Agent Skills
› spacedriveapp/spacebot
› review-fix-loop
review-fix-loop
GitHub用于处理代码审查反馈,通过解析问题严重性、建立闭环表格并实施最小化修复,实现每个发现与代码变更及证据的严格对应。结合分层验证和重跑控制,旨在减少往返沟通,高效关闭审查轮次。
Trigger Scenarios
address review feedback
fix PR comments
close findings
respond to reviewer notes
reduce review churn
Install
npx skills add spacedriveapp/spacebot --skill review-fix-loop -g -y
SKILL.md
Frontmatter
{
"name": "review-fix-loop",
"description": "This skill should be used when the user asks to \"address review feedback\", \"fix PR comments\", \"close findings\", \"respond to reviewer notes\", or \"reduce review churn\". Enforces a finding-to-evidence closure loop for every review round."
}
Review Fix Loop
Goal
Close review rounds with minimal back-and-forth by mapping every finding to a code change and proof.
Execution Loop
- Parse findings into
P1,P2,P3. - Build a closure table before editing.
- Implement the smallest coherent fix batch.
- Run targeted verification.
- Update closure table with outcomes.
- Run broader gate checks.
Closure Table
Use one row per finding:
| Finding | Severity | Owned files | Planned change | Verification command | Result |
|---|
Re-Run Control
- If the same command fails twice, stop rerunning.
- Isolate a smaller reproduction command.
- Patch the smallest likely cause.
- Re-run narrow verification before broad checks.
Verification Ladder
- Start narrow: unit/module behavior checks for touched paths.
- Continue medium: compile/lint/type checks for touched surfaces.
- End broad: repository gate commands.
Handoff Requirements
- Findings closed
- Commands executed
- Pass/fail evidence per finding
- Remaining open findings with rationale
- Residual risk
Version History
- ac52277 Current 2026-07-05 14:56


