원클릭으로
2026-Kite-Class-Platform
2026-Kite-Class-Platform에는 VictorAurelius에서 수집한 skills 39개가 있으며, 저장소 수준 직업 범위와 사이트 내 skill 상세 페이지를 제공합니다.
이 저장소의 skills
Dùng khi user nói 'start new session', 'bắt đầu session mới', '/start-session', 'what's the state?', 'tình trạng hiện tại', hoặc khi cần load context sau khi /clear. Load: CLAUDE.md digest, current wave, open PRs, failing CI, active blockers. Output: single summary block. Cũng check session-lock conflicts khi chạy parallel agents.
Dùng khi user nói 'plan wave', 'cluster gaps', 'wave-pack', 'next wave', hoặc khi cần group ≥3 disjoint gaps thành 1 wave-pack chạy parallel agents. Output: wave plan markdown (foundation PR-ready) + file-overlap matrix + 3-5 agent prompts. Codify pattern từ Wave Observability 2026-04-28 (3 gaps trong ~75 min vs ~6h serial = 5x speedup).
Use when PR touches kitehub-email templates (*.html under templates/emails/), kiteclass-gateway email templates, any new customer-facing email, phrases 'review email', 'kiểm tra email template', 'gửi email cho tenant', 'trial-expiry email', 'welcome email'. Enforces brand/legal/i18n/mobile/GDPR-PDPL gate before customer send per output-review-mandate §5.7.
Dùng khi 'kit parity', 'kit production parity', 'review Track 2 port', 'port theo ui kit', 'kit vs production', 'back-port kit', hoặc trước khi merge PR port kit → production / production → kit. Verifies 4-layer V-model parity (要件定義 / 基本設計 / 詳細設計 / コンポーネント設計) giữa HTML kit prototype và production Next.js code. Bidirectional: kit→production port AND production→kit back-port (production led). Output report /4-layer to documents/04-quality/audits/parity/.
Dùng khi PR thay đổi AI Branding behavior — model swap (Ollama → Bedrock, Llama → Gemma), prompt template change, AIClient/Step interface, ContentModerationService, InstanceQualityReviewer logic, 5 *QualityCheck classes. Auto-trigger qua audit-gate khi files match `kiteclass/kiteclass-core/src/main/java/com/kiteclass/core/module/{ai,branding,instance,quality,moderation,provisioning}/**/*.java`. Manual checklist mode (5 sections × scoring) + delta-vs-baseline rubric. Output: `documents/04-quality/audits/ai-branding/YYYY-MM-DD-<change>.md`.
Dùng khi user nói 'security audit', 'pentest', 'kiểm tra bảo mật', 'dependency scan', hoặc trước production deploy. Deep security check /100 — vượt xa quality-audit §2. v2 audit format mandatory per GAP-564: mỗi control bind với evidence block (Command run + Output + Verdict + Evidence artifact ID).
Dùng khi user nói 'audit prototype', 'review ui kits', 'check landing parity', 'kiểm tra prototype HTML', hoặc trước khi merge wave UI kits. Extends quality/ui-review for static HTML prototype path (vs Next.js dev server). Runs 3 scripts: link-checker (no broken hrefs in kit HTML) + landing-parity (stricter than Tier 1: cards + scores + persona pills + screen counts) + state-coverage (default/loading/empty/error/success/dark per dossier §4). Codifies 2026-04-29 GAP-263 Phase 2 + closes GAP-264.
Dùng khi user nói 'end session', 'đóng session', 'kết thúc session', '/end-session', 'finish work', 'wrap up', hoặc trước khi /clear cho session quan trọng. Working-tree clean + sync gate (Step 0a: no dirty/uncommitted, main synced OR in-flight branch pushed+handed-off) + docs-sync 5-target (CSV/ROADMAP/wave-history/MEMORY/session-handoff per session-end-context-check.md §4.5) + auto-write session-handoff note + archive session-lock + 1-line summary. Symmetric counterpart cho /start-session.
Dùng khi user nói 'review UI', 'check design', 'audit screenshots', 'UI trông thế nào', hoặc sau mỗi PR có thay đổi frontend. Auto-chạy sau mỗi frontend PR. Capture before/after screenshots, score per-screen trên thang /128. Covers KiteClass (port 4700) + KiteHub (port 4701) — tất cả public, auth, và dashboard pages.
Dùng khi user nói 'extract citations', 'trích dẫn luận văn', 'audit thesis cite', 'verify bibliography', 'orphan citation check', 'kiểm tra cite luận văn', hoặc khi review thesis chapter trước defense. Parse `[N]` cite keys từ thesis chapters + verify chéo với `documents/08-thesis/references/bibliography.md` → báo 3 bucket: matched / orphan-body (cite không có entry) / orphan-bib (entry không cite).
