Skip to content
Agentmart
Submit a tool

autopilot

Activates full autonomous execution — from idea to working, verified code

Skill by TheTrustedAdvisor

IndexedMIT★ 7
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/thetrustedadvisor-autopilot

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Activates full autonomous execution — from idea to working, verified code

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/autopilot

What's inside

Skill name
autopilot
Description
Activates full autonomous execution — from idea to working, verified code
License
MIT
Instructions
37 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

## Activation

This skill activates the **autopilot agent** for full lifecycle execution.

The autopilot agent will:
- Expand vague requirements into concrete acceptance criteria
- Create a structured plan with testable criteria
- Implement code changes (parallel when independent)
- Run build, typecheck, tests as verification
- Review for security and code quality
- Persist all artifacts to `.omg/` directories

## Trigger Keywords

autopilot, autonomous, build me, create me, make me, full auto, handle it all

## Plan Discovery

Before starting fresh, autopilot checks for existing work:
1. `store_memory` key `omg:active-plan` — skip to execution
2. `store_memory` key `omg:active-spec` — skip to planning
3. `.omg/plans/` and `.omg/research/` via `glob`

## Quality Contract

- Every claim backed by evidence (fresh test output)
- Smallest viable change (no scope creep)
- Same failure 3x → stop and report
- All reviewers must approve before completion

## Examples

Good: "autopilot: build a REST API for bookstore inventory with CRUD using TypeScript"
Good: "build me a CLI tool that tracks daily habits with streak counting"
Bad: "fix the bug in the login page" → use debug or @omg:executor instead

From TheTrustedAdvisor/omg, MIT.

More from TheTrustedAdvisor/omg

Signals

Stars
7
Forks
1
Open issues
0
Last commit (this folder)
Apr 7, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from TheTrustedAdvisor

Cite this page

autopilot skill. Agent Mart. https://agentmart.dev/skills/thetrustedadvisor-autopilot (last updated 2026-10-24)