NomaDamas

KOPIS 공연예술통합전산망 Open API를 k-skill-proxy 경유로 조회해 공연 목록·상세와 공연시설 정보를 찾는다. 조회 전용.

공공데이터포털 WHOIS 도메인/IP 정보 API를 k-skill-proxy 경유로 호출해 .kr/.한국 도메인, IP 주소, AS 번호의 공개 등록정보를 조회한다. 조회 전용.

열린국회정보 Open API를 k-skill-proxy 경유로 호출해 의안 검색·상세와 국회의원 본회의 표결정보를 조회한다. 조회 전용.

Browse 대법원경매정보(courtauction.go.kr) 부동산 매각공고 by 매각기일·법원·기일/기간 입찰, expand each notice into 사건번호·용도·주소·감정평가액·최저매각가, search property items by free conditions(지역·용도·가격·면적·유찰횟수), and look up a case directly by 법원+사건번호. Read-only, slow-by-design (~2s/call) to avoid IP blocks.

법원 전자소송 지급명령 신청을 위해 채권자·채무자·청구금액·청구원인·증빙 정보를 인터뷰하고, 신청서 초안과 공식 전자소송 브라우저 입력 handoff를 준비한다.

국방전자조달시스템(D2B) 공개 입찰공고 검색 화면에서 공고건명·공고구분·공고/개찰일·G2B공고번호·발주기관 조건으로 공고를 조회한다.

당근부동산(realty.daangn.com) 공개 웹 데이터로 지역 기반 부동산 매물 검색과 상세 확인을 수행한다. 문의/예약/계약 자동화는 제외한다.

인터넷등기소(IROS)에서 법인/부동산 등기부등본(등기사항증명서) 발급을 준비하고, 사용자가 직접 로그인·결제한 브라우저 흐름 안에서 장바구니·열람·저장을 안전하게 보조한다.

Guide developers through creating a custom generation pipeline plugin for AutoRAG-Research. Walks through scaffolding, implementing BaseGenerationPipeline methods, composing with retrieval pipelines, writing YAML configs, testing, and installing. Use when building a new RAG generation strategy (e.g., chain-of-thought RAG, multi-hop RAG).

Guide developers through creating a custom data ingestor plugin for AutoRAG-Research. Ingestors load external datasets (HuggingFace, local files, APIs) into the database. Uses @register_ingestor decorator for automatic CLI parameter extraction. Use when ingesting a new dataset format into AutoRAG-Research.

Guide developers through creating a custom retrieval pipeline plugin for AutoRAG-Research. Walks through scaffolding, implementing BaseRetrievalPipeline methods, writing YAML configs, testing, and installing. Use when building a new search/retrieval strategy (e.g., Elasticsearch, ColBERT, custom vector search).

Guide developers through creating a custom evaluation metric plugin for AutoRAG-Research. Covers both retrieval metrics (recall, precision, etc.) and generation metrics (BLEU, ROUGE, etc.). Walks through scaffolding, implementing metric functions with @metric decorators, writing configs, testing, and installing. Use when building a new evaluation metric.

Query AutoRAG-Research pipeline results using natural language. Converts questions to SQL, executes safely (SELECT-only), returns formatted results. Auto-detects DB connection from configs/db.yaml or env vars. Use for pipeline comparison, metrics analysis, token usage.

Process [APPROVE] and [IGNORE] replies on /refactor review threads. Applies approved fixes to the codebase, resolves all responded threads on GitHub, commits and pushes changes. Sequential single-agent workflow. All output is in English.

Orchestrate a 3-agent PR code review debate using Claude Code Teams. Spawns Devil's Advocate, Neutral Judge, and Approval Advocate reviewers who analyze the current PR diff in parallel. Synthesizes findings, auto-fixes unanimous issues, and posts inline PR comments for disagreements. All output is in English.

Stage 2 design skill usable in Codex and Claude Code. Generate and iterate slide-XX.html files in the selected slides workspace.

Stage 3 conversion skill usable in Codex and Claude Code. Convert approved HTML slides to PDF or per-slide PNG reliably, and to experimental / unstable PPTX/Figma outputs on a best-effort basis.

Stage 1 planning skill usable in Codex and Claude Code. Build and iterate slide-outline.md until explicit user approval.

End-to-end presentation workflow usable in Codex and Claude Code. Use when making a full presentation from scratch — planning, designing slides, editing, and exporting. PDF and per-slide PNG are preferred; PPTX/Figma export is experimental / unstable.

Generate square Instagram-style card news by reusing the slides-grab workflow with card-news mode enabled. Defaults to per-slide PNG export.

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

Use this skill when building or tuning the terminal-only romance simulation, persona files, live chat UX, or ECC trace instrumentation in this repository.

Use this skill when working on BetterThanYou battle flows, shared scoring, the CLI HUD, Homebrew packaging, or the optional web helper. Keep the CLI as the primary product surface and keep scoring logic in packages/core.

Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

Use BananaTape CLI to create, launch, inspect, and clean up local AI image editing projects from an agent.

Use this skill whenever the user asks to generate, create, render, draw, or make an image, picture, illustration, icon, logo, or any other visual asset. Also use it when the user wants to edit, modify, restyle, or combine existing images (provide them as inputs). The skill drives the `gti` CLI, which uses the user's local Codex ChatGPT authentication to call the private image-generation backend. Trigger phrases include "generate an image", "create a picture", "make an image of", "draw me a", "render this", "make this cat wear a hat", and similar. Prefer this skill over describing images in text.

Search local KakaoTalk keyword, BM25, and EmbeddingGemma vector indexes through the katok CLI.

Use MinSync to add git-free incremental semantic indexing and query to a local workspace.

Use Jikji find to locate local files, folders, metadata, and parsed document text through a non-destructive prebuilt agent map/search index while saving repeated LLM calls, tokens, and time.

Start or reuse the Cat-In-Lattice tmux sidecar in a bottom pane. Use when the user explicitly asks for $cat-in-lattice, wants the cat companion opened below the current pane, or wants to send a notice through the installed local launcher.