Dùng khi user nói 'figure curation', 'thesis figures', 'caption', 'đánh số hình', 'INDEX figure', 'curate figure cho Chapter N', 'add figure to thesis', 'kiểm tra caption hình', 'audit figure thesis'. Codifies selection criteria (figure vs table vs prose), per-chapter numbering N.M, Vietnamese caption format, per-chapter INDEX generation. Pair với GAP-646 thesis-docx pipeline.
Use when user asks to generate a Word / docx — contract, letter, policy, certificate, 'hợp đồng', 'công văn', 'khoá luận', thesis report. Wave 5 shipped teacher-contract; Wave 100.7 Phase 3b shipped thesis-report (Create pipeline). Additional templates land per GAP-047 / GAP-208 roadmap.
Dùng khi PR thêm/sửa `.claude/hooks/*.py`, 'review hook', 'kiểm tra hook coverage', 'hook test missing', 'audit hook', 'hook BLOCK false-positive'. 13-point rubric (Wave 75 outside-in fold-in): event matcher + BLOCK/WARN gradient + override trailer + fail-safe + wiring + false-positive + idempotency + performance budget + exit code matrix + fixture parity + stdin malformed JSON + stdout JSON schema + cold-start vs steady-state. Reference rubric-checklist.md cho full criteria + edge-case-catalog.md cho 15 known patterns.
Dùng khi user nói 'api audit', 'contract check', 'kiểm tra API', 'endpoint match docs?', 'breaking change?', hoặc trước release. Verify API endpoints match api-contract.md /100.
Dùng khi user nói 'audit', 'quality check', 'kiểm tra chất lượng', 'điểm chất lượng', 'ready to merge?', 'persona coverage', hoặc trước khi merge wave vào main. Chấm điểm 11 categories /110 điểm (10 tech + 1 persona coverage).
Dùng khi user nói 'business audit', 'logic check', 'kiểm tra business logic', 'code đúng rules chưa', hoặc trước GA release. Verify code implement đúng rules.md + use-cases.md. 5 categories /100.
Dùng khi user nói 'ops audit', 'production ready?', 'kiểm tra ops', 'deploy checklist', 'monitoring check', hoặc trước GA release. Production operations readiness /100.
Dùng khi user nói 'perf audit', 'performance check', 'load test', 'kiểm tra hiệu năng', 'N+1', 'bundle size', hoặc trước production deploy. Baseline performance metrics /100.
Dùng khi user nói 'check docs', 'đã update đủ docs chưa', 'pre-merge check', 'pre-pr check', 'living docs check', '/session-docs-check', hoặc trước khi commit/push/PR/merge. Detect thay đổi trong branch hiện tại, đối chiếu với Living Documents matrix, báo cáo files PHẢI update mà chưa update (rules.md, use-cases.md, api-contract.md, ROADMAP.md, gap files, skill index, README các tầng folder).
Use when PR touches marketing copy (landing pages, blog, pricing page, brochure), legal docs (Terms of Service / TOS, Privacy Policy, Data Processing Agreement / DPA, SLA), or when user says 'review legal', 'review marketing', 'update TOS', 'privacy policy', 'kiểm tra pháp lý', 'xem điều khoản', 'điều khoản sử dụng'. Establishes legal counsel sign-off, dated versioning, compliance checklist for Vietnam (Nghị định 13/2023 PDPL, Luật Quảng cáo, Luật Bảo vệ Người tiêu dùng) + extraterritorial (GDPR, CAN-SPAM). Required before ship per output-review-mandate §5.8.
Use khi sắp tag release / push image / merge PR thay đổi terraform-aws hoặc workflow CI. Phrases trigger — "preflight deploy", "simulate deploy", "kiểm tra deploy trước khi tag", "check trước khi staging", "what could break before deploy", "deploy dry-run", "find pre-deploy issues". Chạy 8 categories of checks chống lại hệ thống thật để bắt class-of-issues mà tag-time fail (multi-arch base image, IAM ARN naming drift, OIDC trust scope, secret naming, region pin, workflow if-conditions). Grounds in AWS Well-Architected, OpenSSF Scorecard, GitHub Actions Hardening Guide, Sigstore Cosign Best Practices, CIS Docker Benchmark.
Dùng khi user nói "smoke test AWS", "verify Phase 2.3", "kiểm tra AWS sau apply", "post-apply check", "verify AWS resources", "AWS health check", "kiểm tra hạ tầng AWS", "Phase 2.1 verify", "Phase 2.2 OIDC check", "Phase 4 staging verify", hoặc khi vừa hoàn tất `terraform apply` và cần verify state. Tier 1 read-only ONLY per `.claude/rules/agent-aws-access.md` §2 — không create/delete/modify resources, không đọc secret values. Output: pass/fail summary + audit artifact saved to `documents/04-quality/audits/aws-verification/YYYY-MM-DD-<topic>.md`.
