Skip to content
LiveNew tools this week
Submit
AIMarketly
app-builder logo

app-builder

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

techwavedev/agi-agent-kit0installs4starsDevOps & CI/CD

SKILL.md

Full skill instructions

App Builder - Application Building Orchestrator

Analyzes user's requests, determines tech stack, plans structure, and coordinates agents.

🎯 Selective Reading Rule

Read ONLY files relevant to the request! Check the content map, find what you need.

FileDescriptionWhen to Read
project-detection.mdKeyword matrix, project type detectionStarting new project
tech-stack.md2025 default stack, alternativesChoosing technologies
agent-coordination.mdAgent pipeline, execution orderCoordinating multi-agent work
scaffolding.mdDirectory structure, core filesCreating project structure
feature-building.mdFeature analysis, error handlingAdding features to existing project
templates/​SKILL.mdProject templatesScaffolding new project

📦 Templates (13)

Quick-start scaffolding for new projects. Read the matching template only!

TemplateTech StackWhen to Use
nextjs-fullstackNext.js + PrismaFull-stack web app
nextjs-saasNext.js + StripeSaaS product
nextjs-staticNext.js + FramerLanding page
nuxt-appNuxt 3 + PiniaVue full-stack app
express-apiExpress + JWTREST API
python-fastapiFastAPIPython API
react-native-appExpo + ZustandMobile app
flutter-appFlutter + RiverpodCross-platform mobile
electron-desktopElectron + ReactDesktop app
chrome-extensionChrome MV3Browser extension
cli-toolNode.js + CommanderCLI app
monorepo-turborepoTurborepo + pnpmMonorepo

🔗 Related Agents

AgentRole
project-plannerTask breakdown, dependency graph
frontend-specialistUI components, pages
backend-specialistAPI, business logic
database-architectSchema, migrations
devops-engineerDeployment, preview

Usage Example

User: "Make an Instagram clone with photo sharing and likes"

App Builder Process:
1. Project type: Social Media App
2. Tech stack: Next.js + Prisma + Cloudinary + Clerk
3. Create plan:
   ├─ Database schema (users, posts, likes, follows)
   ├─ API routes (12 endpoints)
   ├─ Pages (feed, profile, upload)
   └─ Components (PostCard, Feed, LikeButton)
4. Coordinate agents
5. Report progress
6. Start preview

AGI Framework Integration

Qdrant Memory Integration

Before executing complex tasks with this skill:

python3 execution/​memory_manager.py auto --query "<task summary>"

Decision Tree:

  • Cache hit? Use cached response directly — no need to re-process.
  • Memory match? Inject context_chunks into your reasoning.
  • No match? Proceed normally, then store results:
python3 execution/​memory_manager.py store \
  --content "Description of what was decided/​solved" \
  --type decision \
  --tags app-builder <relevant-tags>

Note: Storing automatically updates both Vector (Qdrant) and Keyword (BM25) indices.

Agent Team Collaboration

  • Strategy: This skill communicates via the shared memory system.
  • Orchestration: Invoked by orchestrator via intelligent routing.
  • Context Sharing: Always read previous agent outputs from memory before starting.

Local LLM Support

When available, use local Ollama models for embedding and lightweight inference:

  • Embeddings: nomic-embed-text via Qdrant memory system
  • Lightweight analysis: Local models reduce API costs for repetitive patterns