This is the skill you reach for when you need to build something from scratch, whether it's a scheduled task, a dashboard, or a web app. It enforces a three-phase workflow: design with explicit user confirmation before writing any code, incremental building with verification at every step, and systematic debugging. Projects are scaffolded in a standard layout under output/projects/ from day one, making them immediately shareable via community-publish without later migration. The methodology emphasizes cost transparency for API calls through sc-proxy, especially LLM usage where high-end models can run 100x more expensive than budget ones. It's opinionated about verification, requiring you to run and check output after each piece rather than writing hundreds of lines blind.

skills.sh installs
5.2K
GitHub stars
32
last updated
Aug 21, 2026

Install

$ npx -y skills add starchild-ai-agent/official-skills --skill project-builder --agent claude-code

Installs into .claude/skills of the current project.

Files

logo.png

Phase 0: SKILL DISCOVERY & REQUIRED READING

⚠️ CRITICAL — UI Design Quality Gate: If the project produces ANY visual HTML output (dashboard, web app, landing page, portfolio, any page the user will see), you MUST read_file the ui-design skill's SKILL.md and follow it BEFORE writing any HTML/CSS. This is not optional. project-builder handles engineering; ui-design handles visual quality (and tells you when to reach for a component library like shadcn/ui, HeroUI, or coss ui instead of hand-writing). Skipping ui-design produces generic AI slop.

A. Pick the sources and tools. For research and API documentation, use web search. For live market numbers or external actions, reuse the relevant installed skill. Read its SKILL.md before use; search missing skills with auto_install=false and install only with user approval. Write custom API code only after checking that no suitable skill covers the operation; verify endpoints and response shapes against current official documentation.

Sponsors

Details

Repository
github.com/starchild-ai-agent/official-skills
Categories
Backend & APIs, DevOps & CI/CD, AI & Agent Building, Release Management, Debugging, Design & UI/UX
First seen
Apr 16, 2026

More from starchild-ai-agent/official-skills

All 43
1grafana avatartempografana/skillsStand up Grafana Tempo as a cost-efficient distributed-tracing backend that only needs object storage, and write TraceQL queries against it. Covers OTLP + Jaege5.2Kskills.sh installs
2forcedotcom avatardata360-schema-getforcedotcom/sf-skillsRetrieve Data Lake Object (DLO) and Data Model Object (DMO) schema information from Salesforce Data Cloud using REST APIs. Use this skill when you need to inspe5.1Kskills.sh installs
3ziniao-open avatarziniao-skill-makerziniao-open/skills创建 ziniao-cli 的自定义 Skill。当用户需要把紫鸟 API 操作封装成可复用的 Skill(包装原子 API 或编排多步流程)时使用。5Kskills.sh installs
4jeffallan avatardotnet-core-expertjeffallan/claude-skillsUse when building .NET 8 applications with minimal APIs, clean architecture, or cloud-native microservices. Invoke for Entity Framework Core, CQRS with MediatR,5Kskills.sh installs
5iii-hq avatariii-engine-configiii-hq/iiiConfigures the iii engine via iii-config.yaml — workers, adapters, queue configs, ports, and environment variables. Use when deploying, tuning, or customizing t4.9Kskills.sh installs
6forcedotcom avatarplatform-agentsetup-categories-fetchforcedotcom/sf-skillsFetch agentic setup prompt categories from a connected Salesforce org using the Connect API. Use this skill to call GET /agenticsetup/categories and return the 4.9Kskills.sh installs