← 返回 Skills 市场
Moltbot Best Practices
作者
Next Frontier AI
· GitHub ↗
· v1.1.3
5036
总下载
20
收藏
28
当前安装
5
版本数
在 OpenClaw 中安装
/install moltbot-best-practices
功能描述
Best practices for AI agents - Cursor, Claude, ChatGPT, Copilot. Avoid common mistakes. Confirms before executing, drafts before publishing. Vibe-coding essential.
安全使用建议
This skill is reasonable to install if you want agent-behavior guidance. Before applying the suggested OpenClaw memory configuration, decide whether you are comfortable with agents saving and searching past session context, especially if your sessions include private, sensitive, or stale information.
功能分析
Type: OpenClaw Skill
Name: moltbot-best-practices
Version: 1.1.3
The skill bundle consists entirely of documentation and configuration advice aimed at improving the behavior and reliability of AI agents. The `SKILL.md` file, treated as a prompt injection surface, contains instructions for the agent to be more transparent, confirm actions, seek approval, and stop when commanded, all of which are security-enhancing behaviors. The recommended configuration changes are for improving agent memory and context handling, not for malicious purposes. There is no executable code, data exfiltration, or any other indicators of malicious intent or significant vulnerabilities.
能力评估
Purpose & Capability
The skill's stated purpose is agent behavior guidance, and the artifacts align with that purpose by encouraging confirmation, approval before publishing, stopping on user command, and limiting unnecessary background work. The optional memory configuration is related to agent continuity but has privacy implications.
Instruction Scope
Runtime instructions mostly constrain agent behavior and increase user control; no hidden prompt override, credential handling, data exfiltration, or unrelated tool use was found.
Install Mechanism
The package contains only SKILL.md, README.md, and package.json with no scripts, dependencies, or executable files. The install examples are slightly inconsistent between README and SKILL.md, but that appears to be documentation inconsistency rather than suspicious behavior.
Credentials
The skill does not request environment variables, credentials, network authority, or local file access. Its recommended OpenClaw config enables memory and session search, which is user-directed but can expose past context to future agent work.
Persistence & Privilege
No autonomous persistence mechanism is installed by the package, but the recommended memoryFlush and sessionMemory settings would intentionally persist and reuse context across sessions if the user applies them.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install moltbot-best-practices - 安装完成后，直接呼叫该 Skill 的名称或使用
/moltbot-best-practices触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.1.3
- Skill renamed from "moltbot, openclaw-best-practices" to "moltbot-best-practices"
- Description and keywords updated for clarity and broader tool coverage (now mentions ChatGPT, Copilot, GitHub Copilot, developer/dev tools, TypeScript, LLM)
- Minor text and formatting tweaks for conciseness and consistency in SKILL.md
- Version bumped to 1.1.3
v1.1.2
Rebranded to OpenClaw
v1.1.1
SEO update: added claude-code, copilot, agentic keywords
v1.1.0
Added recommended config for memory flush and session memory search
v1.0.0
- Initial release of "moltbot-best-practices": a guide to help AI agents avoid common mistakes and adopt proven best practices.
- Covers 15 key rules including: confirming tasks before action, never publishing without approval, stopping immediately when told, avoiding over-automation, and processing messages in order.
- Provides quick reference and anti-pattern lists for easy adoption.
- Originates from real-world failures to help agents act more reliably and align with user expectations.
元数据
常见问题
Moltbot Best Practices 是什么？
Best practices for AI agents - Cursor, Claude, ChatGPT, Copilot. Avoid common mistakes. Confirms before executing, drafts before publishing. Vibe-coding essential. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 5036 次。
如何安装 Moltbot Best Practices？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install moltbot-best-practices」即可一键安装，无需额外配置。
Moltbot Best Practices 是免费的吗？
是的，Moltbot Best Practices 完全免费（开源免费），可自由下载、安装和使用。
Moltbot Best Practices 支持哪些平台？
Moltbot Best Practices 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Moltbot Best Practices？
由 Next Frontier AI（@nextfrontierbuilds）开发并维护，当前版本 v1.1.3。
推荐 Skills