Token导航 LogoToken导航

Agent Skill · 研究检索

skill-state-manager(技能状态管理器)

skill-state-manager 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 OpenClaw 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

skill-state-manager 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 34,766。

总安装 2,186周安装 92GitHub Stars 1下载 765核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
0.0.1

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:skill-state-manager(技能状态管理器)
来源仓库:https://github.com/qipengguo/skill-state-manager
安装命令:
openclaw skills install skill-state-manager
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install skill-state-manager

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

管理 API 密钥和其他工具的状态持久性的元技能。每当工具需要身份验证或因 401/403 错误而失败时调用。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install skill-state-manager;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

skill-state-manager 怎么安装?

在终端执行 openclaw skills install skill-state-manager。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

skill-state-manager 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

skill-state-manager 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

skill-state-manager 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

skill-state-manager 用的人多吗?

公开数据是累计安装 2,186 次,近一周安装 92 次,下载 765 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

skill-state-manager 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
skill-state-manager

技能状态管理器 · 本页

2,1861接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
skill-state-manager
description
A Meta Skill that manages API keys and state persistence for other tools. Invoke whenever a tool requires authentication or fails with 401/403 errors.

🛡️ Skill State Manager (SSM)

Say goodbye to manual config editing and endless repetitive token pasting!

The Skill State Manager (SSM) is a revolutionary "Meta Skill" designed for modern AI assistants (like Claude Code, Codex). It acts as your invisible, native auth butler. Whenever a third-party tool (like Notion, Jira, or a custom API) needs a secret or API key, SSM automatically steps in.

No more hunting down hidden .env files. No more hardcoded secrets. Just a seamless, native conversational experience—if a tool needs an auth token, your AI will simply ask you for it *once*, save it securely, and then immediately resume your workflow.


🌟 Why You'll Love It

  • 🗣️ Native Conversational Flow: You never have to leave the chat. If a key is missing, the AI pauses the tool, politely asks you for the secret in the chat, and saves it.
  • 🚫 Zero Config Setup: Stop writing boilerplate auth logic for every new tool you create. Let SSM handle the prompting and persistence.
  • 🤝 Platform Aware: It automatically adapts to your CLI environment (Claude Code, Codex), storing states cleanly in ~/.ai-skills-state/.

🤖 Instructions for the AI Assistant

As an AI assistant, you are equipped with the "Skill State Manager" (SSM) rules to handle authentication and state persistence for custom third-party tools/skills.

WHEN TO TRIGGER SSM:

  • DO NOT trigger for built-in tools (e.g., shell, file read/write, search) or public tools without authentication.
  • TRIGGER SSM when you are about to use a custom tool that interacts with third-party authenticated services (e.g., Jira, Notion, Custom APIs) OR when a tool explicitly requires secrets.
  • TRIGGER SSM if a tool execution fails with a 401/403 authentication error.

SSM WORKFLOW:

When triggered, you MUST follow these exact steps sequentially:

  1. Detect Platform: Determine which AI platform you are currently running in. Your behavior must adapt based on this detection:

- Claude Code: Uses a global storage approach (~/.claude/skills-state/). - Codex / Other CLI: Uses a generic global storage approach (~/.ai-skills-state/).

  1. Check Storage: Look for the credentials in the designated local directory based on the detected platform:

- If Claude Code: check ~/.claude/skills-state/<tool-name>.json - If Codex / Other: check ~/.ai-skills-state/<tool-name>.json

  1. Prompt User (If Missing):

- If the required credentials (e.g., API keys, tokens) are not found in the storage, STOP the tool execution. - Ask the user politely for the required information via a chat message. - *Example*: "The current operation requires the Notion API, but your API key was not found. Could you please provide it? I will save it locally in ~/.claude/skills-state/notion-skill.json (or the appropriate path) for future use."

  1. Save State:

- Once the user provides the information in the chat, use the Write tool to save it into the JSON file resolved in Step 1. - For Claude Code, write to ~/.claude/skills-state/<tool-name>.json. - For Codex / Other CLI, write to ~/.ai-skills-state/<tool-name>.json. - Ensure the content is stored as valid JSON. - Proceed with the actual tool execution using the newly acquired credentials.


🛠️ Usage Example

User: "Can you query my Jira board for high-priority bugs?" AI (Internal Thought): *I need to use the Jira tool. Let me check ~/.ai-skills-state/jira-tool.json.* AI (Internal Thought): *File not found. Triggering SSM.* AI: "To query your Jira board, I need your Jira API token and URL. Could you please provide them here? I'll save them locally in ~/.ai-skills-state/jira-tool.json so you won't have to enter them again." User: "Sure, my token is xyz123 and url is https://myorg.atlassian.net." AI (Internal Thought): *Writes data to ~/.ai-skills-state/jira-tool.json using the Write tool.* AI: "Thanks! I've saved your credentials. Now, let's look at those high-priority bugs..." *(Proceeds to execute Jira query)*

平台分布

OpenClaw

85.3%
按下载量换算653

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills