dotfiles

현재 세션에서 한 작업(또는 주어진 텍스트·파일)을 비전문가·미래의 자신도 이해하도록 쉽게 풀어 설명하는 인터랙티브 HTML 페이지 생성. 목차·단계별 펼침접힘·핵심요약·용어풀이 포함. ~/Desktop 저장 후 자동 오픈. 트리거: "쉽게 설명", "정리해줘", "복기", "풀어서 설명", "이해하기 쉽게", "설명해줘", "요약해줘".

Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for Opus 4.7 (with adaptive thinking) inside the chat app — Codex.ai, the Mac app, the iOS app — NOT the API. Use this skill whenever the user wants to write, rewrite, optimize, improve, sharpen, or polish a prompt for the chat app. Trigger phrases include "rewrite this prompt", "make this a better prompt", "optimize this prompt", "turn this into a prompt", "help me prompt this", "draft a prompt that...", "I want to ask...", or whenever the user pastes a draft prompt and asks for improvements. Also trigger when the user describes a task they plan to send into the chat app and clearly wants a reusable, well-structured prompt rather than a direct answer. The output is always a single, copy-pasteable prompt in a code block that the user sends as-is — never a template with placeholders. Always ends with the exact line "Think before answering (maximum reasoning)".

Use this when you need to EVALUATE OR IMPROVE or OPTIMIZE an existing LLM agent's output quality - including improving tool selection accuracy, answer quality, reducing costs, or fixing issues where the agent gives wrong/incomplete responses. Evaluates agents systematically using MLflow evaluation with datasets, scorers, and tracing. IMPORTANT - Always also load the instrumenting-with-mlflow-tracing skill before starting any work. Covers end-to-end evaluation workflow or individual components (tracing setup, dataset creation, scorer definition, evaluation execution).

Codex 세션 탐색 및 분석. agf 데이터 소스(history.jsonl)를 활용한 세션 리스트 조회, 검색 및 상세 분석. "세션 목록", "session list", "세션 검색", "session search", "agf" 등의 요청 시 자동 적용.

Analyzes an MLflow session — a sequence of traces from a multi-turn chat conversation or interaction. Use when the user asks to debug a chat conversation, review session or chat history, find where a multi-turn chat went wrong, or analyze patterns across turns. Triggers on "analyze this session", "what happened in this conversation", "debug session", "review chat history", "where did this chat go wrong", "session traces", "analyze chat", "debug this chat".

Analyzes a single MLflow trace to answer a user query about it. Use when the user provides a trace ID and asks to debug, investigate, find issues, root-cause errors, understand behavior, or analyze quality. Triggers on "analyze this trace", "what went wrong with this trace", "debug trace", "investigate trace", "why did this trace fail", "root cause this trace".

Create professional, dark-themed architecture diagrams as standalone HTML files with SVG graphics. Use when the user asks for system architecture diagrams, infrastructure diagrams, cloud architecture visualizations, security diagrams, network topology diagrams, or any technical diagram showing system components and their relationships.

브런치 블로그 글 작성을 도와주는 Skill. 사용자가 초안 파일(.md)을 @멘션하면서 "브런치", "글 작성", "블로그 글" 등을 언급하면 활성화. vault-intelligence 시스템으로 관련 자료를 검색하고, 구조 제안, 스타일 체크 등을 수행. 단, Codex가 직접 글을 쓰지 않고 사용자의 글쓰기를 보조하는 역할.

현재 세션의 조사/분석/연구/평가 결과를 Obsidian vault ($VAULT_ROOT/001-INBOX/)에 한국어 마크다운 문서로 저장. frontmatter 자동 생성, vis hybrid search로 Related Notes 자동 추가. 외부 URL/YouTube 요약은 범위 밖.

Multi-project tmux orchestration for Codex. Sets up tmux session/window with CC instances per project, then dispatches prompts. Use when (a) the user says "cc-orchestra" or asks to orchestrate multiple projects, OR (b) the user mentions another project name as a dispatch target (e.g. "pacman에서 X 해줘", "thomas와 bo에 Y 적용", "<proj>에서 ..."), OR (c) the assistant determines that work belongs to a sibling project (file paths under another repo, plan document assigns the task there, build /test ownership lies elsewhere) while running as the main pane of an active task. Skip when the user says "여기서 / 이 파일 / 현재 프로젝트" or the work is clearly within the current pane's project.

