Hands-on prompt engineering and LLM evaluation. Built around a diagnose-then-ship loop: forensic transcript critique ▎ that names the exact failure mode, paired with a fixer that produces complete, deployment-ready rewrites — not ▎ vague advice.
I have spent more than 25 years in programming and web development, with a strong focus on performance, security, and writing lean code that does not waste resources. Good code should be clear, fast, safe, and practical to maintain. That same mindset is what I bring to this skill.
I work daily with Windows infrastructure — Active Directory, GPO, hybrid identity with Entra ID, endpoint hardening (TPM, BitLocker, WDAC), and migration planning for SMB environments. I've built this agent around the same diagnostic workflow I use on real environments: form hypotheses first, ask precise questions, and only prescribe after understanding the actual root cause. No checklists. No generic advice.
Structured audit of resume, LinkedIn profile and interview readiness. Career Readiness Score 0-100 across 5 areas, main Career Blockers, a rewritten draft of your weakest resume sections, and 10 prioritized fixes. Based on the assets you provide — does not guarantee interviews or offers (full disclaimer in the report).
Catches cascade failures that partial checks miss — pre-check names the risk before editing, post-check demands evidence values after, then auto-repairs in a loop while rereading the entire file every cycle until zero errors remain.
编程专家.Skill P8级编程助手,覆盖：软件/网站项目总控、API设计、Bug诊断、代码生成、代码审查、重构、测试用例、性能基准、技术选型、文档生成、任务拆解、Spec驱动、Karpathy规范、CMS二次开发、前端设计、MySQL、项目知识图谱。支持 @标识 显式调用跳过路由。
Audit and manage local AI Skills across Codex, Claude Code, and project workspaces. See what is actually active, detect duplicates and variants, compare changes over time, and generate an offline interactive management map. Read-only by default; every real change requires your approval.
다음 기술면접에서 '아는 건데 정리해서 말하지 못한 것'을 없애는 것이 이 스킬의 목표입니다. CS 기초 80·프론트엔드 40·백엔드/시스템설계 40·AI/LLM 엔지니어링 30·행동면접 40, 총 230문항 전부에 면접관의 출제 의도와 답변 뼈대 3줄이 붙어 있고, 역질문 30개(합계 260)와 PREP·STAR·모르는 질문 3단 방어 등 답변 프레임워크 10종이 포함됩니다. Claude가 직군·경력·목표 회사를 물은 뒤 질문→내 답변→출제 의도 기반 피드백→모범 답변 순으로 실전 모의면접을 진행하고, 약한 카테고리는 변형 질문으로 반복 훈련합니다. 이력서를 붙여넣으면 프로젝트별 예상 질문과 '찔리면 아픈 질문'까지 뽑아 줍니다. 특정 회사 기출 모음이 아닌 일반 기술면접 대비용 콘텐츠이며, 합격을 보장하는 자료가 아니라 준비 과정을 구조화하는 도구입니다.