dots

Creates ast-grep patterns for structural code search. Use when finding functions/classes by structure, refactoring code, or when grep returns too many false positives.

Builds Claude Agent SDK agents in Python. Use when creating custom tools, hooks, sub-agents, or MCP integrations with the Agent SDK. Python 에이전트 구축 시 사용.

Graph-based code review with Tree-sitter knowledge graph. Use when reviewing code changes, PRs, or exploring blast radius of modifications in projects with code-review-graph installed (.code-review-graph/ exists). Also use for initial setup of code-review-graph in a new project. Do NOT use for checklist-based reviews without graph (use code-review instead), or for security-focused reviews (use security instead).

Code review hub. 타입 안전성 (TypeScript, Python), lint 감사, 죽은 코드, 테스트 품질 리뷰 (smell, overfitting, 커버리지, 통합/E2E), Terraform/IaC 안전성 (lifecycle, state, credentials). 병렬 에이전트 모드로 다각적 분석 지원. 코드 리뷰, 타입 체크, lint, 테스트 리뷰, terraform, IaC.

데이터 조사/분석 파이프라인 생성. 데이터 수집 -> Python 분석/차트(matplotlib) -> HTML 리포트. Use when 데이터 분석, 조사, investigation, 이상 탐지, 패턴 분석, 리포트 생성, 차트 시각화, 데이터 수집 파이프라인 구축. Also use when 데이터를 모아서 분석하고 보고서를 만드는 작업. Do NOT use for 단순 DB 조회 (use gandy), 단순 차트 하나 (use diagram).

코드 작업 완료 후 변경 내러티브 문서 생성. 변경 요약, 설계 판단 근거, 학습 포인트를 vault에 기록. Vault 위치/매핑은 `documentation` skill, 형식은 `obsidian-write` 참조. Use when completing code work, after PR creation, reviewing what was done, or wanting to document changes for learning. /debrief, 작업 정리, 변경 기록, 회고.

Audits visual design for AI-generated aesthetic patterns and produces improvement plans. Use when reviewing UI design, checking if a website looks "AI-generated", auditing .pen files for generic aesthetics, or improving visual identity. Also use when "AI purple", "looks generic", "soulless design", "design review", "AI스러운", "디자인 점검", "디자인 감사", or "escape AI aesthetic". Do NOT use for code review (use code-review) or accessibility audit.

견적 산정 + 점진적 설계 합의 (견적→범위→구조→상호작용→계약→구현). Use when 견적내자, 견적 내줘, estimate effort, scope is unclear for multi-component work, new feature domain with undefined boundaries, or system integration requiring architectural decisions. 견적, 설계 먼저, 구조 설계, 범위 정의. Do NOT use for single-component changes where scope is already clear, or when a plan already exists (use plan-review instead).

DevOps hub. Local CI (Justfile, lint, test, pre-commit hooks), GitLab CI pipelines, Docker (Dockerfile, compose.yaml, multi-stage builds), GitHub Actions (workflows, custom actions, reusable workflows, release, security). CI/CD 파이프라인, 도커, GitHub Actions.

개인 지식 vault(Obsidian) 위치와 "어떤 작업을 어디에 기록하는가"의 단일 진실 소스. 다른 스킬(recall, debrief, intake, paper, standup, wakeup, vis-graph 등)이 vault 경로/매핑을 hardcoding하지 않도록 이 스킬을 참조한다. 형식 규약(frontmatter, checkbox, 링크, namespace 폴더화)은 obsidian-write 참조. Use when 다른 스킬에서 vault 위치 또는 namespace 매핑을 결정해야 할 때, 또는 vault 구조 자체를 점검·변경할 때.

RSS/Atom 피드를 수집하고 프로젝트 dependency와 대조하여 관련 보안/기술 뉴스를 리포팅. Use when checking security advisories, supply chain news, CVE alerts, or technology updates relevant to current project. /feed (전체), /feed security, /feed backend, /feed frontend. Do NOT use for general web search (use WebSearch instead).

Provides fzf command patterns and configurations. Use when writing fzf commands, interactive filters, or pipeline compositions.

DB 조회/분석 지원. gandy 쿼리, .gandy 설정, 데이터 수집/분석 워크플로우. Use when querying databases, writing gandy queries, setting up .gandy project config, collecting or analyzing DB data, exploring table structure, or any situation involving gandy, pj:db. Also use when user needs data from postgres or sqlite for investigation, reporting, or debugging. Do NOT use for SQL migration, schema design, or ORM framework setup (use devops instead).

Audits, improves, and tracks Claude Code agent harness (CLAUDE.md, rules, hooks, skills, agents, settings, memory, architecture, knowledge base). Use when reviewing harness quality, adding constraints/rules/hooks, designing agent teams/orchestration, optimizing agent performance, diagnosing agent misbehavior, setting up harness for a new repository, or managing documentation freshness. Do NOT use for creating new skills (use my-skill-creator) or basic Claude Code setup (use claude-guide).

Local markdown search engine CLI. Use when searching notes, querying documents, managing collections, indexing, embedding, or retrieving document content. Also use when ir search, ir update, ir embed, ir collection, ir status, ir daemon, ir get.

[DEPRECATED — use obsidian-write] Writes Logseq pages (legacy `key:: value` properties + `___` namespace). 본 vault는 2026-04-29 Obsidian으로 마이그레이션됨. 별도 logseq vault에 작업 시에만 사용.

