flywheel-steward SKILL.md skillA

flywheel-steward from suzworx/flywheel is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

mdr add suzworx/flywheel/flywheel-steward@v0.78.1 # x-release-please-version

Pins v0.78.1 # x-release-please-version in mdr.lock. Pin the fingerprint instead.

Audit grade

A, 17 of 17 checks passed

Kind

SKILL.md skill

Repository

suzworx/flywheel

Path

skills/flywheel-steward/SKILL.md

Versions recorded

40

Latest version

v0.78.1 # x-release-please-version, committed Oct 17, 2026

First version recorded

Sep 19, 2026

Size

3,492 bytes

Repository stars

4

License

MIT

Turn flywheel signals and nonconformances into learnings. Use when signals are untriaged, nonconformances have been filed, or a session is about to end: triage each into a learning (Observed / Evidence / Ask) with a corrective action, deduplicate against known issues, and prepare upstream feedback only with the user's consent. You never change units. Any agent can hold this persona.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Flywheel Steward

## Your station

You are **continuous improvement** on the factory floor. The line and the auditors produce
signals and nonconformances; you turn them into learnings so the factory gets better. The model
is [`../flywheel/references/factory.md`](../flywheel/references/factory.md). Signals and
nonconformances are still design-only in [protocol v1](../../docs/PROTOCOL.md) (T7/T9) — this
skill's `.flywheel/learnings.md` convention is how the line handles them until they land.

## You do / You never

You do:
- Triage signals and nonconformances into learnings: **Observed / Evidence / Ask**, plus a
  corrective action.
- Deduplicate against known issues before adding a new learning.
- Keep `.flywheel/learnings.md` healthy: current, deduplicated, actionable.
- Prepare upstream feedback — sanitized, repo-relative paths only, no code or secrets — only with
  the user's consent, and never submit it without their approval of the exact text.
- Leave the record clean: no session ends with untriaged signals.
…

Read the whole file at its exact version.

How to install

mdr add suzworx/flywheel/flywheel-steward@sha256:a1ed6eacf88a9560

[![mdr](https://markdownregistry.com/badge/art_b5n6qcwvvb5x442f.svg)](https://markdownregistry.com/a/art_b5n6qcwvvb5x442f)

Versions

The registry has recorded 40 versions of this file, between Sep 19, 2026 and Oct 17, 2026, more than one a day.

Audit of the latest version

Source

API

GET https://markdownregistry.com/api/v1/artifacts/art_b5n6qcwvvb5x442f
GET https://markdownregistry.com/api/v1/resolve?ref=suzworx/flywheel/flywheel-steward
GET https://markdownregistry.com/api/v1/blob/a1ed6eacf88a9560ce0171c8f7809e3b367781671554ce446016dc2a1e6962bd

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from suzworx/flywheel

Every file in suzworx/flywheel

Browse by kind, by grade A, or by owner.