NomaDamas

GS Quant의 Instrument/Data 구조화 방식에서 영감을 받아 한국 채권을 표준 Bond Instrument 필드로 정리하고, 종목명·발행사·ISIN으로 발행조건·잔액·CALL/PUT·CB/EB/BW를 출처와 함께 검색·비교한다. Use for Korean bond lookup or comparison. Not for live quotes, YTM, credit opinions, or investment advice.

사업자등록번호 하나로 "이 사업자, 실제 문제 없나"를 확인한다 — 국세청 사업자등록 상태·국민연금 가입 사업장·국세 체납 명단·금융위 법인개요·조달청 부정당제재·지방행정 인허가 영업상태를 무료 공공 데이터로 교차 조회해 사실만 병렬하는 실사 리포트(점수·등급·위험 판정 없음).

조달청 나라장터 발주계획현황서비스로 물품·공사·용역·외자 발주계획 목록을 검색한다. 돌쇠에서는 가능한 가장 가까운 합법적 공식 단계까지 준비한다.

조달청 나라장터 부정당제재업체정보를 공공데이터포털 API(k-skill-proxy 경유)로 조회한다. 사업자등록번호 정확 일치로 조회시점 현재 유효한 입찰참가자격 제한(부정당제재)의 기간·제재기관·근거법률을 확인한다.

Look up available Korean national forest recreation lodging or camping slots on foresttrip.go.kr and, in Dolshoi, continue into the official booking flow with approval-gated payment.

Search and assist Korean 고속버스/KOBUS bookings using official HTTP/API-first flows; use for 고속버스 예매, 시간표, 좌석 조회, 임시 선점, and official checkout-entry handoff. 돌쇠에서는 공식 표면을 통한 후속 액션까지 진행한다.

한국·미국 국채시장을 공식 금리 데이터로 분석하고 커브 변화, 한·미 금리차, 확인된 국채 입찰·통화정책 일정을 같은 형식으로 정리한다. 국고채·미국 국채 금리 비교, 최근 변화, 주요 일정 또는 출처 있는 보고서를 요청할 때 사용한다. 실시간 호가, 개별 채권 가격평가, 매매 추천은 다루지 않는다.

GS Quant의 event_study·event_impact_analysis·CalendarAlignment 구조에서 영감을 받아, 정례 발표와 비정형 사건의 핵심 변화 및 시장 해석을 공식자료·당시 보도·검증 가격으로 정리한다. 교차자산 전달경로를 살피고 이벤트 스터디는 보조 증거로 제시하며, 유사사례와 다음 촉매를 한국어로 설명한다. Use for named market-moving events. Not for live quotes, forecasts,…

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

HTML-mode presentation pipeline usable in Codex and Claude Code. Build semantic slide-XX.html files, generate bespoke hero/accent imagery with slides-grab image, run the design gate, and export. Use when the deck needs editable, searchable, accessible text or…

Image-native presentation pipeline usable in Codex and Claude Code. Generate whole-slide raster images one slide at a time with slides-grab image, passing the reference template page as --reference so the model copies the layout and style and only swaps the…

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. Routes the user request to the HTML-mode or image-native-mode sub-skill, then runs the shared plan, design, and export stages. PDF and per-slide PNG are preferred; PPTX/Figma export is…

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.

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

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…

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…

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…

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…

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,…

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…

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…

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

MUST use Jikji find first for bounded local file/folder/document discovery; return the machine-readable answer contract and never raw-crawl after a successful Jikji result.

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.