What is create-eval-from-docs?

A skill that turns KubeVirt user-guide documentation into MCPChecker evaluation tasks. MCPChecker tasks test whether tools produce the expected results, and the output is written as YAML files.

Use it to extract workflows from KubeVirt compute, storage, and network guides, connect them to available MCP tools, and generate tasks with scripts that can check cluster state using kubectl.

It helps expand test coverage from documented user workflows instead of creating every evaluation task by hand.

create-eval-from-docs — Skill for Claude Code by lyarwood

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/lyarwood/kubevirt-ai-helpers

agentmods

npx agentmods add skills/lyarwood/kubevirt-ai-helpers/create-eval-from-docs

Made for: Claude Code.

Or install kubevirt, the plugin that ships this one along with the rest of its 4 skills, 17 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lyarwood/kubevirt-ai-helpers/create-eval-from-docs/github.svg)](https://agentmods.dev/skills/lyarwood/kubevirt-ai-helpers/create-eval-from-docs)

Your own site

<a href="https://agentmods.dev/skills/lyarwood/kubevirt-ai-helpers/create-eval-from-docs"><img src="https://agentmods.dev/badge/skills/lyarwood/kubevirt-ai-helpers/create-eval-from-docs/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lyarwood/kubevirt-ai-helpers/create-eval-from-docs"><img src="https://agentmods.dev/badge/skills/lyarwood/kubevirt-ai-helpers/create-eval-from-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,349 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00064	$0.06349
Opus 5	$0.00032	$0.03174
Sonnet 5	$0.00013	$0.01270
Haiku 4.5	$0.00006	$0.00635

Measured 11d ago against content hash 7b4b6baab745, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

create-eval-from-docs 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 11d 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.

plugins/kubevirt/skills/create-eval-from-docs/SKILL.md · 599 lines

How it starts

The opening of the file, as written. The whole thing — 599 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Eval from Docs

This skill provides the detailed implementation logic for the /kubevirt:create-eval-from-docs command. It covers how to read user-guide documentation, extract actionable workflows, map them to available MCP tools, and generate MCPChecker evaluation task files.

When to Use This Skill

When executing the /kubevirt:create-eval-from-docs command
When a user wants to generate MCPChecker evaluation tasks from KubeVirt user-guide documentation
When expanding eval coverage for the kubernetes-mcp-server kubevirt toolset

Prerequisites

KubeVirt user-guide repo: Must be available as a working directory. Default path: look for a directory containing docs/compute/, docs/storage/, docs/network/ with a mkdocs.yml at root. If not found, ask the user for the path.
kubernetes-mcp-server repo: Must be available as a working directory. Default path: look for a directory containing evals/tasks/kubevirt/. If not found, ask the user for the path.
kubectl: Must be installed (which kubectl) for generating verify scripts that validate cluster state.

Repository Layout Context

User-Guide Documentation Structure

docs/
├── compute/          # Live migration, CPU/memory hotplug, run strategies, NUMA, hugepages, etc.
├── storage/          # Disks, volumes, hotplug, snapshots, clones, CDI
├── network/          # Interfaces, multus, service mesh, network policies
├── user_workloads/   # VM lifecycle, instancetypes, templates, preferences
├── cluster_admin/    # Installation, upgrades, feature gates, migration policies
└── debug_virt_stack/ # Debugging, logging, virsh commands

Existing Eval Task Structure

evals/tasks/kubevirt/
├── helpers/
│   └── verify-vm.sh           # Reusable verification functions
├── create-vm-basic/
│   └── task.yaml              # v1alpha2 format
├── troubleshoot-vm/
│   └── task.yaml
└── ...                        # 12 tasks total

Available MCP Tools

KubeVirt toolset (dedicated tools):

vm_create - Create VM with instancetype/preference/workload params
vm_clone - Clone VM via VirtualMachineClone resource
vm_lifecycle - Start, stop, or restart a VM (changes runStrategy)

Read the full file on GitHub · 599 lines

Changes

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.

11d ago First seen · 599 lines · 64 tokens per session scan A 7b4b6baab745

Subscribe to this mod's changes

create-eval-from-docs is a skill published in the GitHub repository lyarwood/kubevirt-ai-helpers (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 64 tokens to every session and 6,349 once invoked, about $0.0003 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 2026-08-31.

Building agents Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

create-eval-from-docs