claude

develop

Engineering skills: SQL, clean architecture, clean code, DDD, database optimization, chaos engineering, Spring Boot, Kotlin, TDD, testing, bug diagnosis, security audit, architecture review, deprecation & migration, SRE, performance profiling & optimization, incident response, documentation strategy, like-my-code (a repo's style as harness conventions, each rule with evidence and a cited source). ADR drafting moved to write:plans (ADR format); diagram moved to write:diagram.

3 on GitHubby newkayak12v2.2.0MITupdated todayengineering
/

Plugin develop from marketplace newkayak12-claude-skills in newkayak12/claude-skills. Commands read from the repo's manifest — today.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (36)

  • architecture-designer

    Use when designing or documenting system architecture — topology, trade-offs, ADRs, database choice ("시스템 아키텍처 설계해줘", "ADR 써줘", "design this system"). version: "1.3.0" - "design a system architecture for this product" - "should we use microservices or a monolith?" - "write an ADR for this technology

  • architecture-review

    Use when an existing codebase feels hard to change and you want ranked refactor targets from git history, not a redesign. Triggers on: "어디부터 리팩토링할까", "코드가 얽혀서 손대기 힘들어", "where should we refactor this repo". - "Our repo is painful to change — find the modules worth deepening first" - "Review the arch

  • architecture-workflow

    Use when designing a system from scratch, evaluating a monolith-to-MSA migration, or needing a structured end-to-end architecture process from domain discovery to documentation. Triggers on: "system architecture from scratch". - "Design a full architecture for our new e-commerce platform from domain

  • bug-diagnoser

    Use when a bug, failing test, error, or wrong result is reported and the cause is unproven — invoke before reading or editing code. Triggers on: "fix this bug", "debug this", "why is this failing", "고쳐줘", "안 돼요", "에러 나요", "왜 이러죠", "갑자기 안 돼", "디버깅". - "Page 2 of the product list shows 9 items instead

  • chaos-engineer

    Use when you want to test whether a system survives real failures. Triggers on: "장애 주입 테스트", "game day 준비", "pod 죽여보고 싶어", "chaos experiment", "kill a pod in staging", "simulate zone outage". Not for active incidents. - "I want to run a chaos experiment on our Kubernetes cluster to test pod failure

  • circuit-breaker-tuner

    Use when a slow or failing downstream exhausts upstream threads and breakers, bulkheads or fallbacks need tuning. Triggers on: "서킷 브레이커 설정", "서킷이 자주 열려", "cascading failure", "circuit breaker tuning". Not for SQL or chaos. - "Our circuit breaker is tripping too often and causing unnecessary service

  • clean-architecture

    Use when designing layered architectures, separating concerns across boundaries, implementing ports and adapters, or when business logic is leaking into frameworks and the codebase feels tangled. Triggers on: "의존성 규칙", "레이어 아키텍처". version: "1.0.0" - "design a clean architecture for this service" - "

  • clean-code

    Use when a diff, branch or PR needs review or a gate verdict, code needs refactoring, or a requirement needs implementing cleanly. Triggers: "코드 리뷰", "이 브랜치 리뷰해줘", "PR 리뷰", "리팩토링", "어떻게 구현해?", "review this branch", "code review". version: "2.1.0" - "quality gate: does this diff meet the acceptance c

  • cli-developer

    Use when building a command-line tool — subcommands, flags, prompts, progress bars, shell completions, cross-platform distribution. Triggers on: "CLI 도구 만들어줘", "서브커맨드 설계", "build a CLI". Not for web UIs or REST APIs. - "Build a CLI tool that manages deployment configurations across environments" - "

  • connection-pool-tuner

    Use when DB connections time out or the pool is exhausted under load. Triggers on: "커넥션 풀 고갈", "HikariCP 사이즈 어떻게 잡아?", "트래픽 몰리면 타임아웃", "pool exhaustion", "pgBouncer tuning", "Connection timeout". - "Our application is getting 'connection pool exhausted' errors under load" - "Help me tune HikariCP se

