Skills ai-engineer
📦

ai-engineer

Content revision r2 Safe

Build Production-Ready LLM Systems

Production AI systems require reliable retrieval, orchestration, safety, monitoring, and cost controls. This skill provides structured engineering guidance across the complete LLM application lifecycle.

Supports: Claude Codex Code(CC)
🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "ai-engineer" from https://skillstore.io/skills/sickn33-ai-engineer.md and its manifest at https://skillstore.io/api/skills/sickn33-ai-engineer/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Test it

Using "ai-engineer". Design a RAG system for an internal policy library.

Expected outcome:

A staged architecture covering document ingestion, permission-aware hybrid retrieval, reranking, cited answers, offline evaluation, monitoring, and gradual rollout.

Using "ai-engineer". Reduce the cost and latency of an existing support assistant.

Expected outcome:

A prioritized plan using model routing, semantic caching, prompt compression, streaming, budget limits, and quality checks before each optimization.

Using "ai-engineer". Plan a customer service agent with refund tools.

Expected outcome:

A controlled workflow with scoped tools, explicit approval thresholds, durable state, escalation paths, audit logs, failure recovery, and adversarial tests.

Security Audit

Safe
v6 • 7/23/2026 Open versioned report

All four static findings are false positives caused by safety and information-retrieval terminology in SKILL.md. The file contains guidance only and does not direct system reconnaissance, jailbreak behavior, code execution, or data exfiltration. No net-new semantic security risks were found.

1
Files scanned
191
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/sickn33-ai-engineer/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sickn33-ai-engineer/security.svg)](https://skillstore.io/skills/sickn33-ai-engineer?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/sickn33-ai-engineer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-ai-engineer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/sickn33-ai-engineer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

sickn33. (2026). ai-engineer security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-ai-engineer/audits/6

BibTeX citation

@techreport{sickn33-sickn33-ai-engineer-2026, author = {sickn33}, title = {ai-engineer security audit report (audit version 6)}, institution = {Skillstore}, year = {2026}, number = {6}, url = {https://skillstore.io/skills/sickn33-ai-engineer/audits/6}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "ai-engineer security audit report (audit version 6)" version: "unspecified" type: report authors: - name: "sickn33" date-released: "2026-07-23" url: "https://skillstore.io/skills/sickn33-ai-engineer/audits/6" identifiers: - type: other value: "skillstore:sickn33-ai-engineer:audit:6" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
68
Community
83
Spec Compliance

What You Can Build

Add an LLM Feature

Design a reliable model integration with typed outputs, fallback behavior, testing, and cost limits.

Build Enterprise RAG

Plan ingestion, chunking, hybrid retrieval, reranking, evaluation, access control, and production monitoring.

Define an Agent Architecture

Turn a product workflow into tools, state transitions, guardrails, human escalation, and measurable success criteria.

Try These Prompts

Plan a Basic LLM Feature
Design an LLM feature for [use case]. State assumptions, model choice, request flow, safety controls, tests, and a small rollout plan.
Design a RAG Pipeline
Design a RAG system for [documents and users]. Cover ingestion, chunking, retrieval, reranking, citations, evaluation, permissions, latency, and cost.
Architect an AI Agent
Design an agent for [workflow]. Define tools, permissions, state, memory, failure handling, human approval points, observability, and adversarial tests.
Review a Production AI Platform
Review this architecture: [details]. Identify reliability, security, quality, latency, and cost risks. Prioritize fixes and define measurable release gates.

Best Practices

  • Define quality, latency, cost, safety, and reliability targets before selecting models or frameworks.
  • Evaluate retrieval and generation separately with representative data, adversarial inputs, and traceable failure categories.
  • Use least-privilege tools, redact sensitive data, require approval for high-impact actions, and monitor production behavior.

Avoid

  • Do not choose an agent when a deterministic workflow or simple model call can solve the task.
  • Do not send sensitive data to external models without authorization, minimization, redaction, and retention controls.
  • Do not launch without evaluation baselines, observability, fallback behavior, cost limits, and a rollback plan.

Frequently Asked Questions

What types of systems does this skill cover?
It covers LLM applications, RAG pipelines, AI agents, vector search, multimodal integrations, model APIs, safety controls, and production operations.
Does it require a specific model provider?
No. It supports provider-hosted and open-source models, with selection based on quality, latency, cost, privacy, and deployment constraints.
Can it design a complete RAG architecture?
Yes. It can address ingestion, chunking, embeddings, retrieval, reranking, context construction, citations, evaluation, permissions, monitoring, and cost.
Can it implement autonomous agents?
It can design and implement controlled agent workflows with tools, memory, state, guardrails, evaluation, and human approval points.
Does it replace security or compliance review?
No. Its guidance supports engineering decisions, but qualified reviewers must validate privacy, security, legal, and compliance requirements.
What information should I provide?
Provide the use case, users, data sources, existing stack, constraints, success metrics, permissions, budget, latency targets, and deployment environment.

Developer Details

Author

sickn33

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Ref

ebdfe608f5de2b66ff37ab4af12af8ac4f5e8006

Maintenance freshness

7/26/2026

Usage

6 downloads · 92 views

File structure

📄 SKILL.md