@claudecodelog X 계정의 릴리스 노트를 수집하여 Obsidian 문서로 정리. 매일 morning-auto.sh에서 자동 호출되거나, 수동으로 /Codex-release-tracker 실행. --backfill 인자 시 3개월 소급 처리.

This skill should be used when the user asks to "CRAP 분석", "crap4java 실행", "메서드 복잡도 분석", "코드 품질 게이트 확인", "CRAP score 확인", "변경된 파일 CRAP 분석", "cyclomatic complexity + coverage 분석", "crap 점수가 8 이상인 메서드 찾아줘", or mentions CRAP metric, JaCoCo coverage + complexity 조합 분석. Java Maven 프로젝트의 메서드별 CRAP(Change Risk Anti-Patterns) 점수를 측정하여 리팩터링 우선순위를 제시.

매일 아침 업무 시작 전 어제 작업 내역을 정리하여 Daily Note에 반영. 서브 에이전트 기반 병렬 처리로 메인 컨텍스트 절약. "어제 작업 정리해줘", "daily log", "업무 내역 정리" 등의 요청 시 자동 적용.

Use Databricks built-in AI Functions (ai_classify, ai_extract, ai_summarize, ai_mask, ai_translate, ai_fix_grammar, ai_gen, ai_analyze_sentiment, ai_similarity, ai_parse_document, ai_query, ai_forecast) to add AI capabilities directly to SQL and PySpark pipelines without managing model endpoints. Also covers document parsing and building custom RAG pipelines (parse → chunk → index → query).

Quick reference for building full-stack Databricks Apps with apx (React + FastAPI). Use when working on apx projects, creating routes, adding components, or managing dev servers.

Builds Python-based Databricks applications using Dash, Streamlit, Gradio, Flask, FastAPI, or Reflex. Handles OAuth authorization (app and user auth), app resources, SQL warehouse and Lakebase connectivity, model serving integration, foundation model APIs, LLM integration, and deployment. Use when building Python web apps, dashboards, ML demos, or REST APIs for Databricks, or when the user mentions Streamlit, Dash, Gradio, Flask, FastAPI, Reflex, or Databricks app.

Create and configure Declarative Automation Bundles (formerly Asset Bundles) with best practices for multi-environment deployments (CICD). Use when working with: (1) Creating new DAB projects, (2) Adding resources (dashboards, pipelines, jobs, alerts), (3) Configuring multi-environment deployments, (4) Setting up permissions, (5) Deploying or running bundle resources

Apache Iceberg tables on Databricks — Managed Iceberg tables, External Iceberg Reads (fka Uniform), Compatibility Mode, Iceberg REST Catalog (IRC), Iceberg v3, Snowflake interop, PyIceberg, OSS Spark, external engine access and credential vending. Use when creating Iceberg tables, enabling External Iceberg Reads (uniform) on Delta tables (including Streaming Tables and Materialized Views via compatibility mode), configuring external engines to read Databricks tables via Unity Catalog IRC, integrating with Snowflake catalog to read Foreign Iceberg tables

Patterns and best practices for Lakebase Autoscaling (next-gen managed PostgreSQL). Use when creating or managing Lakebase Autoscaling projects, configuring autoscaling compute or scale-to-zero, working with database branching for dev/test workflows, implementing reverse ETL via synced tables, or connecting applications to Lakebase with OAuth credentials.

Patterns and best practices for Lakebase Provisioned (Databricks managed PostgreSQL) for OLTP workloads. Use when creating Lakebase instances, connecting applications or Databricks Apps to PostgreSQL, implementing reverse ETL via synced tables, storing agent or chat memory, or configuring OAuth authentication for Lakebase.

MLflow 3 GenAI agent evaluation. Use when writing mlflow.genai.evaluate() code, creating @scorer functions, using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), building eval datasets from traces, setting up trace ingestion and production monitoring, aligning judges with MemAlign from domain expert feedback, or running optimize_prompts() with GEPA for automated prompt improvement.

