← 返回 Skills 市场
Self Improving Agent
作者
mike5230Odense
· GitHub ↗
· v1.0.0
17554
总下载
7
收藏
301
当前安装
1
版本数
在 OpenClaw 中安装
/install self-improvement
功能描述
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
安全使用建议
Install only if you want a persistent agent-memory workflow. Before enabling hooks, prefer project-level and narrowly matched hooks over global empty-match hooks, review the scripts, and keep learning files out of version control unless the team intentionally wants reviewed shared memory. Log short sanitized lessons, not raw transcripts, secrets, tokens, customer data, private prompts, full command output, or sensitive environment details.
能力评估
Purpose & Capability
The self-improvement purpose coherently matches markdown learning logs, reminder hooks, OpenClaw workspace memory, and a local skill-scaffolding helper; no artifact evidence shows exfiltration, credential theft, destructive behavior, or hidden unrelated capability.
Instruction Scope
The instructions say to automatically log common user corrections, feature requests, knowledge gaps, errors, full context, user context, raw error output, and input parameters into durable files, but they do not clearly require consent, minimization, or redaction of secrets, private user text, proprietary context, or sensitive command output.
Install Mechanism
Installation and hooks are disclosed and opt-in, and the reviewed hook scripts mostly emit reminders; however the example hook configurations use empty matchers and include a global user-level setup, which can run local command hooks on every prompt across unrelated work once enabled.
Credentials
Local markdown logging is proportionate to the stated goal, but the templates and examples can preserve sensitive environment details, internal paths, command inputs, API behavior, and user context in files that may later be committed, injected into prompts, or shared.
Persistence & Privilege
The skill explicitly creates durable learning files, promotes lessons into future agent context files such as AGENTS.md, CLAUDE.md, SOUL.md, and TOOLS.md, and documents cross-session transcript reading, message sending, and sub-agent spawning without strong retention or access-boundary guidance.
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 self-improvement - 安装完成后，直接呼叫该 Skill 的名称或使用
/self-improvement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
v1.0.0
Self-Improvement Skill v1.0.0 — initial release
- Provides a structured system for logging errors, learnings, and feature requests to markdown files.
- Defines clear actions and file formats for different scenarios: errors, user corrections, feature requests, outdated knowledge, and best practices.
- Integrates with the OpenClaw platform for automatic skill loading, memory management, and inter-session communication.
- Offers guidelines for promoting important or broadly applicable learnings to project-level files like AGENTS.md, SOUL.md, and TOOLS.md.
- Includes setup instructions for both OpenClaw and generic agent-based environments.
元数据
常见问题
Self Improving Agent 是什么？
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 17554 次。
如何安装 Self Improving Agent？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install self-improvement」即可一键安装，无需额外配置。
Self Improving Agent 是免费的吗？
是的，Self Improving Agent 完全免费（开源免费），可自由下载、安装和使用。
Self Improving Agent 支持哪些平台？
Self Improving Agent 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 Self Improving Agent？
由 mike5230Odense（@mike5230odense）开发并维护，当前版本 v1.0.0。
推荐 Skills