# Agentpilot

Prepare and run AgentPilot improvements through one entry.

- Repository: https://github.com/HKUDS/AgentPilot (7784 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add HKUDS/AgentPilot --skill agentpilot -g -a claude-code -y`
Codex: `npx skills add HKUDS/AgentPilot --skill agentpilot -g -a codex -y`
Cursor: `npx skills add HKUDS/AgentPilot --skill agentpilot -g -a cursor -y`
Gemini CLI: `npx skills add HKUDS/AgentPilot --skill agentpilot -g -a gemini-cli -y`

## Description

Prepare and run AgentPilot improvements through one entry. Use when the user requests AgentPilot or iterative improvement with it. The current agent fills missing task/evaluation inputs, then hands a ready environment to the configured AgentPilot runner.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# AgentPilot

Use this one entry to prepare inputs and run the real AgentPilot proposer → worker → eval loop. Read the user's goal, project instructions and relevant existing configuration, preserving their edits and choices. The current agent prepares and operates the runner; the configured engine owns improvement decisions and policy updates.

## Choose the workflow

- **An existing formal run or runnable RSI configuration fits the request:** follow [references/formal.md](references/formal.md) and its existing task, evaluation, worker and budget. Resume its own records when continuing a run. Examples or templates elsewhere in a repository do not by themselves select an experiment.
- **The task, evaluation or runnable setup is missing:** prepare it in the current conversation as described below, then reassess readiness and continue through the same entry. You do not need a session or JSON handoff to begin investigating. A test command alone is not a configured Arena environment.

The installed core launcher, when needed:

```text
{{AGENTPILOT_COMMAND}}
```

## Prepare incomplete inputs

Use your normal reading, editing and command tools. Understand what the project does and inspect relevant tests or failures. Without an explicit task, infer a focused improvement from real project evidence; if the project and conversation cannot establish what to do, ask only for the missing information. A bare invocation is valid, but an empty project is not a reason to invent requirements.

The rest: https://github.com/HKUDS/AgentPilot/blob/HEAD/agentpilot/src/agentpilot/host/skills/agentpilot/SKILL.md