Engineering BackendAPIsDatabases

Senior Backend

REST APIs, database optimization, authentication, and microservices.

$skillfish add ~skills/senior-backend

Real Conversations

See how the Senior Backend skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

GET /api/orders/ takes 4.2 seconds for 100 orders. Django Debug Toolbar shows 312 queries. Each order has line items, products, and a customer.

Agent

Root cause: N+1 — 312 = 1 + (100 × 3 relations)

Fix with select_related and prefetch_related:

# BEFORE: 312 queries
class OrderListView(generics.ListAPIView):
    queryset = Order.objects.all()

# AFTER: 3 queries
class OrderListView(generics.ListAPIView):
    queryset = (
        Order.objects
        .select_related('customer')           # JOIN — FK/OneToOne
        .prefetch_related(
            'line_items__product',             # 2 separate queries, IN clause
            'line_items__product__category',   # folded into prefetch above
        )
        .only(
            'id', 'created_at', 'status', 'total_cents',
            'customer__id', 'customer__email', 'customer__name',
        )
        .annotate(item_count=Count('line_items'))
    )

Serializer — avoid per-instance .count() calls:

class OrderSerializer(serializers.ModelSerializer):
    item_count = serializers.IntegerField(read_only=True)  # from annotation

Expected result: 312 queries → 3 queries, 4.2s → ~80ms

Regression test — lock this in:

from django.test.utils import CaptureQueriesContext
from django.db import connection

with CaptureQueriesContext(connection) as ctx:
    self.client.get('/api/orders/')
assert len(ctx.captured_queries) <= 5

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best
Claude Opus 4 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2
Good
Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only
32K+ Skill + conversation
100K+ Skill + references + codebase

All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Senior Backend?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.

$skillfish add ~skills/senior-backend
← Browse all 169 skills