quality-flywheel

quality-flywheel is a skill for Claude Code, Codex from GoogleCloudPlatform/vertex-ai-samples. It costs 128 tokens per session (1,887 once invoked), scanned A, original, Apache-2.0.

A toolkit for testing and improving generative-AI models and agents with Google's GenAI Evaluation SDK. It can create evaluation data, run measures such as rubric-based checks and code execution, and examine the results.

In plain words
What is it for?
Use it to build datasets from synthetic examples or session traces, configure evaluation metrics, run evaluations, analyze failures, and guide improvements.
Why use it?
It replaces informal judging with repeatable tests against datasets or recorded agent sessions. The results help identify recurring quality problems and suggest code or prompt changes.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/googlecloudplatform/vertex-ai-samples/quality-flywheel
Any agent
npx skills add GoogleCloudPlatform/vertex-ai-samples --skill quality-flywheel
Clone the repo
git clone --depth 1 https://github.com/GoogleCloudPlatform/vertex-ai-samples

Made for: Claude Code, Codex.

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.

agentmods badge for quality-flywheel

README.md
[![agentmods](https://agentmods.dev/badge/skills/googlecloudplatform/vertex-ai-samples/quality-flywheel.svg)](https://agentmods.dev/skills/googlecloudplatform/vertex-ai-samples/quality-flywheel)
Your own site
<a href="https://agentmods.dev/skills/googlecloudplatform/vertex-ai-samples/quality-flywheel"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/vertex-ai-samples/quality-flywheel.svg" alt="Measured on agentmods" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,887 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00128 $0.01887
Opus 5 $0.00064 $0.00944
Sonnet 5 $0.00026 $0.00377
Haiku 4.5 $0.00013 $0.00189

Measured 4d ago against content hash 6d059789b5dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quality-flywheel 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 4d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/generate_eval_code.py, scripts/parse_adk_traces.py, scripts/validate_dataset.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/quality-flywheel/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Flywheel Skill

You are the Quality Flywheel — an expert in GenAI evaluation. Your mission is to help users evaluate and iteratively improve their GenAI models and agents using the Google GenAI Evaluation SDK (google.genai / vertexai).

When to use this skill

  • Evaluating GenAI agents or models using client.evals.evaluate()
  • Creating synthetic datasets or ingesting session traces
  • Selecting, configuring, or writing custom evaluation metrics
  • Analyzing rubric verdicts and loss patterns
  • Suggesting concrete code/prompt improvements based on eval results

Workflow

Follow this workflow sequentially when assisting users:

Step 0. Setup & Project Initialization

  • CRITICAL: Before generating or executing any scripts, obtain the GCP Project ID and Location (e.g., global, us-central1). Check environment variables first (GOOGLE_CLOUD_PROJECT, GOOGLE_CLOUD_LOCATION). If not found, ask the user.
  • Newer Gemini models may only be available in the global region — use location="global" if the user wants to use them.

Step 1. Dataset Creation & Formatting

  • Parse Inputs: Convert user-provided descriptions into the SDK formats (EvalCase, AgentData, ConversationTurn, EvaluationDataset). See references/dataset_schema.md for the full type hierarchy and examples.

  • Single-Turn (Model Eval): Create EvalCase objects with prompt strings. Use client.evals.run_inference(model=..., src=dataset) to populate model responses if needed.

  • Multi-Turn (Agent Eval): If the user wants to test a multi-turn agent but lacks data:

    1. Generate Scenarios: Use client.evals.generate_user_scenarios with a UserScenarioGenerationConfig specifying user_scenario_count, simulation_instruction, and environment_data.
    2. Run Inference: Use client.evals.run_inference with a user_simulator_config to simulate interactions up to max_turn.

Read the full file on GitHub · 193 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 4d ago First seen · 193 lines · 128 tokens per session scan A 6d059789b5dc

Subscribe to this mod's changes

quality-flywheel is a skill published in the GitHub repository GoogleCloudPlatform/vertex-ai-samples (784 stars, last pushed 2d ago), licensed Apache-2.0. It adds 128 tokens to every session and 1,887 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

retro-marimo-pair

Session retrospective for improving marimo-pair and marimo.codemode. Use when the user wants to analyze friction from a pairing session, identify what went wrong, and brainstorm improvements to the skill docs or the underlying API. Trigger on: "retro", "what went wrong", "improve the skill", "session review"…

marimo-team/marimo-pair · 84 tokens

marimo-pair

Drive a live marimo notebook as a workspace: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes. Use when the user wants to start a marimo notebook or pair on an active marimo session.

marimo-team/marimo-pair · 56 tokens

review-prs

Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…

googleapis/mcp-toolbox · 162 tokens

stale-sweep

Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…

googleapis/mcp-toolbox · 159 tokens

zeroclaw

Help users operate and interact with their ZeroClaw agent instance — through both the CLI (zeroclaw commands) and the REST/WebSocket gateway API. Use this skill whenever the user wants to: send messages to ZeroClaw, manage memory or cron jobs, check system status, configure channels or providers, hit the gateway API…

zeroclaw-labs/zeroclaw · 167 tokens

triage-issues

Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…

googleapis/mcp-toolbox · 164 tokens