Browse The Skill Store

Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

Published AI benchmarks measure brains in jars. They test models in isolation or within a single reference harness — and then attribute all performance to the model. This skill teaches you to decompose agent performance into its two actual components: model capability and harness multiplier. The result is evaluations that predict real-world behavior instead of benchmark theater.

Professional prompt engineering, audit, and evaluation system for production-grade AI agents and workflows.

RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.

production agent architect

by Roy Yuen

$6

Architect, scaffold, and harden production-grade AI agents with battle-tested patterns and systematic evaluation.

Audit your AI agent's evaluation coverage to identify missing release gates and production risks.

AI Eval & Test Suite Quality Gate

by PubsProToolkit

$14

An adversarial gate that audits an AI eval or test suite — LLM-judge rubrics, datasets, regression tests, metrics — for gameable criteria, data leakage, missing edge cases, and non-determinism, then returns one PASS/REVISE/FAIL verdict.

🧠 AI Memory Optimizer

by Martin Gunderman

$7

Drastically reduce RAG costs and latency while improving retrieval accuracy through advanced memory architecture.

LLM Eval Framework Builder

by Arnstein Larsen

$17

You changed the prompt, tried four inputs, it looked better, you shipped — and three days later support tickets say outputs are worse for an entire class of inputs you didn't test

Convert loose prompt sets into structured, target-ready records with variables, contracts, and eval cases.

RAG Failure Diagnostics & Architect

by Arnstein Larsen

$7

A retrieval architect that diagnoses why RAG returns confident-but-wrong answers, picks the right context architecture (RAG vs knowledge graph vs structured/temporal retrieval) instead of defaulting to vector search, and designs the institutional-memory schema embeddings throw away.

Diagnose broken RAG systems. 8 failure categories: chunking, embeddings, retrieval, reranking, hallucination. Recall@k measurement.

Diagnose RAG bottlenecks with precision metrics (Recall, MRR, nDCG) to identify retrieval or ranking failures.

AI Feature Eval Writer

by PubsProToolkit

$14

Design and write the eval suite for your LLM-powered feature — the metrics that match your failure modes, a golden dataset plan with starter cases, anchored rubrics, LLM-as-judge prompts with the known bias mitigations, and pass/fail gates wired for CI.

Agent Eval Harness

by Echo Rose

$5

Agent Eval Harness - A Premium AI Agent Skill

Agent Harness Architect

by PubsProToolkit

$14

Model quality is table stakes — the harness is where agents win or fail. This designs yours: it writes a structured, testable system prompt (role, tools, boundaries, method, output contract, failure handling) and maps every concern to the right layer — prompt, tool, guardrail, or evaluation — so the pieces reinforce each other instead of fighting.

Your skill works today. Will it work after the next model update? Build the harness that answers with numbers. Builds a standalone regression test harness with mechanical grading to verify skill behavior after model or code updates.