Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub · Developer Tools
Vibe Coding Best Practices v3.0
Provides a comprehensive AI-assisted development workflow with PLAN/ACT separation, multi-agent collaboration, fault recovery, and security code review best...
skill openclawclawhub Free
Provides a comprehensive AI-assisted development workflow with PLAN/ACT separation, multi-agent collaboration, fault recovery, and security code review best...
⬇ 0 downloads ★ 0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- references/01-quickstart.md, references/02-single-agent.md, references/03-multi-agent.md, references/04-emergency.md, references/05-security-qa.md, references/06-tools.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.0
Provenance
- Publisher
- russellfei
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Vibe Coding 最佳实践指南
vibe-3k = Vibe Coding Best Practices v3.0（3K 行级全流程指南） 你是主厨，AI 是厨房团队。你设计菜单、品尝每道菜，但不亲自切每根胡萝卜。
10 条核心原则
先想后 prompt — 5 分钟思考省 5 小时迭代 Plan ≠ Act — 分离规划和执行，用不同模型/session Design Doc 是枢纽 — 压缩上下文，可审查，可交接 小步提交 — 每个功能点一个 commit，Git 是安全网 新功能新 session — 上下文溢出是第一杀手 循环修复就回退 — 3 次修不好 = 方案有问题 安全不能 vibe — Auth/支付/数据必须人工 review LOG.md 是续命药 — 记录进度，任何时候都能恢复 多 Agent 分工明确 — PM 规划、Dev 执行、QA 审查 验收有 checklist — 自动化检查 + 人工确认
参考文档（按需加载）
文件内容何时读取references/01-quickstart.md核心概念 + 项目启动 + 规则文件 + 4 套项目模板启动新项目时references/02-single-agent.mdPLAN/ACT 分离 + Design Doc + Prompt 技巧 + 上下文管理单人 AI 开发时references/03-multi-agent.md多 Agent 协作 + Git Worktree 并行 + Race Condition 防护 + 时间戳规范多 Agent 协作时references/04-emergency.md故障分级 + 恢复 SOP + 灾难恢复 + >24h 长任务管理出问题或长任务时references/05-security-qa.md安全红线 + 验收 Checklist + 自动化验收脚本安全审查/验收时references/06-tools.md工具推荐（Claude Code / Kimi / Antigravity / OpenClaw）工具选型时
启动前 5 分钟清单
在碰 AI 之前写下： 解决什么问题？ 目标用户？ 核心功能（P0/P1/P2） 技术栈约束 什么叫「完成」？
PLAN/ACT 分离（最重要）
PLAN 阶段: 大上下文 thinking 模型（Gemini / OpenAI / Claude 最新旗舰）只分析、只规划 → 输出 Design Doc ACT 阶段: 新 session + 快速模型（各厂商轻量级模型）→ 读 Design Doc → 逐步实现 永远不要在同一个 session 里做 Plan 和 Act
故障快速参考
信号动作单个错误，信息清晰粘贴完整 stack trace → AI 修来回改同一文件 3+ 次🛑 停！git stash → 换模型/策略多处报错，越修越乱git reset --hard <stable> → 重新 PlanAI 重复/遗忘/答非所问关 session → LOG.md → 新 session 接力
安全红线
Auth、支付、数据库 Schema、用户数据、API Key — 绝不 vibe，必须人工逐行 review。
实际案例
使用中的真实案例记录在 memory/tasks/ 目录。每次完成 Vibe Coding 项目都会生成 task 记录，包含执行过程、踩坑和成果。
工具信息时效性
⚠️ 工具相关信息（Kimi Agent Swarm、Antigravity Kit 等）截至 2026-02，具体能力和 API 以官方文档为准。
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
6 Docs
- references/01-quickstart.md
- references/02-single-agent.md
- references/03-multi-agent.md
- references/04-emergency.md
- references/05-security-qa.md
- references/06-tools.md