← 返回 Skills 市场
119
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install self-improving-agent-3-0-16
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
This skill appears to do what it says: help capture and promote learnings. Before enabling it, review and decide whether to enable the PostToolUse error-detector hook (it examines CLAUDE_TOOL_OUTPUT and may see sensitive command output). If you enable hooks, prefer per-project (not global) configuration, inspect the scripts, set executable permissions deliberately, and avoid enabling cross-session sharing unless you trust the environment. No credentials are requested by the skill, but be careful not to log secrets when making entries in .learnings; the skill's docs explicitly recommend redacting sensitive content.
功能分析
Type: OpenClaw Skill
Name: self-improving-agent-3-0-16
Version: 1.0.0
The 'self-improvement' skill bundle is designed to help AI agents track errors, corrections, and new insights by logging them to local markdown files. It includes shell scripts (activator.sh, error-detector.sh, extract-skill.sh) and OpenClaw hooks (handler.js) to automate reminders and skill scaffolding. The implementation follows security best practices, such as including path traversal protections in the extraction script and explicit instructions in SKILL.md to avoid logging secrets, tokens, or sensitive environment variables.
能力评估
Purpose & Capability
Name and description match the included assets: README, templates, .learnings templates, hook handlers, and helper scripts all implement capturing learnings, errors, and feature requests and promoting them to workspace files. The provided extract-skill helper, activator, and error-detector support the stated goal and are proportionate.
Instruction Scope
Most runtime instructions stay within scope (create .learnings files, write summarized entries, promote to workspace files). However the error-detector script reads the CLAUDE_TOOL_OUTPUT environment variable (tool output) to detect errors; this env var is not declared in the skill metadata. While the scripts do not transmit that output externally, reading tool output can surface sensitive data if the hook is enabled globally—SKILL.md warns not to log secrets, but the script will inspect raw output unless the user restricts the hook.
Install Mechanism
No install spec or remote downloads. This is an instruction-only skill with included local scripts and hook code. All code is present in the bundle; there are no network fetches or extract steps that would write arbitrary remote artifacts to disk.
Credentials
The skill requests no credentials or config paths. The only implicit environment dependency is CLAUDE_TOOL_OUTPUT (used by error-detector) and typical filesystem access to create files under the workspace or ~/.openclaw. Because CLAUDE_TOOL_OUTPUT may contain sensitive command output, enabling the PostToolUse hook should be a conscious, limited decision.
Persistence & Privilege
always is false and the skill is user-invocable. The code optionally copies hooks into ~/.openclaw/hooks and writes workspace files (e.g., ~/.openclaw/workspace/.learnings) only when the user follows the installation instructions; nothing forces global installation or modifies other skills' configs. Hook handler injects a virtual reminder file at bootstrap rather than modifying unrelated files.
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-improving-agent-3-0-16 - 安装完成后，直接呼叫该 Skill 的名称或使用
/self-improving-agent-3-0-16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
Initial release of the self-improving-agent skill for continuous learning and improvement.
- Provides a standardized process for logging learnings, errors, and feature requests to dedicated markdown files in `.learnings/`.
- Includes initialization steps to create necessary log files without overwriting existing data.
- Outlines clear logging categories and promotion workflows for escalating important insights to workspace files (`AGENTS.md`, `SOUL.md`, etc.).
- Adds guidance for OpenClaw-specific setup and generic integration with other agents.
- Details safe logging practices, emphasizing privacy and avoiding exposure of sensitive information.
- Supplies easy-to-follow markdown templates for learning and error entries.
元数据
常见问题
Self Improving Agent 3.0.16 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 119 次。
如何安装 Self Improving Agent 3.0.16？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install self-improving-agent-3-0-16」即可一键安装，无需额外配置。
Self Improving Agent 3.0.16 是免费的吗？
是的，Self Improving Agent 3.0.16 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Self Improving Agent 3.0.16 支持哪些平台？
Self Improving Agent 3.0.16 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 3.0.16？
由 youngsiAI（@youngsiai）开发并维护，当前版本 v1.0.0。
推荐 Skills