Cold Start Safe Architecture

01 / SKILL INTRODUCTION

About this skill

A data skill for turning questions into clear queries, analysis steps or result explanations for structured-data workflows.

TRIGGER DESCRIPTION

Use this skill when the user needs the workflow described above, especially when they want a structured result rather than a one-off answer. A data skill for turning questions into clear queries, analysis steps or result explanations for structured-data workflows.

01Progressive disclosure

Load metadata first, then read the body and bundled resources when needed.

02Evaluable iteration

Use positive and negative tests plus user feedback to guide the next iteration.

03Clear output contract

Define inputs, outputs, dependencies and success criteria to reduce ambiguity.

02 / SKILL FILES

Skill files

Act as a Senior Expo + Supabase Architect.

Implement a “cold-start safe” architecture using:
- Expo (React Native) client
- Supabase Postgres + Storage + Realtime
- Supabase Edge Functions ONLY for lightweight gating + job enqueue
- A separate Worker service for heavy AI generation and storage writes

Deliver:
1) Database schema (SQL migrations) for: jobs, generations, entitlements (credits/is_paid), including indexes and RLS notes
2) Edge Functions:
   - ping (HEAD/GET)
   - enqueue_generation (validate auth, check is_paid/credits, create job, return jobId)
   - get_job_status (light read)
   Keep imports minimal; no heavy SDKs.
3) Expo client flow:
   - non-blocking warm ping on app start
   - Generate button uses optimistic UI + placeholder
   - subscribe to job updates via Realtime or implement polling fallback
   - final generation replaces placeholder in gallery list
4) Worker responsibilities (describe interface and minimal endpoints/logic, do not overbuild):
   - fetch queued

This is an online preview. Copy it and continue editing in your local skill directory.

YAML FRONTMATTERSkill metadata

nameCold Start Safe Architecture

descriptionUse this skill when the user needs the workflow described above, especially when they want a structured result rather than a one-off answer. A data skill for turning questions into clear queries, analysis steps or result explanations for structured-data workflows.

03 / WORKFLOW

How to use

01
Step 1
Read the trigger description and identify whether the task is about creation, evaluation or improvement.
02
Step 2
Open SKILL.md and confirm the input, output and bundled resource requirements.
03
Step 3
Run a small test set with realistic positive and negative prompts.
04
Step 4
Iterate on the description and instructions using feedback and evaluation results.

04 / DISCUSSIONS

Discussions and feedback

—feedback records

Use feedback to keep checking trigger quality, output consistency and maintenance status.

Back to skills