  • database-optimizer

    Use when DB slowness is server-side, not query text. Triggers on: "락 경합", "VACUUM 밀림", "shared_buffers 튜닝", "파티셔닝 설계", "lock contention", "stale statistics", "InnoDB buffer pool". Not for SQL rewrites or pool sizing. - "Our database queries are slow and we're hitting performance bottlenecks" - "Help

  • database-workflow

    Use when investigating database performance degradation end-to-end — from query quality through server tuning, connection layer, and transaction safety. Triggers on: "database workflow", "DB 성능 전체", "database performance investigation", "DB 전체 점검". - "Run the full database workflow — prod DB is slow

  • deprecation-and-migration

    Use when dropping, renaming, or retiring a column, table, API, or feature others may use — counts consumers, plans expand/contract, recommends deprecate vs keep. Triggers on: "컬럼 지우는 마이그레이션", "이 API 없애자", "drop this column". - "Rename users.name to full_name on a live table with 5M rows, no downtime

  • dockerfile-optimizer

    Use when someone shares a Dockerfile and needs it improved for build speed, image size, or security. Triggers on: "도커 최적화", "이미지 크기", "빌드 시간", "Dockerfile", "docker optimize", "이거 좀 봐줘" (when a Dockerfile is pasted). Not for Kubernetes or compose. - "optimize this Dockerfile" - "why is my Docker ima

  • documentation-strategy

    Use when a team needs a plan for what docs to write. Triggers on: "문서 뭐부터 써야 해?", "온보딩 문서 정리", "런북/ADR 체계", "doc coverage map", "documentation audit", "주석/독스트링 달아줘", "OpenAPI 문서 만들어줘". - "Our codebase has no docs and new engineers keep asking the same questions repeatedly" - "We have documentation b

  • domain-driven-design

    Use when aligning code structure with business concepts, designing service boundaries, or when domain experts and developers cannot agree on what things mean. Triggers on: "도메인 모델링", "바운디드 컨텍스트", "DDD", "domain-driven design", "bounded context". version: "1.0.1" - "help me model this business domain

  • event-storming

    Use when starting a product, untangling legacy, or mapping a business process before code. Triggers on: "이벤트 스토밍", "도메인 이벤트 뽑아보자", "도메인 모델링 워크숍", "workshop with domain experts", "map our business flow". - "We're starting a new product and need to model the domain before writing code" - "Help me run

  • flaky-test-analyzer

    Use when tests pass locally but fail in CI, pass some runs and fail others, or someone suspects a test is unreliable but cannot reproduce the failure consistently. Diagnoses root causes and provides concrete fixes. Triggers on: "flaky test". - "Our tests pass locally but randomly fail in CI — I need

  • frontend-developer

    Use when building or fixing UI — React/Next.js components, layouts, hooks, forms (App Router, TypeScript, Tailwind defaults). Triggers on: "build a React component", "React 컴포넌트", "Next.js 폼". Not for Vue/Svelte/Angular. - "Build a React dashboard with data fetching, state management, and responsive

  • incident-response-playbook

    Use when a production incident is active or needs a post-mortem. Triggers on: "장애 났어", "프로덕션 터졌어", "포스트모템 써줘", "severity 분류", "prod is down", "write an RCA". Not for SLO setup or chaos tests. - "We just had a production outage and need a structured incident response process" - "Help me create an on-

  • kotlin-specialist

    Use when writing idiomatic Kotlin — coroutines and Flow, KMP, Compose, Ktor, DSLs. Triggers on: "Kotlin coroutines", "코루틴", "코틀린으로 전환", "Flow 취소 처리". Not for Spring Java backends or Android XML layouts. - "Help me write idiomatic Kotlin code using coroutines for async processing" - "Convert this Jav

  • like-my-code

    Use when a repo's code style must become written policy — harness conventions (coding.md, boundaries.md) backed by repo evidence. Triggers: "내 코드 스타일로 컨벤션 뽑아줘", "이 레포 스타일을 정책으로", "like my code", "extract conventions from this repo". version: "0.1.0" - "이 레포 코드 스타일 분석해서 하네스 컨벤션으로 만들어줘" - "참고 프로젝트 하나

  • operations-workflow

    Use when preparing a service for production, hardening a flaky system, or building lasting operational improvements after an incident. Triggers on: "production readiness review", "going to prod", "pre-launch ops check", "system hardening", "운영 준비". - "Run a full production readiness review before we

