⚠️ AUTHORIZED USE ONLY This skill is for educational purposes or authorized security assessments only. You must have explicit, written permission from the system owner before using this tool. Misuse of this tool is illegal and strictly prohibited.

Mandatory confirmation gate Before running any command that probes, exploits, changes, persists on, extracts data from, or attempts credential access against a target:

1. Ask the user to state the exact target URL, IP, account, or resource.
2. Ask the user to confirm written authorization and the permitted scope.
3. Show the exact command(s) and explain their expected effect.
4. Wait for explicit confirmation in the current conversation.

Without that confirmation, remain read-only and provide defensive guidance only. Prefer a sandbox, disposable VM, or controlled lab.

AI Engineering Toolkit

Overview

A collection of 6 structured, expert-level workflows that turn your AI coding assistant into a senior AI engineering partner. Each skill encodes a repeatable methodology — not just "ask AI to help," but a step-by-step decision framework with quantitative scoring, checklists, and decision trees.

The key difference from ad-hoc AI assistance: Scores and qualitative outputs can vary by evaluator, model and context; calibrate rubrics and record versions before making comparisons. You can use the scoring systems as team baselines and write them into CI/CD pipelines.

When to Use This Skill

• Use when evaluating or optimizing LLM system prompts before production deployment
• Use when designing a RAG pipeline and need structured architecture decisions (not just boilerplate code)
• Use when planning token budget allocation across context window zones
• Use when running pre-launch security audits on AI agents
• Use when building evaluation frameworks for LLM applications
• Use when thinking through product strategy before writing code

Availability and scope

This AAS tree bundles this overview only; the six named workflow packages, 65 test cases and CI templates are not included here. Do not claim a 65-test run or a scored assessment without actual supplied rubric, cases, harness and recorded execution. The upstream collection is an optional separately reviewed source; its installation does not validate a production system.

How It Works

Skill 1: Prompt Evaluator

A defined evaluator can score prompts across 8 dimensions (Clarity, Specificity, Completeness, Conciseness, Structure, Grounding, Safety, Robustness) on a 1-10 scale with weighted aggregation to a 0-100 score. Identifies the 3 weakest dimensions, generates targeted rewrites, and re-evaluates. Supports single prompt, A/B comparison, and batch evaluation modes.

Skill 2: Context Budget Planner

Analyzes token distribution across 5 context zones (System, Few-shot, User input, Retrieval, Output) and produces an optimized allocation plan. Includes a compression strategy decision tree for each zone. Common finding: output zone squeezed to under 6% — this skill catches that before truncation happens.

Skill 3: RAG Pipeline Architect

Walks through a complete architecture decision tree: document format → parsing strategy → chunking approach (fixed/semantic/recursive) → embedding model selection → retrieval method (vector/keyword/hybrid) → evaluation metrics (Faithfulness, Relevancy, Context Precision). Covers Naive RAG, Advanced RAG, and Modular RAG patterns.

Skill 4: Agent Safety Guard

Executes a 65-point red-team audit across 5 attack categories: direct prompt injection, indirect prompt injection (via RAG documents), information extraction (system prompt / API key leakage), tool abuse (SQL injection, path traversal, command injection), and goal hijacking. The AI constructs adversarial test prompts for evaluation purposes, asks the user for confirmation before each test phase, judges pass/fail, and generates fix recommendations. All tests are contained within the evaluation context and do not interact with external systems. It is recommended to run audits in a sandboxed environment (Docker/VM).

Skill 5: Eval Harness Builder

Designs evaluation metric systems for LLM applications. Includes LLM-as-Judge scoring framework with bias mitigation strategies (position bias, verbosity bias, self-enhancement bias). Outputs CI/CD-ready evaluation pipeline templates.

Skill 6: Product Sense Coach

…