AGENT SKILL

review-pr-2x

Run review-pr twice and monitor PR checks with gh pr checks --watch.

License 许可
MIT
最近更新
2026-11-15
Stars
★ 0
Forks
0

01 前言 Front Matter

name
review-pr-2x
license
MIT
metadata
{ "author": "local", "version": "2.0" }
description
Run review-pr twice and monitor PR checks with gh pr checks --watch.
compatibility
Requires GitHub CLI (gh) and the review-pr skill logic.

03 SKILL.md 正文

Run review-pr twice, with one 5-minute interval between the two rounds to catch delayed review feedback.

Input: Optional PR number or URL (e.g., review-pr-2x 19). If omitted, infer from current branch using the same rule as review-pr.

Execution Plan

  1. Resolve target PR (same logic as review-pr).
  2. Execute 2 rounds of the review/fix/check cycle.
  3. Between round 1 and round 2: first wait for CI to finish, then wait 5 minutes for delayed review comments.

Per Round (i = 1..2)

  • Before the round: verify PR state; if the PR is merged or closed, stop and report the final summary.
  • Announce: Round i/2 start.
  • Execute the full review-pr workflow for the same PR:
    • collect actionable review comments (including inline file/line comments)
    • monitor CI/check status using gh pr checks <pr> --watch and inspect failed logs if needed
    • implement fixes
    • check for conflicting files before commit/push:
      git diff --name-only --diff-filter=U
      rg -n "^(<<<<<<<|=======|>>>>>>>)" .
      
      • if conflicts are found, resolve all conflicting files first
    • push changes
    • re-monitor PR status with gh pr checks <pr> --watch
  • Announce: Round i/2 done with concise summary.

Interval (between round 1 and round 2)

  1. First, wait for CI to complete:
    gh pr checks <pr> --watch
    
  2. Then pause 5 minutes to catch delayed review comments:
    sleep 300
    

Report that the workflow is intentionally paused for the polling interval.

Completion Output

Provide a final summary including:

  • total rounds executed (and whether the run stopped early because the PR was merged/closed)
  • commits created per round (if any)
  • latest review status
  • latest CI status
  • conflict-file check results by round
  • remaining blockers (if any)

Guardrails

  • Use the same PR for all rounds.
  • If no actionable feedback and CI is green in a round, still continue to the next scheduled round.
  • Conflict-file checks are mandatory before each round's commit/push.
  • If hard-blocked (permission/network/tool outage), report immediately and stop.

04 同仓库更多 Skills

cookeyholder
cookeyholder/using-ai-skills

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

测试与质量前端开发
★ 0
cookeyholder
cookeyholder/using-ai-skills

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 0
cookeyholder
cookeyholder/using-ai-skills

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

视觉设计
★ 0
cookeyholder
cookeyholder/using-ai-skills

slack-gif-creator

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

邮件与沟通图像与多媒体
★ 0
cookeyholder
cookeyholder/using-ai-skills

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Skill与智能体开发
★ 0
cookeyholder
cookeyholder/using-ai-skills

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Skill与智能体开发
★ 0