Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add onfire7777/universal-ai-skills-library --skill ai-expertise-enginegit clone --depth 1 https://github.com/onfire7777/universal-ai-skills-libraryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/onfire7777/universal-ai-skills-library/ai-expertise-engine)<a href="https://agentmods.dev/skills/onfire7777/universal-ai-skills-library/ai-expertise-engine"><img src="https://agentmods.dev/badge/skills/onfire7777/universal-ai-skills-library/ai-expertise-engine/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/onfire7777/universal-ai-skills-library/ai-expertise-engine"><img src="https://agentmods.dev/badge/skills/onfire7777/universal-ai-skills-library/ai-expertise-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.01931 |
| Opus 5 | $0.00023 | $0.00966 |
| Sonnet 5 | $0.00009 | $0.00386 |
| Haiku 4.5 | $0.00005 | $0.00193 |
Grade A, and why
ai-expertise-engine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Expertise Engine
Purpose
Provide world-class AI expertise across the full spectrum — from prompt engineering and LLM usage to AI system architecture, agent design, RAG pipelines, fine-tuning, safety, and cutting-edge research.
Prompt Engineering Mastery
The Prompt Engineering Hierarchy
- System Prompt Design: Define persona, constraints, output format, and behavioral rules
- Few-Shot Examples: Provide 2-5 high-quality input/output examples
- Chain-of-Thought: "Think step by step" / "Let's work through this systematically"
- Structured Output: Specify exact JSON schema, Markdown format, or template
- Meta-Prompting: Prompt the AI to generate better prompts
Advanced Prompt Techniques
- Role Assignment: "You are a senior security researcher with 20 years of experience..."
- Constraint Setting: "You MUST cite sources. You MUST NOT speculate without evidence."
- Output Templating: "Respond in this exact format: [template]"
- Self-Consistency: Generate multiple responses and pick the most common answer
- Tree of Thought: Explore multiple reasoning paths, evaluate each, select the best
- ReAct Pattern: Reason → Act → Observe → Reason → Act (for tool-using agents)
- Reflection Prompting: "Review your answer. What might be wrong? Revise if needed."
- Decomposition: Break complex tasks into subtasks with separate prompts for each
Prompt Anti-Patterns
- Vague instructions without specific output format
- Too many instructions at once (cognitive overload)
- Contradictory constraints
- Assuming the model knows your context
- Not providing examples when the task is ambiguous
- Over-constraining creativity when exploration is needed
LLM Architecture Understanding
Transformer Architecture
- Self-Attention: Allows each token to attend to all other tokens (O(n²) complexity)
- Multi-Head Attention: Multiple attention patterns in parallel
- Feed-Forward Networks: Position-wise transformations
- Layer Normalization: Stabilizes training
- Positional Encoding: Injects sequence order information
- KV Cache: Stores key-value pairs for efficient autoregressive generation
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 178 lines · 46 tokens per session scan A 3b99255eb9af
ai-expertise-engine is a skill published in the GitHub repository onfire7777/universal-ai-skills-library (16 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,931 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
mistral
Mistral AI provides frontier open and commercial AI models, featuring mistral-large-latest, mistral-small-latest, codestral-latest for coding, and mistral-embed for semantic search.
ai-automation
Workflow automation skills using AI. Build chatbots, automate repetitive tasks, integrate LLMs into pipelines, design intent-based assistants. Triggers on: chatbot, automation, workflow, AI agent, RAG, LLM integration, intent recognition, conversation design.
pentest-llm
LLM application red team — OWASP LLM Top 10, prompt injection, RAG poisoning, MCP server abuse, agent tool abuse, jailbreak testing advisory. Triggers on LLM red team, prompt injection, jailbreak, RAG poisoning, OWASP LLM Top 10, MCP abuse, agent tool abuse, AI security testing.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.
llm-application-dev
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.