End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want to define and execute without intervention during planning, when the user asks for autonomous or end-to-end work, or asks to go from idea to done without approval gates.
73 stars
0 votes
0 copies
4 views
Added May 28, 2026
businessgo
Security analysis
A100/100
Scanned September 20, 2026
$npx -y skills add doodledood/manifest-dev --skill auto --agent claude-code
Installs into .claude/skills of the current project.
Are you the author of Auto?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/doodledood-auto)
---
name: auto
description: 'End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want to define and execute without intervention during planning, when the user asks for autonomous or end-to-end work, or asks to go from idea to done without approval gates.'
argument-hint: '<task>'
user-invocable: true
---
Run the flow for the task given or inferable from the conversation; with
neither, halt with usage.
Where shared understanding is missing, invoke figure-out with the task and
`--autonomous`; invoke define; invoke do with the exact Manifest path
define reports. No path → stop and report.
Do not set or print a continuation goal during understanding or definition.
/do owns the completion backstop. Automatic continuation begins at execution;
an interrupted earlier phase must be restarted by the caller.
