ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.
61
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
78%
25%Regulatory Document Intelligence System
Production RAG retrieval pipeline
Approved vector DB
100%
100%
Approved embedding model
0%
100%
Hybrid search
100%
100%
Reranking step
0%
100%
Chunking strategy
100%
87%
Vector index strategy
25%
100%
Safety guardrails
100%
100%
Observability setup
0%
0%
Embedding caching
37%
25%
Structured outputs
100%
100%
Error handling
0%
16%
Without context: $1.8844 · 9m 25s · 54 turns · 59 in / 29,718 out tokens
With context: $2.1169 · 10m 28s · 43 turns · 51 in / 37,797 out tokens
68%
-2%Customer Support AI API Service
LLM API serving with safety and observability
FastAPI framework
100%
100%
Async processing
100%
100%
Semantic caching
10%
0%
Rate limiting / cost controls
90%
100%
Observability integration
40%
0%
PII detection
90%
100%
Prompt injection guard
100%
100%
Structured I/O
100%
100%
Circuit breaker / fallback
37%
50%
Adversarial tests
100%
100%
Streaming support
0%
0%
Without context: $1.1927 · 5m 1s · 37 turns · 41 in / 21,659 out tokens
With context: $2.1469 · 7m 57s · 50 turns · 55 in / 34,970 out tokens
75%
11%Automated Competitive Intelligence Agent
Multi-agent orchestration and memory
Approved agent framework
0%
0%
Agent state management
37%
75%
Memory system
70%
100%
Tool integration
90%
100%
Structured tool outputs
62%
87%
Cost controls
90%
100%
Error handling / graceful degradation
90%
100%
Safety guardrails
90%
100%
Observability
10%
0%
Production architecture
100%
100%
Multi-agent specialization
100%
100%
Without context: $1.0580 · 5m 26s · 28 turns · 32 in / 21,688 out tokens
With context: $1.6884 · 7m 16s · 43 turns · 207 in / 28,704 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
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.