신호(기사/관찰/아이디어/문제)를 글로벌 하네스(~/.claude/ 전체)로 흡수. 추출→대조→Gap→적용→흡수율 측정. Use when 외부 기사 참조, "이게 문제야", "이걸 개선하자", "이 패턴을 반영해", 하네스 메타 개선, 스킬 진화, 글로벌 룰 개선. Do NOT use for 프로젝트 레벨 하네스 (use harness-engineering).

Generates mise.toml project configuration. Use when setting up project tools, environment variables, or task automation with mise.

Creates and manages Claude Code skills. Use when creating new skills, updating existing skills, or converting repeated prompts into reusable skill packages.

Writes Obsidian pages (frontmatter, checkbox, folder-based namespace, wikilink) following conventions. Use when creating namespace pages (troubleshoot, decision, qa, spec, incident, issue), writing journal entries, promoting journal to pages, or editing existing pages. Vault 위치/namespace 매핑은 `documentation` skill 참조. Do NOT use for reading/searching (use ir directly).

Extracts text, tables, and structure from PDF files using opendataloader-pdf. Use when reading PDFs, converting PDF to markdown/JSON/HTML, extracting tables from PDF, processing scanned PDFs with OCR, or analyzing PDF content for RAG pipelines. Do NOT use for creating/editing PDFs, Word/Excel/PPT files (use xlsx2md for Excel), or viewing PDFs (use Read tool for simple PDF viewing).

Reviews execution plans for scope, codebase validity, risk, and completeness before implementation. Use when reviewing a plan, 계획 리뷰, 계획 검증, checking plan quality before execution, or "리뷰해줘" after plan mode. Includes TDD, BDD, DDD methodology domains.

Generates PowerPoint architecture diagrams with auto-layout and orthogonal routing using PPTXGenJS. Use when creating AWS architecture diagrams, infrastructure layouts, system design slides, IDC 구성도, or any diagram that needs boxes with right-angle connectors in .pptx format. Also use when 아키텍처 다이어그램, 인프라 구성도, PPT 생성, 구성도 만들기, 슬라이드 자동 생성. Do NOT use for simple text-only presentations (use PowerPoint directly), data charts (use data-investigation), or ASCII/Mermaid diagrams (use diagram skill).

소프트웨어 공학 원칙 바스켓. 원칙 카탈로그 열람, 코드/설계/프로세스/테스트의 원칙 준수도 평가, 위반 식별 및 개선 가이드. Use when 원칙 평가, 원칙 점검, 원칙 검증, principles check, 코드 품질 근본 진단, 설계 원칙 리뷰, 아키텍처 원칙 점검, 프로세스 원칙 점검, 테스트 원칙 점검, 테스트 설계, or when other review skills need a principled foundation. Do NOT use for specific code review (use code-review), security audit (use security), or strategic decisions (use strategic-thinking).

기능별 QA 체크리스트 생성, 수동 테스트 실행, 결과 기록. Use when QA 테스트, 체크리스트 만들기, 수동 검증, 기능 확인, qa 진행, checklist. Do NOT use for automated test code (use plan-review tdd / code-review instead) or BDD spec (use plan-review bdd instead).

Searches local markdown notes and documents using ir CLI. Use when searching notes, querying documents, managing collections, or retrieving document content.

Load context from Obsidian vault (journals, session pages) and JSONL session history. Vault 위치/구조는 `documentation` skill 참조. Temporal queries scan JSONL by date, topic queries use ir BM25. Use when "recall", "어제 뭐 했지", "what did we work on", "이전 작업", "session history".

기존 코드의 안전한 리팩토링. Characterization Test로 동작 보존하며 구조 개선

CLI command naming convention for Justfile and Makefile. Enforces GAT (group-action-target) word order, grouped listing, mandatory descriptions. Use when creating Justfile recipes, Makefile targets, or reviewing task runner configs for naming consistency. Also use when asking "what should I name this command?" for task runners. Do NOT use for npm scripts, mise tasks, or Claude Code skill naming.

AST parsing, S-expression queries, tag extraction via tree-sitter CLI. Use when parsing code into AST, extracting tags, visualizing syntax trees, or performing structural analysis beyond ast-grep.

파일 의존성 그래프(dep), DB 스키마 ERD(schema), Obsidian vault 지식 그래프(vault)를 vis-network 기반 인터랙티브 HTML로 시각화. Vault 위치는 `documentation` skill 참조. Use when visualizing dependency graphs, import structure, circular dependencies, database structure, table relationships, ERD, vault knowledge graph, or page interconnections.

Converts Excel (.xlsx) files to Markdown tables with merged cell handling. Use when reading xlsx files, converting spreadsheets to markdown, or analyzing Excel data. Do NOT use for CSV files (read them directly) or creating Excel files.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Guides Claude Code setup, configuration, and operations. Use when setting up CLAUDE.md, creating rules, configuring hooks, creating slash commands, installing external skills, reviewing configuration, organizing prompt architecture, optimizing delegation strategy, managing context window, or improving Claude Code workflows. Do NOT use for creating new skills (use my-skill-creator) or building Agent SDK agents (use claude-agent-sdk).

체계적 의사결정 프레임워크. First Principles, Trade-off 분석, Cognitive Bias 점검

복잡도에 따라 ASCII art 또는 Mermaid 다이어그램을 선택하여 생성. Use when visualizing architecture, drawing diagrams, explaining structure visually, or 도식화/다이어그램 요청 시. 중간 복잡도는 ASCII art 우선.

Performs small structural code cleanups (tidyings). Use when preparing code changes, removing dead code, reducing nesting, or cleaning up before feature work.

방향 수정 신호 감지 및 세션 전체 회고. Use when detecting course correction signals ("아니/잠깐/근데"), session retrospective, or reviewing overall progress. /reflect 또는 "회고해줘"로 수동 호출.