원클릭으로
improve-branch
Manual-only workflow for proposing one evidence-backed, high-leverage improvement to the current branch, PR, or issue goal.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Manual-only workflow for proposing one evidence-backed, high-leverage improvement to the current branch, PR, or issue goal.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | improve-branch |
| description | Manual-only workflow for proposing one evidence-backed, high-leverage improvement to the current branch, PR, or issue goal. |
| disable-model-invocation | true |
What is the single most compelling, high-leverage addition you could make toward the goal of the current branch (and its PR/issue, when they exist)?
Only propose it if it is genuinely compelling. It is fine to refrain when you have no strong suggestion — no change beats a marginal one.
Use when:
/improve-branchDo not use:
~/.agents/skills/improve-codebase/SKILL.md~/.agents/skills/improve-local/SKILL.md~/.agents/skills/improve-targeted/SKILL.mdFirst actions:
Selection rules:
Output:
Compatibility impact: none | removed (requested) | kept existing (requested).Use when running autonomous verified tasks or spawning, steering, inspecting, resuming, or replanning Ralph multi-agent runs via ,ralph go, tmux dashboards, or role attach.
Manual-only workflow for proposing one evidence-backed, high-leverage improvement to the current codebase.
Manual-only workflow for proposing one evidence-backed, high-leverage improvement to the local changes.
Manual-only workflow for proposing one evidence-backed, high-leverage improvement to a targeted part of the codebase.
Interview the user until you have 100% confidence about what they actually want.