project-builder은(는) 무엇을 하나요?
종합 프로젝트 엔지니어링: 설계, 점진적 구축, 검증, 체계적 디버깅. 사용자가 요청한 소프트웨어, 대시보드, 스케줄 작업 또는 웹 앱(예: 가격 모니터, 일일 요약 작업, API 배포)을 구축할 때 사용합니다.
종합 프로젝트 엔지니어링: 설계, 점진적 구축, 검증, 체계적 디버깅. 사용자가 요청한 소프트웨어, 대시보드, 스케줄 작업 또는 웹 앱(예: 가격 모니터, 일일 요약 작업, API 배포)을 구축할 때 사용합니다.
이 스킬은 AI 에이전트(Claude Code, Cursor, Codex 등)가 소프트웨어 프로젝트를 처음부터 끝까지 체계적으로 관리할 수 있도록 설계된 종합 프로젝트 엔지니어링 도구입니다. 주요 기능으로는 요구사항 분석 및 설계 문서 작성, 작은 단위의 점진적 코드 구현, 각 단계별 자동 검증, 그리고 문제 발생 시 체계적인 디버깅 절차를 제공합니다. 사용자가 "가격 모니터 구축", "일일 요약 작업 생성", "API 배포"와 같은 요청을 할 때, 이 스킬은 프로젝트 생명주기 전반에 걸쳐 일관된 프로세스를 적용하여 생산성과 결과물의 품질을 크게 향상시킵니다. 이 스킬은 다양한 플랫폼에서 사용 가능하며, 그 목적은 개발자가 요구사항 정의부터 배포까지의 모든 단계에서 신뢰할 수 있는 프레임워크를 제공하는 것입니다.
npx skills add https://github.com/starchild-ai-agent/official-skills/tree/main/skills/project-builder종합 프로젝트 엔지니어링: 설계, 점진적 구축, 검증, 체계적 디버깅. 사용자가 요청한 소프트웨어, 대시보드, 스케줄 작업 또는 웹 앱(예: 가격 모니터, 일일 요약 작업, API 배포)을 구축할 때 사용합니다.
This repo contains 20 individual skills — each has its own dedicated page.
Preview panel and iframe diagnostics: registry, ports, paths, blank screens. Use when a preview tab is broken or missing (e.g. white screen, tab disappeared, 404 on assets, preview not loading, list running services).
Register a custom LLM endpoint with your own API key for chat in Starchild. Use when adding a personal Anthropic, OpenAI, Grok, Qwen, DeepSeek, NEAR AI, or Venice key as a chat model (e.g. add my Claude key, register DeepSeek).
Interactive web charts: line, bar, candle, scatter, with HTML and screenshot output. Use when visualizing data for analysis or BI (e.g. plot BTC vs gold last year, bar chart of revenue by quarter, compare two return series).
Generate TradingView-style candlestick charts with indicators. Use when the user wants a visual chart, price visualization, or technical analysis plot.
Connect a ChatGPT or Codex subscription via OAuth device-code login. Use when the user wants to sign in with their ChatGPT Plus, Pro, or Team account (e.g. "use my Codex subscription", "log in with ChatGPT").
Code specialist for writing, debugging, and technical implementation. Use when the user needs code written, bugs fixed, files edited, or features built.
Crypto spot prices, OHLC charts, market discovery, and global stats. Use when looking up coin prices, market caps, trending coins, sector rankings, or comparing tokens (e.g. BTC price, ETH chart, top gainers).
Crypto derivatives data: funding rates, open interest, liquidations, long/short ratios. Use when researching perp markets, tracking Hyperliquid whale positions, or comparing ETF flows (e.g. BTC funding, ETH OI, liquidation heatmap).
Share or open-source any project the user has built — a running preview/service, a project directory, a dashboard, or scripts. Use whenever the user wants to publish, share, make public, list, distribute, deploy publicly, or open-source something. Three independent actions — publish_preview (allocate a public URL for a running service), list_in_dashboard (show it on the public Project Dashboard for discovery), open_source (push project source to the community GitHub repo). Do NOT search the filesystem for publish-related code or write custom deploy/upload scripts — this skill is the single entry point.
Composio gateway: act on 1000+ connected apps like Gmail, Slack, GitHub, Calendar. Use when the user wants to act in a connected SaaS app (e.g. send Gmail, create Notion page, add Calendar event, open a GitHub issue).
Trade perp futures, spot, and RWA on Hyperliquid DEX with up to asset max leverage. Use when placing perp or spot orders, setting TP/SL, or moving funds on Hyperliquid (e.g. long BTC 5x, sell ETH, deposit USDC, set stop).
Agent onboarding for Orderly Network - omnichain perpetual futures infrastructure, MCP server, skills, and developer quickstart
Frontend & fullstack development with live preview. Use when the user wants to build a web page, frontend app, fullstack project, or any web UI — including React, Vue, Vite, static HTML, Express, FastAPI, or any framework that produces a browser-viewable result. Also use when the user wants to deploy, publish, or share a preview to the public internet (community publish).
Scaffold new skills with valid frontmatter, directory layout, and a starter SKILL.md. Use when building a new reusable workflow or wrapping a new API (e.g. create a kalshi skill, scaffold an API helper, start a charting skill).
Search, install, and publish skills across official, community, and global registries. Use when finding or sharing skills (e.g. install a "funding rate" skill, list installed skills, publish my custom skill to the registry).
Build 16:9 slide decks as HTML, exported to PDF (not PowerPoint format). Use when making a deck, presentation, or pitch (e.g. 10-slide pitch deck for X, training course on Y, quarterly results presentation).
Telegram bot binding: create the bot, connect to Starchild, verify, troubleshoot. Use when setting up Telegram delivery (e.g. add my TG bot, bot binding code, fix "telegram not pushing", whitelist a TG username).
Stocks, forex, and commodities prices: real-time quotes and historical bars. Use when looking up traditional-market prices (e.g. AAPL quote, EUR/USD chart, gold price, SPY history). Not for crypto.
Twitter/X data: fetch tweets, search, user profiles, followers, replies, trends. Use for any x.com or twitter.com URL or lookup (e.g. summarize this tweet, recent posts by @vitalikbuterin, search $SOL min_faves:50).
Onboarding script for first-time Starchild users: positioning, quick wins, discovery. Use when the user is new or vague (e.g. "what can you do", "I don't know where to start", first session with no context, generic hello).
ElevenLabs text-to-speech with mac-style say UX.
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.
Capture and automate macOS UI with the Peekaboo CLI.
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".