some-engineer-mind

Stops Claude from stacking guesses on top of unknowns. When uncertainty appears in code, configs, APIs, or error messages, this skill forces a brief pause to verify — by reading source, running a small check, or asking the user — instead of fabricating a plausible-sounding answer. 모르는 지점 위에 추측을 쌓아 코드를 만들지 않도록, 막혔을 때 *말하고 묻는* 길을 먼저 권하는 엔지니어링 철학 스킬.

Blocks speculative code, options, abstractions, and flags built for hypothetical future needs (YAGNI). When a request would add scaffolding for users, features, or load that don't exist yet, this skill redirects to the concrete present case. 오지 않은 미래 요구를 위해 미리 코드·옵션·추상화·플래그를 깔아두지 않게 막는 엔지니어링 철학 스킬.

Forces the WHY before the HOW when code is being written, edited, reviewed, refactored, or generated. Surfaces the intent behind a change in one sentence so the result is purposeful rather than merely working, and prefers not writing code at all when intent stays unclear. 코드를 작성·수정·리뷰·생성·리팩터할 때 '동작하느냐'보다 '왜 만드는가(의도)'를 먼저 짚게 만드는 엔지니어링 철학 스킬.

Enforces minimal-code-for-same-output discipline. Before letting new functions, files, modules, abstractions, or dependencies grow the codebase, this skill checks whether the same outcome can be achieved by extending what already exists, and gives a line-count estimate up front. 코드를 작성·확장·리팩터·생성·추가할 때 최소한의 코드량으로 같은 결과를 내도록 강제하는 엔지니어링 철학 스킬.

Leaves the WHY beside non-obvious decisions — in commit messages, PR descriptions, and short comments next to surprising code. Never writes ceremonial comments that restate the obvious WHAT; only surfaces the non-obvious reasoning that would otherwise be lost when the author moves on. 코드를 짠 사람의 머릿속에만 있는 *왜*를 코드 옆에 한 줄로 남기는 엔지니어링 철학 스킬.

Treats failure as a precondition for risky work. Before deploys, data deletions, migrations, force pushes, dependency upgrades, or other hard-to-undo actions, this skill builds the retreat path first — dry-run, backup, staged rollout, explicit rollback procedure written down — so the user can enter the action with composure. 실패할 가능성이 있는 작업에 들어가기 전에 되돌아올 길을 먼저 마련하는 엔지니어링 철학 스킬.

Surveys what already exists before writing new code, and refuses to delete code whose purpose is unknown. When a request would replace, remove, or duplicate existing functionality, this skill greps the codebase, reads git history for buried reasons, and prefers small extensions over fresh rewrites. 새 코드를 짓기 전에 코드베이스 안에 이미 있는 것을 먼저 살피고, 모르는 코드를 함부로 치우지 않게 만드는 엔지니어링 철학 스킬.

Forces reproduction before any fix. When something doesn't work, this skill stops the symptom→guess→patch loop and first reproduces the bug locally on the same branch, data, and inputs the user saw — because an unreproduced bug is an unsolved one. 버그·이상 동작 앞에서 추측 패치의 유혹을 끊고, 먼저 눈앞에 똑같이 재현하게 만드는 엔지니어링 철학 스킬.

Translates between engineering and non-engineering vocabularies. When a vague sensory request comes from a PM, designer, ops team, client, or non-developer stakeholder, this skill converts it into precise intent through a short clarifying exchange; when reporting results back, it strips library/function names and speaks in outcomes the requester actually cares about. 실무자·기획자·디자이너·비개발자 요청자와 주고받을 때 개발 용어를 걷어내고 일상어로 묻고 답하는 엔지니어링 철학 스킬.

Surveys established design patterns, framework conventions, and idioms before designing anything from scratch. When the user is about to structure a new module, service, or feature, this skill names the underlying problem type (state management, caching, async handling, etc.) and points to the canonical solution before falling back to bespoke construction. 무언가를 새로 설계·구현·구조화하기 전에 이미 정립된 디자인 패턴이 있는지 먼저 살피는 엔지니어링 철학 스킬.

Small grooming each time code is finished, named, reviewed, or committed — removing unused imports, variables, and dead code; tightening identifier names to expose intent; and leaving the file one notch cleaner than it was found. Never expands into unrelated refactors that bloat the PR. 코드를 작성·수정·리뷰·커밋·완료할 때마다 작은 정돈을 습관화하는 엔지니어링 철학 스킬.