← 返回 Skills 市场
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
164
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install self-improvement-test
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: inject lightweight reminders and provide helpers to log and promote "learnings". Before enabling it, review the included scripts and hook handler (they are short and readable). Prefer enabling hooks at the project level rather than user/global level if you want to limit injection to specific workspaces. If you run extract-skill.sh, be aware it will create files/directories under the current workspace (it includes checks to avoid absolute paths or '..' but still writes locally). No credentials are requested, but as with any hook that alters agent bootstrap/context, only enable it if you trust its content and the referenced repository.
功能分析
Type: OpenClaw Skill
Name: self-improvement-test
Version: 1.0.0
The 'self-improvement-test' skill bundle provides a framework for AI agents to log errors, user corrections, and new insights into local markdown files within a '.learnings/' directory. It includes utility scripts like 'extract-skill.sh' for scaffolding new skills and OpenClaw hooks ('handler.js') to inject reminders into the agent's context. The logic and instructions are consistent with the stated goal of continuous improvement, and the scripts include basic safety checks (e.g., path validation in 'extract-skill.sh') to prevent directory traversal.
能力评估
Purpose & Capability
Name/description (log learnings, detect errors, promote learnings) align with the files and scripts provided. No unrelated credentials, binaries, or surprising requirements are requested. The included hooks and scripts directly support logging, reminders, and extracting learnings into skill scaffolds.
Instruction Scope
SKILL.md instructs copying a hook into OpenClaw hooks and creating a .learnings/ workspace that will be injected into sessions. That's expected for a "self-improvement" skill, but it does mean the skill injects reminder context into agent sessions (workspace/prompt injection). The scripts only emit reminder text or create local skill scaffolds; they do not exfiltrate data. Review that you want reminder injection into every session you enable and prefer project-level installs over global user-level if you want to limit scope.
Install Mechanism
There is no automated install spec; installation is manual (git clone or copying the hook). The package bundles scripts and hook handlers in the repo rather than downloading arbitrary binaries at runtime. This is a lower-risk install model, but installing or enabling hooks will cause agent-run code to execute (activator/error-detector scripts and the handler), so inspect scripts before enabling.
Credentials
The skill declares no required env vars or credentials. The error-detector script reads CLAUDE_TOOL_OUTPUT (an agent-provided env var) which is reasonable for detecting command failures but is not declared in requires.env — this is expected in OpenClaw/Claude contexts. No secrets or unrelated credentials are requested.
Persistence & Privilege
always:false (not force-included). However SKILL.md guides enabling hooks at user-level (~/.claude/settings.json or ~/.openclaw) which would cause the hook scripts and virtual-file injection to run for all sessions for that user. That is intentional for reminders but you should enable at project scope if you want to avoid global persistence.
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-test - 安装完成后，直接呼叫该 Skill 的名称或使用
/self-improvement-test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-improvement-test skill.
- Enables continuous improvement by logging learnings, errors, and feature requests in structured markdown files.
- Provides clear guidelines on when and how to log corrections, failures, feature requests, and best practices.
- Includes recommendations for promoting broadly applicable lessons into project-wide memory files.
- Offers integration instructions for both OpenClaw and generic agent environments.
- Supplies detailed templates and ID conventions for consistent learning, error, and feature request entries.
元数据
常见问题
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks. 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 164 次。
如何安装 Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install self-improvement-test」即可一键安装，无需额外配置。
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks. 是免费的吗？
是的，Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks. 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks. 支持哪些平台？
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks. 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 Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.？
由 lintqiu（@lintqiu）开发并维护，当前版本 v1.0.0。
推荐 Skills