By aws-samples
Automate AIDLC operations on AWS: execute self-improving loops via continuous trace evaluation and PR proposals, run 4-stage canary deployments on Kubernetes with SLO gates and human approvals, handle incident response from alarms, enforce cost budgets with model recommendations, and log audits for compliance.
npx claudepluginhub aws-samples/sample-oh-my-aidlcops --plugin agenticops모든 사용자 발화·agent 행동·phase 전환·gate 판정을 ISO 8601 타임스탬프와 함께 감사 로그에 기록한다. 사용자 입력은 축약·요약 없이 verbatim blockquote로 보존하며, SOC2·ISMS-P 감사 요구사항에 매핑되는 보존 정책(30·90·365일)을 프로젝트별로 선택한다. 모든 AIDLC skill이 호출 가능한 공통 감사 계층을 제공한다.
Agent 또는 skill의 프로덕션 배포를 canary 1% → 10% → 50% → 100% 4단계로 자동 진행한다. 각 단계는 continuous-eval 통과와 SLO 준수를 gate로 하며 circuit breaker가 SLO 위반을 감지하면 즉시 이전 단계로 자동 롤백한다. 100% 승격은 사람 승인이 필수다.
Ragas 기반 품질·안전 평가를 매 배포 직후와 매 1시간 cron으로 실행하여 faithfulness, answer relevance, context precision, toxicity, PII leakage 지표를 측정한다. Golden dataset 관리와 regression gate(baseline 대비 5%p 하락 시 차단)를 수행하며 autopilot-deploy의 canary gate에 사용된다.
AWS Pricing과 Cost Explorer를 MCP로 조회하여 agent별 비용 귀속을 집계하고 예산 alert을 발행하며, 사용 패턴이 정당하면 Opus → Sonnet → Haiku 모델 다운그레이드를 권고한다. 월간 예산 ceiling을 초과할 것으로 예상되는 배포는 veto하여 autopilot-deploy의 pre-flight gate로 작동한다.
CloudWatch/Prometheus 알람을 수신하여 severity 분류, runbook 조회, hypothesis 생성, 진단 MCP 쿼리, 사람 승인 기반 remediation 수행까지 자동화한다. SEV1은 즉시 on-call 호출, SEV2/3은 agent가 drafted response를 준비한 뒤 사람 승인 후 실행한다.
Langfuse production trace를 관찰하고 품질 regression·비용 이상·실패 패턴을 자동 분석한 뒤 prompt·skill 수정안을 PR draft 형태로 제안한다. Observe → Analyze → Propose → PR 4단계 루프를 실행하며 self-improving-agent-loop ADR의 자동화 경계(Rollout/Score/Filter까지만 자동, Train/Deploy는 사람 승인)를 강제한다.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Battle-tested Claude Code plugin for engineering teams — 50 agents, 188 skills, 68 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Share bugs, ideas, or general feedback.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim