Back to Resources

Series

Rhize Media resource articles grouped into ordered series: how our plugins, workflows and technical stack change over time, one part at a time.

All series

Pick a story

4 parts · updated September 26, 2026

Measuring Agent Skills

Three measurements of how AI agents actually use a skill library: why a list failed, why subagents never browsed it, and what Claude Code's native plugin evals do and do not prove.

Open the series
In this series · 4 partsShow the parts
  1. Part 1Managing AI Agent Skills: A Case Study in Preventing DuplicationLearn how a generated skill map can reveal duplicate AI skills, stale forks and routing gaps, with a practical audit sequence and case-study limits.Jim Deola · August 9, 2026
  2. Part 2Why Aren't My Claude Code Subagents Using My Skills?Diagnose why a Claude Code subagent is not using an installed skill: check preloading, tool access, task instructions and execution evidence.Jim Deola · August 26, 2026
  3. Part 3How to Test Claude Code Plugins and Interpret Eval ResultsTest Claude Code plugins with bounded cases and inspect errors, routing, baseline access and output quality before interpreting eval scores.Jim Deola · September 16, 2026
  4. Part 5AI Agent Memory Benchmarks: What Two Small Studies Show UsLearn how to evaluate AI agent memory and workflow benchmarks: task design, retrieval quality, missing telemetry, grading and limits.Rhize Media Team · September 26, 2026

2 parts · updated August 26, 2026

Procedural Memory

How we taught our AI systems to keep the code they already wrote: the registry, the first paired benchmark, and what each measurement changed about the method.

Open the series
In this series · 2 partsShow the parts
  1. Part 1What Is Procedural Memory for AI Agents, and When Is It Useful?Understand procedural memory for AI agents, how it differs from saved facts, and the trust, validation and measurement needed before reusing a workflow.Jim Deola · August 23, 2026
  2. Part 2AI Workflow Benchmarks: Why Our First Comparison Was InvalidWhy an early AI workflow benchmark could not compare performance, what it still measured and which controls the next test needed.Jim Deola · August 26, 2026

Find the constraint first.
Then decide what AI should fix.

The next step is a 30-minute call.

Tell us where work stalls: missed calls, slow follow-up, numbers you can't trust, decisions that wait on you. We'll talk through what we'd look at first and whether we're the right partner. If we're not, we'll say so.

Book a 30-min callBrowse all resources

No obligation. No pitch deck.