Deploy and query Databricks Model Serving endpoints. Use when (1) deploying MLflow models or AI agents to endpoints, (2) creating ChatAgent/ResponsesAgent agents, (3) integrating UC Functions or Vector Search tools, (4) querying deployed endpoints, (5) checking endpoint status. Covers classical ML models, custom pyfunc, and GenAI agents.

Databricks development guidance including Python SDK, Databricks Connect, CLI, and REST API. Use when working with databricks-sdk, databricks-connect, or Databricks APIs.

Creates, configures, and updates Databricks Lakeflow Spark Declarative Pipelines (SDP/LDP) using serverless compute. Handles data ingestion with streaming tables, materialized views, CDC, SCD Type 2, and Auto Loader ingestion patterns. Use when building data pipelines, working with Delta Live Tables, ingesting streaming data, implementing change data capture, or when the user mentions SDP, LDP, DLT, Lakeflow pipelines, streaming tables, or bronze/silver/gold medallion architectures.

Comprehensive guide to Spark Structured Streaming for production workloads. Use when building streaming pipelines, working with Kafka ingestion, implementing Real-Time Mode (RTM), configuring triggers (processingTime, availableNow), handling stateful operations with watermarks, optimizing checkpoints, performing stream-stream or stream-static joins, writing to multiple sinks, or tuning streaming cost and performance.

Generate realistic synthetic data using Spark + Faker (strongly recommended). Supports serverless execution, multiple output formats (Parquet/JSON/CSV/Delta), and scales from thousands to millions of rows. For small datasets (<10K rows), can optionally generate locally and upload to volumes. Use when user mentions 'synthetic data', 'test data', 'generate data', 'demo dataset', 'Faker', or 'sample data'.

Unity Catalog system tables and volumes. Use when querying system tables (audit, lineage, billing) or working with volume file operations (upload, download, list files in /Volumes/).

Build Zerobus Ingest clients for near real-time data ingestion into Databricks Delta tables via gRPC. Use when creating producers that write directly to Unity Catalog tables without a message bus, working with the Zerobus Ingest SDK in Python/Java/Go/TypeScript/Rust, generating Protobuf schemas from UC tables, or implementing stream-based ingestion with ACK handling and retry logic.

This skill should be used when the user asks to find duplicate Java code, check DRY violations, "중복 코드 찾아줘", "dry4java 실행", "구조적으로 유사한 코드 찾아줘", "중복 선언 분석", "코드 중복도 확인", "copy-paste 패턴 찾기", or mentions structural similarity, Jaccard similarity, DRY (Don't Repeat Yourself) in Java codebase context. Java 소스 코드의 구조적 유사도를 AST 기반으로 측정하여 중복 선언 후보를 찾고 리팩터링 방향을 제시.

서버 로그(ActionRunner/p6spy)에서 SQL 추출, 포맷팅, 마스킹 분석. 사용자가 Spring Boot 서버 로그를 붙여넣고 "SQL 뽑아줘", "SQL 정리해줘", "로그에서 쿼리 추출", "마스킹 확인", "어떤 SQL이 실행됐는지 분석" 등을 요청할 때 반드시 이 스킬 사용. actionSet JSON, query(xxx) 포맷 SQL, p6spy 로그가 섞인 텍스트도 처리 가능.

자연어로 이전 Codex 세션을 검색하고 요약하는 스킬. agf 키워드 검색과 qmd 의미 검색을 병행하여 정확도를 높이고, git 커밋 조사와 AI 요약까지 제공한다. "세션 찾아줘", "지난번 작업 찾기", "이전에 했던 ~~ 세션", "~~ 작업한 세션 보여줘", "세션 검색", "작업 이력", "resume session", "이전 대화 찾기", "그때 세션", "그 세션" 등의 요청 시 반드시 이 스킬을 사용할 것. /agf나 qmd-search를 직접 호출하기 전에 이 스킬을 먼저 고려할 것.

This skill should be used when working with GitHub CLI (gh) for pull requests, issues, releases, and GitHub automation. Use when users mention gh commands, GitHub workflows, PR operations, issue management, or GitHub API access. Essential for understanding gh's mental model, command structure, and integration with git workflows.

any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report

Codex의 응답(브레인스토밍·분석·계획·결정사항 등)을 인터랙티브 HTML 리뷰 페이지로 변환. 각 항목에 👍채택/🤔의문/🔁수정/❌거절 버튼, 코멘트, LocalStorage 자동저장, Markdown·프롬프트 export 기능 포함. ~/Desktop에 저장 후 브라우저로 자동 열림.

