.
+- Avoid widespread redesigns unless asked; prioritize small, safe diffs and ASK before large UI rewrites.
+- Always read and update the memory file.
+
+## Related Skills
+- `/create` → read `.kiro/skills/create/SKILL.md` — Implement UI components
+- `/preview` → read `.kiro/skills/preview/SKILL.md` — Preview design before implementation
+- `/enhance` → read `.kiro/skills/enhance/SKILL.md` — Improve existing UI code