Dùng khi user upload/paste file .tf, hỏi về "review terraform", "kiểm tra hạ tầng", "IaC review", "deploy lên AWS", "deploy lên Oracle Cloud", "OCI deployment", "chiến lược deploy cloud", "terraform plan", "terraform best practices", "module structure", "state management". Kích hoạt khi thấy từ khoá: EC2, EKS, VPC, RDS, OCI Compute, OCI VCN, Autonomous DB, OKE, infrastructure/terraform-aws, infrastructure/terraform-oracle.
Use when user mentions 'deploy version', 'release v1.0', 'go-live', 'tag release', 'production cutover', 'release checklist', 'deploy plan', or before tagging any production release. Guides through `release-deploy-standard.md` per-bump-type checklist + go-live runbook + smoke test + rollback procedure.
Use when user says 'development workflow', 'PR workflow', 'branching strategy', 'how to ship', 'quy trình phát triển', 'cách làm PR', or before starting a new feature/PR. Comprehensive end-to-end workflow from planning through release for KiteClass Platform — covers branching, commits, PR template, 7 phases (planning → testing → docs → review → merge), release/hotfix, troubleshooting.
Use when user says 'priority PR plan', 'urgent PR queue', 'plan PRs by priority', 'critical bug fix queue', 'PR-KC plan', 'lập kế hoạch PR ưu tiên', 'PR khẩn', or when scoping a temporary deviation from the master implementation plan (critical bug, unblocked PR, urgent technical debt, manual-test findings). Standards for creating temporary priority PR plans that comply with master implementation plan.
Nhac update living docs sau moi PR/wave
Dùng khi user runs `/check-pr` hoặc nói 'check PR', 'verify CI', 'kiểm tra PR', 'ready to merge?'. Monitor CI via scripts (`scripts/check-ci.sh`), run local E2E + unit tests if Docker / JAVA_HOME available, output verdict (✅ ready / ❌ fix needed / ⚠️ conditional).
Dùng khi user runs `/continue` hoặc nói 'tiếp tục', 'pick next task', 'làm tiếp', 'next priority'. Reads plan documents in priority order (P0 first), applies wave-eligibility pre-flight (Step 0 — ≥3 disjoint sub-tasks → wave + parallel agents), then executes via Superpowers methodology.
Dùng khi user runs `/fix-pr <PR-number>` sau khi `/check-pr` flagged issues. Determines fix strategy (Case A: PR open → amend on branch; Case B: merged → follow-up PR), then addresses brainstorm/test/doc/methodology gaps.
Dùng khi user runs `/quality-plan [scope]` sau `/quality-audit` hoặc `/business-gap-check`. Reads latest audit report, extracts remaining gaps, groups them into PR plan with priority + estimates + wave grouping if dependencies overlap.
Dùng khi user runs `/start-pr` (check current PR artifacts) hoặc `/start-pr PR-X.Y feature-name` (start new PR). Verifies Superpowers artifacts (brainstorm, task breakdown, TDD compliance, tests, docs) and either reports status or kicks off new feature with the methodology scaffolding.
Use when user asks to generate an Excel / xlsx — attendance report, roster, financial breakdown, grade sheet, 'báo cáo điểm danh', 'xuất Excel'. Wave 5 ships weekly attendance report only; additional templates land in later waves per GAP-047 roadmap.
Use when user asks to generate a PDF — invoice, certificate, transcript, letter, report, 'hóa đơn', 'xuất PDF', 'render PDF'. Wave 5 ships Vietnamese tax invoice only; additional templates land in later waves per GAP-047 roadmap.
Dùng khi user nói 'design pattern audit', 'pattern check', 'kiểm tra design patterns', 'God service đâu', 'anti-pattern hotspot', hoặc trước Wave 7+ refactor planning. Score code against `.claude/rules/design-patterns.md` §3 BANNED list. Output: hotspot list (file path + LOC + violated pattern) + score /100.
Dùng khi user nói 'status', 'repo status', 'tình trạng repo', 'health check', 'repo có ổn không', 'security', 'CVE', 'vuln', hoặc khi bắt đầu conversation mới cần đánh giá nhanh trạng thái remote repo. Checks: CI, PRs/branches, audit gaps, GitHub Security (Dependabot + code-scanning + secret-scanning) → output level GREEN/YELLOW/ORANGE/RED/BLACK.
Dùng khi user nói 'rework audit', 'PR nào cần rework', 'context-degraded PRs', 'chất lượng PR gần đây', 'retroactive audit', 'audit lại wave X'. Re-audit PRs merged during high-context-pressure sessions (GAP-199). Output: prioritized rework backlog (P0/P1/P2) feeding audit-to-gap-pipeline.
Dùng khi PR thêm/sửa file trong `documents/04-quality/gaps/GAP-*.md`, 'review gap', 'peer-review gap', 'gap có hợp lệ không?', 'kiểm tra gap', hoặc trước khi đổi status 🔵 OPEN → 🟡 PLANNED. Peer-review checklist cho gap files.
Dùng khi PR thêm/sửa file trong `.claude/rules/*.md`, 'review rule', 'kiểm tra rule change', 'rule PR'. ADR-like reviewer checklist cho rules docs.