ldmrepo

Binance Futures에서 Playwright 브라우저를 통해 Trailing Stop 주문을 UI로 직접 등록하는 자동화 스킬. 활성화 가격(activationPrice), 콜백 비율(callbackRate%), 수량(size)을 파라미터로 받아 Close 탭 → Trailing Stop 선택 → 값 입력 → Close long 순서로 주문을 제출한다. 키워드: 트레일링 스탑, trailing stop, 바이낸스 선물, binance futures, 추적 매도, 자동 청산

XRPUSDT 박스권 자동 스켈핑 전략 스킬. Binance Futures Hedge mode에서 평균회귀형 범위장 스캘프를 설계, 검토, 백테스트, 운용할 때 사용한다. 키워드: XRP, box range, 박스권, scalping, mean reversion, hedge mode, futures bot, funding, open interest, breakout filter

Binance Futures TradingView 차트 설정 자동화. 수평선 그리기, 지표 추가, 차트 초기화. 키워드: 차트 설정, 차트 분석, 수평선, 지지선, 저항선, TradingView, 차트 최적화, horizontal line, chart setup

Obsidian Vault 지식 저장소 관리 스킬. 키워드: obsidian, vault, 노트, 지식, knowledge, playbook, journal, 저널, 리뷰

주식 트레이딩 대가(드러켄밀러, 리버모어, CANSLIM, 튜더 존스, 피터 린치)의 전략을 암호화폐 시장에 적용하는 가이드. 트레이딩 전략, 진입/청산 조건, 리스크 관리, 모멘텀, 추세추종, 평균회귀, 돌파매수, BTC 사이클, 알트코인 로테이션, 텐배거 발굴에 대한 질문이나 코인 투자 전략이 필요할 때 사용.

Binance 거래소 API 기본 정보. 마이클이 필요시 도구를 직접 생성하여 사용. 키워드: 바이낸스, binance, 포트폴리오, 잔고, 선물, 거래, spot, futures, balance

NLM 세컨드 브레인 — 노트북 조회, 학습 기록, 경험 축적. 키워드: NLM, 세컨드 브레인, second brain, 노트북, notebook, 학습, 교훈, lesson, 경험, knowledge

Polymarket 예측시장 API 기본 정보. 마이클이 필요시 도구를 직접 생성하여 사용. 키워드: 폴리마켓, polymarket, 예측시장, PM, 베팅, prediction market

Decomposes a project milestone into bounded, verifiable feature-list entries suitable for the planner/coder/reviewer cycle in the agent harness.

Handles bounded bug-fix sessions in the long-running harness by reproducing, isolating, fixing, verifying, and recording defects with explicit blocker and issue tracking.

Applies a structured evidence-based review checklist for bounded session results, validating scope, correctness, verification, artifact consistency, and resumable repository state.

Implements a selected bounded feature task within the long-running harness, respecting current-task scope, verification requirements, artifact updates, and clean-state handoff rules.

Evaluates whether a bounded implementation or bug-fix session introduced regressions, using task-aware verification evidence, repository state checks, and explicit risk recording.

Establishes a reproducible repository bootstrap path for long-running agent sessions, including execution entry points, state artifacts, smoke readiness, and baseline environment normalization.

Breaks large or ambiguous work into bounded, verifiable session-sized tasks that can be selected, implemented, reviewed, and handed off safely within the harness.

Enforces the repository's verification gate for bounded sessions by evaluating required test scope, execution evidence, pass/fail status, and gate impact on task approval.

Builds the Pixel Office Node.js backend server with JSONL file watching, Claude Code log parsing, agent state machine, and WebSocket real-time API. Triggers when server-side features need building or modification.

Builds the Pixel Office React frontend that integrates the game engine, WebSocket client, and dashboard UI. Creates the complete user-facing application with agent monitoring panel. Triggers when UI features, layout changes, or frontend integration is needed.

Builds the Pixel Office Canvas 2D game engine with sprite animation, tile map rendering, BFS pathfinding, and character state visualization. Pure Canvas 2D, no external game libraries. Triggers when game engine features need building or modification.

Orchestrates the full Pixel Office build pipeline by dispatching parallel sub-agents, managing shared type contracts, and performing final integration verification. Triggers when user requests building, rebuilding, or modifying the Pixel Office app.

Downloads and configures MetroCity pixel art assets for the Pixel Office project. Generates programmatic placeholder sprites when external downloads are unavailable. Triggers when asset setup, sprite sheet creation, or tile map definition is needed.

This skill should be used when the user wants to "build a harness", "design an agent team", "set up a harness", "configure an agent team for this project", or needs to generate agent definitions (.claude/agents/) and skills (.claude/skills/) tailored to a specific domain. Analyzes the project domain, selects an architecture pattern from 6 options, and generates a complete, production-ready agent team with orchestration, skills, and validation. Use when the user mentions harness, agent team, multi-agent system, or asks to automate a complex multi-step workflow with specialized agents.