teo-project
claude[ARCHIVED] interactive-os 전용 파이프라인 스킬. 설치 대상이 아닌 참고 자료
24 skills · 4 agents
현재 Codex 개인 스킬 미러와 한국어 의도 정렬, ecosystem research, 리팩토링 감사 스킬 모음
Plugin teo-stack from marketplace teo-marketplace in developer-1px/teo-claude-code. Commands read from the repo's manifest — 22 days ago.
app-owned-boundary-refactor프런트엔드 코드의 책임 종류와 배치 위치를 서로 다른 축으로 판별한다. app-owned와 reusable 배치, Page-local/global 승격, route/page/widget 위치, 명목상 FSD layer 제거를 검토할 때 사용한다.
canonical-module-auditAudit or refactor duplicate responsibilities, consumer-local bypasses, and missing capabilities toward one canonical owner. Use for 정본 모듈 감사 or 같은 역할·같은 책임·같은 모듈; ordinary textual duplication alone is not an ownership audit.
cohesionFind code that changes for the same reason and propose or implement cohesive module boundaries. Use for $cohesion, 응집도, or requests to group related responsibilities; file size or similar names alone are not sufficient.
conflictUse an Evaporating Cloud to examine a real dilemma: identify shared goals, competing needs, actions, and assumptions that might permit a better alternative. Use for $conflict, /conflict, or apparently incompatible choices; a routine comparison alone does not require this workflow.
content-first-ui기존 디자인 시스템으로 UI를 만들거나 정보구조·배치를 개선할 때 콘텐츠와 도메인 이해, 어포던스·아이콘 검토, 결정트리를 통한 기존 컴포넌트 매핑, 그룹핑과 배치, 최소 정보성 문구, 섹션 재배치 순서로 설계한다. 화면 빌더와 React·HTML·A2UI 생성에 적용하며, 단순 번역·오탈자·기능 버그 수정을 전체 재설계로 확대하지 않는다.
design-product-story-parity디자인 정본, 제품 UI, Story Page의 상태·TSX·CSS·동작을 일치시키고 fixture 경계를 판별한다. Story Page 구현·리팩토링, 디자인 import, pixel matching, Story 전용 TSX·designCase·fixture store smell, 디자인에는 있지만 제품 로직으로 도달할 수 없는 UI 상태를 다룰 때 사용한다.
discussReconstruct latent intent and converge decisions through sequential causal reasoning before execution. Use for /discuss, $discuss, ambiguous goals, why-before-how conversations, or when the user wants to understand a problem before changing anything. Investigate available context before asking, surf
doubtQuestion whether concepts, code, or procedures are necessary and simplify them when requested. Use for $doubt, /doubt, 이거 다 필요해?, 불필요한 거 정리, or a focused complexity review.
driveCarry an agreed software objective through bounded, sequential work units using the existing implementation and PR workflows. Use for $drive, 1시간 알아서, 다음 슬라이스까지, 하나씩 완성해, or scoped continuous execution. Not for a single routine implementation, a PR-only merge queue, strategy discussion alone, or clo
entity-interface-refactor프런트엔드의 UI event와 product command를 인과관계로 구분하고 Feature·Entity·Widget의 capability 경계를 판별한다. FSD 경계, command 소유권, Entity·Widget callback·dispatch·store 누출을 검토할 때 사용한다.
layer-abstraction-refactor이름뿐인 중간 계층과 실제 추상화 벽을 구분한다. REST·runtime·host operation 분류, 정본 client 교체, facade·provider·port·entrypoint 존속 여부, layer skipping을 판단할 때 사용한다.
mainReturn a repository to its current main or configured base branch and clean up proven merged or redundant local work. Use for $main, /main, or an explicit return-to-main request.
mergeAssess or prepare existing PRs for landing, resolve in-scope CI, review, and conflict blockers, and merge when authorized. Use for $merge, merge 가능?, merge 준비, CI 대응 후 merge, or a scoped PR merge queue. Not for ordinary local branch integration or new implementation.
namingReview or improve names in code, APIs, files, UI, and domain models using semantic and usage evidence. Use for $naming, naming review, 이름 변경, ambiguous names, or vocabulary consistency.
ocp새 타입이나 variant를 추가할 때 같은 책임의 분기가 여러 소비자에서 함께 바뀌는지 점검하고 확장 지점을 정리한다. /ocp, 개방 폐쇄, 흩어진 분기 리팩터링에 사용한다. switch나 registry가 있다는 사실만으로 적용하지 않는다.
researchResearch external standards, practices, adoption, and experiments to explain ecosystem direction or compare a local option with relevant peers. Use for $research, /reference, ecosystem research, or an evidence-backed external comparison.
resolve-lintReduce lint, static-analysis, guard, warning, and code-smell findings without optimizing mechanically for a clean count. Use when the user asks to resolve, fix, clean up, reduce, or make progress on lint findings (including "lint 해결", "lint 고쳐", "warning 정리", "가드 위반 수정", or threshold smells such as
responsibility-surface-refactor실제 외부 public surface를 보존하는 내부 책임 분리와 app-internal facade 제거를 구분한다. package index·facade를 유지한 리팩터링이나 public API 호환성 판단에 사용하며 내부 re-export 경로 보존에는 사용하지 않는다.
resume-workRecover an interrupted software task by reconciling its agreed intent with current repository, worktree, issue, and PR state. Use for $resume-work, 뭐 하던 거야?, 어디까지 했지?, 세션이 끊겼어, 현황 파악 후 재개, or continuing interrupted work. A status request stays read-only; ordinary progress reporting without lost cont
same-lensAudit every applicable occurrence of a known defect mechanism, reconcile coverage, and prepare issue packets and recurrence-prevention candidates. Use for $same-lens or 같은 렌즈로 전수 조사. The audit itself does not modify files or register issues.
show-meOpen and verify frontend work from the current repository or worktree. Use for `$show-me`, “보여줘”, “확인할게”, “띄워줘”, “URL 줘”, “어디서 봐?”, before opening a local app for visual verification, or when handing off frontend work. Discover and use the repository's own preview contract, prove URL ownership, walk
srp파일의 단일 책임과 분리 후 locality를 점검하고 필요한 리팩터링을 수행한다. /srp, 책임 분리, 파일 분할 요청에 사용한다. 숫자는 import/export-from을 제외한 후보 LOC 하한이며 목표 파일 크기가 아니다.
teo-devTake an agreed software change through issue setup, implementation, verification, commit, push, and PR after an explicit execution handoff such as 진행해 or 이슈 따고 진행. Excludes provisional discussion, read-only status, existing-PR landing follow-ups handled by merge, and a different workflow chosen by t
[ARCHIVED] interactive-os 전용 파이프라인 스킬. 설치 대상이 아닌 참고 자료
24 skills · 4 agents
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Claude Skills for Obsidian
6 skills
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.