AI(ChatGPT·Codex·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬. 번역투·영어 인용 과다·기계적 병렬·관용구·피동태 남용·접속사 남발·리듬 균일성·이모지/불릿 과다 등 10대 카테고리 40+ AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 자연스러운 한국어로 재작성한다. 5인 파이프라인(분류학자→탐지기→윤문가→내용 감사관·자연스러움 리뷰어 병렬)으로 구동하며 웹 서비스 확장도 지원. 트리거 — "AI 티 없애줘", "AI 같은 글 자연스럽게", "GPT/ChatGPT 문체", "AI 번역투 고쳐", "사람이 쓴 것처럼 윤문", "AI 윤문", "ChatGPT 티 제거", "한글 AI 탐지·윤문", "AI 글 사람처럼", "번역투 제거", "영어 인용 많은 글 윤문", "AI 글 티 안 나게", "휴머나이저", "humanize Korean", "AI detector bypass 한글". 후속 작업 — "특정 카테고리만 다시", "윤문 강도 조정", "장르 바꿔서", "이 문단만", "2차 윤문", "웹 서비스로 만들어줘", "API로 배포", "내용은 그대로 두고 톤만" 도 모두 이 스킬. 단순 맞춤법·오탈자 교정은 직접 처리, 번역은 번역 스킬, 내용 추가·삭제를 동반한 재작성은 별도 집필 스킬.

Instruments Python and TypeScript code with MLflow Tracing for observability. Must be loaded when setting up tracing as part of any workflow including agent evaluation. Triggers on adding tracing, instrumenting agents/LLM apps, getting started with MLflow tracing, tracing specific frameworks (LangGraph, LangChain, OpenAI, DSPy, CrewAI, AutoGen), or when another skill references tracing setup. Examples - "How do I add tracing?", "Instrument my agent", "Trace my LangChain app", "Set up tracing for evaluation"

Use when working with Java codebase — navigation, refactoring, cross-project search. Java 프로젝트(특히 5개 규모 multi-project) 작업 시 토큰·속도 절약을 위해 구조 도구 우선 사용. 단일 프로젝트는 Serena (mcp__serena__*) — find_symbol, find_referencing_symbols, rename_symbol 등. 다수 프로젝트 동시 검색은 sg --lang java -p '<pattern>'. Triggers on: "Java 작업", "Java refactor", "Java 클래스 검색", "find_symbol", "find_referencing_symbols", "rename in Java", "Java 다중 프로젝트", "Java multi-project", "Spring Boot navigation", "Java 호출 그래프", "incomingCalls", "outgoingCalls".

Onboards users to MLflow by determining their use case (GenAI agents/apps or traditional ML/deep learning) and guiding them through relevant quickstart tutorials and initial integration. If an experiment ID is available, it should be supplied as input to help determine the use case. Use when the user asks to get started with MLflow, set up tracking, add observability, or integrate MLflow into their project. Triggers on "get started with MLflow", "set up MLflow", "onboard to MLflow", "add MLflow to my project", "how do I use MLflow".

Use when the user asks to run mutation testing on a Java file, check test quality by mutating code, find surviving mutants, kill mutants with tests, or says "뮤테이션 테스트", "mutate", "뮤턴트 잡기", "살아남은 뮤턴트", "테스트가 뮤턴트를 잡는지 확인", or wants to verify that tests actually catch bugs. Java Maven 프로젝트의 단일 `.java` 파일에 대해 mutation testing을 실행하는 도구.

Use when creating or updating an Obsidian markdown document (anywhere — vault dir or other projects). Adds Forward Related Notes section (top-5 hybrid search results) to the document after creation. Triggers on: "obsidian 문서 생성", "vault에 저장", "001-INBOX에 작성", "Obsidian markdown 작성", "Related Notes 추가", "vault 정리 후 백링크". Backward Related Notes는 별도 vis-backlink-trigger 스킬이 처리하므로 이 스킬은 Forward만 책임진다.