  • performance-profiling-optimization

    Use when something is slow and you need data-driven profiling. Triggers on: "API가 느려요", "병목 찾아줘", "메모리 계속 늘어나", "p99 latency spike", "profile this endpoint", "high CPU". Not for SQL rewrites or pool sizing. - "Our API response times degraded after the last deploy — help me profile and fix it" - "Pro

  • scenario-actor

    Use when one API scenario spec must be run by hand against a live server — curl per step, captured values chained, evidence logged, verdict returned. Triggers: "이 시나리오 하나만 돌려줘", "이 spec 실행해줘", "run this scenario", "spec=… BASE_URL=…". - "Run S3 from tests/scenarios against the staging URL and show m

  • scenario-director

    Use when a backend's API scenario tests must be collected or read from md, written as specs, then run against a live server by one actor AI per flow (or specs only). Triggers: "API 시나리오 테스트", "시나리오 md 읽고 서버에 돌려줘", "flow test", "시나리오 CI 붙여줘". - "Set up scenario tests for this backend and run them aga

  • security-auditor

    Use when auditing a feature, paths, or a whole service for exploitable flaws in auth, input handling, secrets, or payments — each finding traced entry→sink. Triggers on: "is this exploitable", "보안 점검", "취약점 찾아줘". - "Audit the checkout and order APIs for anything an attacker could actually exploit" -

  • service-boundary-validator

    Use when checking if services can really split or deploy alone. Triggers on: "서비스 쪼개도 될까?", "결합도 너무 높은 것 같아", "DB 공유 문제 없나?", "distributed monolith", "validate this service boundary", "split or merge". - "Should this feature be a new microservice or stay in the existing service?" - "Validate whether

  • spec-driven-development

    Use when a feature should be specified before it is coded — stories, acceptance criteria, tasks, a per-criterion check. Triggers: "스펙 먼저", "명세부터 쓰고 구현", "수용 기준 먼저", "spec first", "spec-driven development". version: "1.1.0" - "write the spec and acceptance criteria first, then implement" - "let's do

  • spring-boot-engineer

    Use when building or extending a Spring Boot 3.x Java backend — REST, Spring Security, JPA, WebFlux, Actuator. Triggers on: "Spring Boot API", "스프링 시큐리티 설정", "JPA 연동". Not for service decomposition or query tuning. - "Build a REST API with Spring Boot including security, JPA, and error handling" - "

  • sql-pro

    Use when someone needs help writing or rewriting SQL — authoring complex joins, CTEs, window functions, or recursive queries — or designing a schema from scratch, normalizing an existing one, or migrating queries between database dialects. - "Rewrite this slow SQL query that's doing full table scans

  • sre-engineer

    Use when setting up production reliability practices. Triggers on: "SLO 정하고 싶어", "에러 버짓", "알람 피로", "반복 작업(toil) 줄이기", "golden signals dashboard", "burn-rate alert". Not for active incidents or chaos tests. - "Define SLOs and error budgets for our user-facing API services" - "Help me set up observabi

  • test-driven-development

    Use when someone wants tests that prove a fix or feature actually works, not just tests that happen to pass — TDD, red-green-refactor, falsifiable tests. Triggers: "TDD", "테스트 먼저 작성", "test-first", "red-green-refactor". - references/testing-anti-patterns.md - "let's do TDD on this feature" - "prove

  • test-master

    Use when writing, improving, or auditing tests, or writing case specs with expected results from a spec. Triggers: "테스트 작성", "테스트 케이스 작성", "test case writing", "단위 테스트", "커버리지 분석", "test plan", "defect report". version: "1.2.0" domain: quality role: specialist scope: testing output-format: report re

  • testing-workflow

    Use when someone wants to build a complete, stable test suite from scratch — starting with TDD discipline, moving into coverage strategy, and ending with flaky test elimination. Triggers on: "testing workflow", "테스트 전체 프로세스", "TDD부터 커버리지까지". - "testing workflow 전체 돌려줘" - "TDD부터 커버리지 전략까지 단계별로 해보자" -

