← 返回 Skills 市场
11217
总下载
19
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install self-improving-agent-1-0-2
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 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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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.
安全使用建议
Install only in trusted workspaces where you are comfortable with an agent writing persistent learning files and possibly editing future-agent instruction files. Prefer project-level setup, avoid global always-on hooks, require explicit approval before promotion to CLAUDE.md/AGENTS.md/Copilot/SOUL/TOOLS or new skills, and redact secrets, personal data, raw transcripts, command outputs, tokens, and environment details before anything is logged or shared across sessions.
功能分析
Type: OpenClaw Skill
Name: self-improving-agent-1-0-2
Version: 1.0.0
The skill bundle is classified as suspicious due to its reliance on powerful capabilities that, while intended for benign self-improvement, present a significant attack surface. Specifically, the `scripts/extract-skill.sh` script performs file system modifications (`mkdir`, `cat >`) and executes shell commands (`sed`, `awk`) based on user-provided input (`skill-name`), which could be exploited if the input is not properly sanitized. Additionally, the `scripts/error-detector.sh` reads the `CLAUDE_TOOL_OUTPUT` environment variable, which can contain sensitive command outputs, and the `SKILL.md` and `references/clawdbot-integration.md` instruct the agent to write to various project and workspace files (`.learnings/*.md`, `CLAUDE.md`, `AGENTS.md`, `SOUL.md`, `TOOLS.md`) and use inter-agent communication (`sessions_send`). While the stated purpose is knowledge management, these capabilities (shell execution, file writes, reading sensitive environment variables, inter-agent communication) are high-risk and could be misused if the agent or its inputs were compromised, pushing it beyond 'benign'.
能力评估
Purpose & Capability
Capturing learnings, errors, and corrections is coherent with the stated purpose, but the artifact goes beyond local notes by encouraging promotion into CLAUDE.md, AGENTS.md, Copilot instructions, SOUL.md, TOOLS.md, reusable skills, and Clawdbot session workflows that can affect future agents and other sessions.
Instruction Scope
The activation criteria and detection triggers are broad common conversation patterns, and the skill says to log immediately and promote aggressively without requiring user confirmation, review, redaction, or sensitive-context exclusions.
Install Mechanism
No deceptive installation behavior is evident. Hook setup is described as opt-in, but the shown empty matcher would run on every prompt when enabled, so users should avoid global or always-on activation unless they accept that scope.
Credentials
Local markdown logging is purpose-aligned, but the templates ask for full context, actual error output, command parameters, and environment details, and the Clawdbot section documents transcript access; that can persist sensitive operational or personal data without minimization guidance.
Persistence & Privilege
The skill creates durable project memory and can modify high-trust agent instruction files; it also documents sessions_history and sessions_send, creating confidentiality and lateral-influence risks that are not tightly scoped.
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-1-0-2 - 安装完成后，直接呼叫该 Skill 的名称或使用
/self-improving-agent-1-0-2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 skill for structured project learnings and continuous improvement.
- Provides detailed guides and templates for logging errors, user corrections, feature requests, and knowledge gaps in markdown files.
- Defines categories, log formats, metadata, and processes for reviewing, resolving, and promoting insights to project documentation.
- Outlines triggers and periodic review steps to ensure recurring issues and valuable knowledge are captured and acted upon.
- Supports detection patterns (corrections, requests, gaps, errors) for automatic or manual entry creation.
元数据
常见问题
Self Improving Agent 1.0.2 是什么？
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. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 11217 次。
如何安装 Self Improving Agent 1.0.2？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install self-improving-agent-1-0-2」即可一键安装，无需额外配置。
Self Improving Agent 1.0.2 是免费的吗？
是的，Self Improving Agent 1.0.2 完全免费（开源免费），可自由下载、安装和使用。
Self Improving Agent 1.0.2 支持哪些平台？
Self Improving Agent 1.0.2 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 1.0.2？
由 TXMERLXN（@txmerlxn）开发并维护，当前版本 v1.0.0。
推荐 Skills