一键导入
workflow-gerrit-fix
Workflow for automatically fixing errors or addressing comments on a Gerrit CL requested by the user.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Workflow for automatically fixing errors or addressing comments on a Gerrit CL requested by the user.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
| name | workflow_gerrit_fix |
| description | Workflow for automatically fixing errors or addressing comments on a Gerrit CL requested by the user. |
Use this skill when the user asks to "fix the errors on Gerrit issue X" or "address reviewer comments on CL X" or similar requests targeting a specific Gerrit Change List (CL).
gerrit_cq (from v8-utils) to check Commit Queue
status.gerrit_get_presubmit_errors (from pndMcp) to
fetch detailed presubmit results.gerrit_comments or gerrit_list_change_comments to read
reviewer feedback or robot comments. This is critical when the goal is to
address reviewer comments.agents/scripts/create_worktree.sh <cl_id> for the CL to avoid polluting the
main workspace.git cl patch X).origin/main to ensure it builds against the
latest code.self subagent with full tool
access.If the user says "fix errors on CL 12345":
gerrit_cq for CL 12345.v8_linux64_rel failed with failing tests.worktrees/cl-12345 and checkout CL.If the user says "address comments on CL 12345":
gerrit_comments for CL 12345.src/objects/lookup.cc.worktrees/cl-12345 and checkout CL.Managing and querying Perfetto traces using the trace_processor MCP server.
Documentation for conditional testing in V8 using gm.py.
Guides the initial analysis and impact assessment of a V8 security report, strictly excluding implementation or fixing.
Executes and interprets V8 tests. Use when running unittests, cctest, or mjsunit, or when debugging test failures. Do not use for building.
Manages git task isolation and environment setup in V8. Use at the start of any new task or bug fix. Do not use for general C++ editing.
Workflow for issue-based debugging in V8. Use when tasked with debugging a specific issue, usually associated with a Buganizer ID or a specific reproduction script. Do not use for performance regressions.