  • transaction-boundary-reviewer

    Use when data goes inconsistent or transactions cause locks. Triggers on: "데이터 정합성 깨져", "@Transactional 범위", "트랜잭션 락 타임아웃", "isolation level", "two writes atomic", "deadlock under load". - "Data is inconsistent after failures — review our transaction boundaries" - "Help me identify where distributed

Hooks (1)

  • SessionStart

    sh

View source on GitHub

More from newkayak12/claude-skills

All 16 plugins →

teams

claudecodex

A sibling of graph for requests too big for one pass: a TaskManager MCP (teams) sizes the request; size L is planned into a PRD and user stories, split into packages that each run the full harness in their own worktree, integrated, QA'd and gated by a background daemon; size S is handed to the development harness. Entry skills teams:orchestrate/develop/document/plan/qa/sprint, board and ticket views (tm_board, teams:board). Runs are kept under .teams_output/ and ~/.harness/tasks/. Zero runtime dependencies beyond Node 18+.

15 skills · 1 MCP server · hooks

3

portfolio

claude

Portfolio and career skills: manage (the portfolio deck as one workflow — material, skeleton, feedback, deck, versions), material (collect handed material), fit (JD or company type), portfolio feedback, rewriting and JD tailoring, pattern analysis, mock interview, interview plan, job-application-workflow (through a 자기소개서 step via write:writer-verification), deck-builder (reference template.pptx + deck.mdx → pptx; recolors a pptx to a brand palette), resume-builder (resume-deck.mdx → the user's own .docx, PDF, page fit, final AI-trace check), and render-review (page-by-page review of a rendered deck or resume).

12 skills · hooks

3

cognition

claude

Thinking quality skills: assumption extraction, bias auditing (v2 — context probe, per-bias remedies, calibration check), fallacy detection, mental models, epistemic reasoning, tradeoff articulation, question upgrading, and second-order thinking.

10 skills · hooks

3

write

claude

Writing skills: plans (gate-ready implementation plans and ticket breakdowns with production-time gap/ambiguity checks + per-step pass bars; technical blog posts; SBI feedback), prd (PRDs, design docs, RFCs and proposals co-written section by section with reader testing), adr (ADRs and fixed-template design reviews), requirements (a requirement or 기획서 split into actors, rules, open questions with defaults, and items with Given/When/Then criteria),spec (a settled conversation synthesised into a spec, open points marked, no re-interview), skill writing, and writer verification (v2 — five passes incl. a humanizer for machine tells, draft loop that rewrites until 🔴🟡 = 0, PR descriptions from a diff as first-class input), and tech-book (performance-based book arc, cumulative examples, transfer practice, six required teaching elements within a chapter length budget, staged review loops with defined severities, lab-running fact checks, pinned chapter end states and a cap closure pass, and PDF in bundled NanumGothic), diagram (checked self-contained SVG + PNG figures: page layout, B-tree, lock timeline, ER, chart, architecture, sequence; moved from develop). Knowledge-base, graph, RAG, and query skills moved to the knowledge plugin.

10 skills · hooks

3

knowledge

claudecodex

Answerability-gated knowledge skills and local MCP: linked Markdown, relation-aware graph extraction, graph visualization, RAG preparation, SQLite index building, and source-grounded retrieval.

8 skills · 1 MCP server · hooks

3

think

claudecodex

Thinking and ideation skills: mentor (any-field mentoring — takes a position, tests yours, hands over the judgment rule), brainstorming (≥3 options before judgment, kill-criteria convergence, hands off to write:plans), grill (a held plan interrogated: repo read first, one numbered round with recommended answers), devils-advocate (steel-man first, core vulnerability + reversibility), redefine-problem, back-to-basics, untangle-thoughts, and negotiate (counsel on your side).

8 skills · hooks

3

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

agents-md

claude

AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.

anthropics/claude-code 155,476

agent-skills

claudecodex

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

addyosmani/agent-skills 116,782

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

Install the "AAS Security Engineer" workflow plugin from Agentic Awesome Skills.

12 skills

sickn33/agentic-awesome-skills 49,620

Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security

4 skills · 3 agents

wshobson/agents 42,461

Maintain develop?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins16 plugins