← 返回 Skills 市场
116
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install self-improving-agent-shared
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 exactly what it says: create and remind you to append learnings to .learnings/ and optionally add lightweight hooks. Before installing or enabling hooks: (1) review the scripts (activator.sh, error-detector.sh, extract-skill.sh) to ensure you’re comfortable with their behavior and local file writes; (2) only enable hooks in environments you trust (they will run on events like UserPromptSubmit or PostToolUse); (3) note that error-detector.sh inspects CLAUDE_TOOL_OUTPUT (tool output) — not secrets — but you should still confirm your agent runtime doesn’t place sensitive data there; (4) the extract script writes files into relative ./skills by design—use --dry-run first or set output-dir to avoid unintended changes; (5) if you want to limit automatic activity, skip enabling the hooks or add matcher filters as suggested in the docs.
能力评估
Purpose & Capability
Name/description (capture learnings, errors, corrections) aligns with provided files: documentation, hook handlers that inject reminders, lightweight activator/error-detector scripts, and a skill-extraction helper. No unrelated credentials, binaries, or network download/install steps are present.
Instruction Scope
SKILL.md and hook docs instruct creating .learnings/, installing optional OpenClaw hooks, and enabling small scripts. Scripts only output reminders or scan a provided CLAUDE_TOOL_OUTPUT variable for error patterns; handler injects a virtual file into bootstrapFiles. The instructions do not instruct reading arbitrary secrets or exfiltrating data. One minor note: error-detector.sh reads the CLAUDE_TOOL_OUTPUT environment variable (a runtime tool output) which is expected in the described agent environments.
Install Mechanism
No install spec is declared (instruction-only skill). Suggested installation is cloning a GitHub repo or using ClawdHub; no archives or remote arbitrary downloads/executables are performed. Scripts live in the repo and would only run if the user opts into hooking them.
Credentials
The skill declares no required environment variables or secrets. Runtime scripts read CLAUDE_TOOL_OUTPUT (tool output injected by the agent runtime) and event/context passed into hook handlers; these are consistent with the described hook behavior and are not sensitive credentials.
Persistence & Privilege
always:false and user-invocable:true. Hook installation and enabling are explicit user actions. The handler only injects a virtual reminder file into bootstrapFiles and does not modify other skills or global configuration autonomously.
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-shared - 安装完成后，直接呼叫该 Skill 的名称或使用
/self-improving-agent-shared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-improving-agent-shared v1.0.0 — Initial Release
- Introduces a comprehensive self-improvement workflow for agents and coding environments.
- Standardizes how errors, learnings, and feature requests are logged in markdown files for ongoing enhancement.
- Provides structured markdown templates for LEARNINGS.md, ERRORS.md, and FEATURE_REQUESTS.md with categorization, metadata, and promotion guidance.
- Offers integration instructions for OpenClaw and generic setups, including workspace structure and session-based learning sharing.
- Details best practices for reviewing and promoting broadly applicable learnings to persistent project files (e.g., CLAUDE.md, AGENTS.md).
- Includes sample workflows, file setup steps, and markdown templates to facilitate adoption.
元数据
常见问题
Self Improving Agent Shared 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 116 次。
如何安装 Self Improving Agent Shared？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install self-improving-agent-shared」即可一键安装，无需额外配置。
Self Improving Agent Shared 是免费的吗？
是的，Self Improving Agent Shared 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Self Improving Agent Shared 支持哪些平台？
Self Improving Agent Shared 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 Shared？
由 LoRexxar（@lorexxar）开发并维护，当前版本 v1.0.0。
推荐 Skills