← 返回
未分类 中文

Conflict Manager

Provides HTTP endpoints for scanning Git repository conflicts across multiple branches and applying AI‑suggested resolutions. Use when the dashboard needs to...
提供 HTTP 端点,用于扫描跨多个分支的 Git 仓库冲突,并应用 AI 建议的解决方案。适用于仪表盘需要...
brajesh9373
未分类 clawhub v1.0.0 1 版本 99447.5 Key: 无需
★ 0
Stars
📥 180
下载
💾 0
安装
1
版本
#latest

概述

Conflict Manager Skill

Overview

This skill implements two public HTTP APIs that the Integration‑Hell‑Dashboard can call:

  1. POST /conflict-scan – Accepts a requirementId (or any custom payload) and returns a list of conflicted files per repository/branch pair.
  2. POST /conflict-resolve – Accepts a resolution payload (repo, source/target branches, optional patch or command list) and attempts a dry‑run merge followed by the actual merge if dryRun is false.

Both endpoints publish WebSocket events so the UI can react in real‑time.

Permissions

  • repo:read – required to list branches and fetch commits.
  • repo:write – required to perform merges and push changes.

Resources

  • scripts/index.js – Core implementation of the two endpoints.

The skill is intentionally minimal; you can extend it with proper Git operations, authentication handling, and smarter AI integration later.

版本历史

共 1 个版本

  • v1.0.0 当前
    2026-05-20 06:13 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-intelligence

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,364 📥 319,268
ai-intelligence

self-improving agent

pskoett
捕获经验教训、错误及修正内容,以实现持续改进。适用于以下场景:(1)命令或操作意外失败;(2)用户纠正Claude(如“不,那不对……”“实际上……”);(3)用户请求的功能不存在;(4)外部API或工具出现故障;(5)Claude发现自身
★ 4,065 📥 802,064
security-compliance

Skill Vetter

spclaudehome
AI智能体技能安全预审工具。安装ClawdHub、GitHub等来源技能前,检查风险信号、权限范围及可疑模式。
★ 1,219 📥 267,034