Skip to content

MustafaKucukcoskun/Refine-agent-kit / .agents/skills/app-builder

app-builder

Verified

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

FileKindSize
SKILL.mdskill md7.4 KB
agent-coordination.mdmarkdown5.4 KB
feature-building.mdmarkdown1.1 KB
project-detection.mdmarkdown1.3 KB
scaffolding.mdmarkdown3.5 KB
tech-stack.mdmarkdown886 B

feature-building.md

View on GitHub
# Feature Building

> How to analyze and implement new features.

## Feature Analysis

```
Request: "add payment system"

Analysis:
├── Required Changes:
│   ├── Database: orders, payments tables
│   ├── Backend: /api/checkout, /api/webhooks/stripe
│   ├── Frontend: CheckoutForm, PaymentSuccess
│   └── Config: Stripe API keys
│
├── Dependencies:
│   ├── stripe package
│   └── Existing user authentication
│
└── Estimated Time: 15-20 minutes
```

## Iterative Enhancement Process

```
1. Analyze existing project
2. Create change plan
3. Present plan to user
4. Get approval
5. Apply changes
6. Test
7. Show preview
```

## Error Handling

| Error Type | Solution Strategy |
|------------|-------------------|
| TypeScript Error | Fix type, add missing import |
| Missing Dependency | Run npm install |
| Port Conflict | Suggest alternative port |
| Database Error | Check migration, validate connection |

## Recovery Strategy

```
1. Detect error
2. Try automatic fix
3. If failed, report to user
4. Suggest alternative
5. Rollback if necessary
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall