---
name: automate-me
description: "Capture explicitly requested working preferences in a reusable local skill, using the current conversation or user-selected examples."
---

# Automate me

Follow the consuming project's instructions and requested scope; use the
[portable defaults](../orbyn-workflow/references/project-policy.md) only where guidance is missing.

Locate an existing skill for the requested workflow before creating one. Use
only the conversation or records the user selected; do not mine unrelated sessions.
Distinguish explicit preferences from inferred patterns and one-off constraints.

Preserve useful defaults, tool permissions, task scope and existing authorization.
Use the available skill-authoring guidance, concise descriptions and references
loaded only when needed. Prefer a small edit over another overlapping mode skill.
Choose a repository path for shared conventions and a personal path only when
requested. Do not change global models, memory, connectors or schedules as a
side effect. Show the resulting file and the preferences it encodes.

## Preference → maintained owner

If the user repeatedly requests export readback, place that check in the export owner when they ask to encode it. Preserve what the preference actually covers: a PDF readback rule should not require application builds for a prose edit. Return the changed owner and an example of when it should not activate.

## Operational method

Use the [local operating method](references/operating-method.md) for the execution
sequence, concrete failure case, expected result and stopping condition. It is
Orbyn-authored guidance; historical source notices remain in provenance.

For conflicting selected examples, prefer an explicit current choice over old
inference, retain contradictory evidence and label weak confidence. One temporary
platform exception does not establish a general preference. A repeated explicit
correction can support a minimal scoped owner edit; missing artifact evidence or
unresolved conflict can justify no change. No automatic historical corpus mining.