About this skill
Autonomously work multiple Project 9 board items in one bounded loop. Each tick dispatches a worktree-isolated sub-agent to implement ONE item and open a PR, autonomously resolves the PR's reviews (CodeRabbit / Copilot / Codex / Claude), classifies the PR's risk, and then auto-merges the low-to-moderate-risk ones (squash) while leaving higher-risk ones for a human — running unbounded by default and stopping on a stagnation circuit-breaker or an empty board. Use when the user says "ボードをループで消化して", "loop the board", "keep working AI-review items until ...", "/beutl-loop". Sub-agent dispatch keeps this orchestrator's context lean across many ticks.
Quick start
- Copy the install prompt. Use the green button above this README.
- Send it to your agent. Paste it into your coding agent’s chat and send.
- Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.
0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1
Content SHA-256: ce2e064b64fe391f57b58610b55613db6aad1ac4114766fd26b459829bb0705c
About this listing
- Category
- General
- Reported license
- MIT
- Listing language (estimated)
- English
- Review status
- Not individually reviewed
- Agent compatibility
- Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.