Claude Skills by Yoodaddy0311

Testing standards enforcing 80% coverage, Testing Pyramid, and TDD workflow. Auto-activates when: writing tests, implementing features, fixing bugs, refactoring code. Triggers: test, coverage, TDD, unit test, integration, e2e, jest, vitest, playwright

Intelligent token optimization engine with adaptive compression and persona-aware output. Auto-activates when: context usage >75%, large-scale operations, --uc flag, output exceeds budget. Triggers: compress, efficient, tokens, --uc, large output, context limit

Dynamic tool approval predicates and the bash command allowlist. Use when the user asks about HITL approvals or tightening the pre-bash gate. Triggers: tool approval, approval predicate, bash allowlist, pre-bash, permission gate, HITL.

에이전트 도구 설계 아키텍처 패턴 - 통합 vs 분리 트레이드오프, description engineering, architectural reduction. Auto-activates when: creating agent tools, debugging tool failures, optimizing tool sets. Triggers: tool design, tool API, MCP tool, agent tool, 도구 설계

Discovery flowchart for Artibot's skill library. Use this as orientation when the user asks 'what skills do you have', 'how do I do X', 'what commands are available', or when picking the right tool for an unfamiliar task.

Evidence-before-claims verification enforcing proof of completion before any "done" claim. Auto-activates when: completing tasks, reporting results, claiming success, writing summaries. Triggers: done, complete, finished, implemented, fixed, resolved, verified, shipped

Quality enforcement for casual or natural-language coding requests. Use when handling natural language coding requests, multi-part instructions, or casual Korean/English coding commands like '해줘', '만들어', '수정해', '바꿔', '고쳐'.

Visual regression testing using SSIM-based screenshot comparison. Auto-activates when: visual testing, UI regression checks, screenshot comparison, component validation, CSS fix suggestions needed. Triggers: visual, screenshot, regression, baseline, pixel, SSIM, UI validation, component check

Evidence-before-claims 거버넌스 엔진 - 6개 safety gate, 증거 기반 디버깅, anti-slack 탐지, 결론 무결성 검증. Auto-activates when: AI governance needed, debugging failures, unverified claims, evidence-based workflow. Triggers: yes-md, evidence, safety gate, verify first, 증거 기반, 검증 우선

Production 무중단 마이그레이션 6섹션 체크리스트 — production 매출·고객 데이터가 걸린 작업. 자연어 트리거: '마이그레이션 해줘', 'DB 이전', '결제 시스템 교체', '무중단 배포', '점진 전환', 'Postgres를 Mongo로 바꿔', 'migrate from X to Y', 'switch from X to Y', 'cutover', 'canary rollout', 'blue-green deployment'.