ai-engineer

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.

Install with Tessl CLI

npx tessl i github:sickn33/antigravity-awesome-skills --skill ai-engineer

What are skills?

1.00x

Quality

16%

Does it follow best practices?

Impact

56%

1.00x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/ai-engineer/SKILL.md

SKILL.md

Review

Evals

Evaluation results

24%

-8%

Internal Knowledge Base Search for Engineering Teams

RAG pipeline with hybrid search and reranking

Criteria

Without context

With context

Recognised vector DB

Recognised embedding model

100%

Hybrid search implemented

100%

Reranking step

83%

Named chunking strategy

50%

100%

Context compression

Query understanding

Observability tooling

Structured outputs

Error handling

100%

50%

PII / sensitive data guard

Without context: $0.9839 · 3m 58s · 30 turns · 79 in / 14,413 out tokens

With context: $1.1498 · 6m 7s · 34 turns · 848 in / 13,684 out tokens

69%

Automated Customer Support System for a Financial Services Platform

Multi-agent orchestration with safety and guardrails

Criteria

Without context

With context

Recommended agent framework

Multi-agent roles

100%

Prompt injection guard

100%

PII detection / redaction

100%

Sensitive data control

100%

Structured outputs

100%

62%

Graceful degradation

100%

Memory system

Observability hook

37%

Content moderation

20%

50%

Adversarial test cases

100%

Without context: $0.9419 · 4m 7s · 26 turns · 75 in / 16,311 out tokens

With context: $1.1130 · 4m 42s · 33 turns · 533 in / 17,208 out tokens

78%

LLM Gateway Service for a Developer Platform

Production LLM API with caching, rate limiting, and observability

Criteria

Without context

With context

FastAPI async serving

100%

Semantic caching

Response memoization

100%

Rate limiting

100%

Cost controls

100%

Circuit breaker / fallback

100%

Streaming endpoint

100%

Observability integration

37%

62%

Structured output handling

62%

100%

Graceful error handling

75%

87%

Load balancing / model routing

25%

Without context: $1.4336 · 6m 34s · 28 turns · 75 in / 28,560 out tokens

With context: $1.0706 · 4m 36s · 27 turns · 24 in / 19,245 out tokens

Evaluated: 8 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Internal Knowledge Base Search for Engineering Teams Automated Customer Support System for a Financial Services Platform LLM Gateway Service for a Developer Platform

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.