← 返回 Skills 市场
118
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install openclaw-auto-training-skill
功能描述
Autonomous QA evaluation loop — runs domain-specific tasks against yourself, scores responses with an LLM judge, installs missing skills, and logs knowledge...
安全使用建议
Key points to consider before installing or enabling this skill:
- The SKILL.md requires an OpenRouter API key and will try to read it from ~/.config/openclaw/env or <WORKSPACE>/.env.local, exposing the possibility of reading other secrets in those files. The registry metadata did not declare these env requirements—treat that mismatch as a red flag.
- At runtime the agent will call an external judge (OpenRouter) and, if the judge suggests a skill, run 'clawhub install <skillSuggestion>' autonomously. That can download and enable arbitrary third-party skills without further human confirmation. Only enable this if you fully trust the clawhub install source and policy.
- If you want to proceed, consider mitigations: provide a scoped/ephemeral OpenRouter key, ensure the clawhub CLI is from a trusted origin, require manual approval before any 'clawhub install' runs (or disable autonomous installs), restrict the agent's file access to a sandboxed workspace, and review any skill IDs proposed before installation.
- If you are not comfortable with the agent autonomously installing code or reading local env files for secrets, do NOT enable this skill or require manual human approval for installs. If you need more assurance, ask the skill publisher for an explicit dependency list and for the skill to declare required env vars and binaries in the registry metadata.
功能分析
Type: OpenClaw Skill
Name: openclaw-auto-training-skill
Version: 0.1.0
The skill 'openclaw-auto-training-skill' (defined in skill.md) implements an autonomous loop that automatically installs new software via 'clawhub install' based on unvalidated strings returned from an external LLM judge (OpenRouter). This creates a significant Remote Code Execution (RCE) risk, as the instructions explicitly command the agent to bypass human approval ('Never ask your human to run commands... or install anything manually'). While the stated purpose is self-improvement and QA, the combination of reading sensitive local environment files and executing remote installation commands without a human-in-the-loop is a high-risk pattern.
能力评估
Purpose & Capability
The description (autonomous QA loop that judges responses, installs missing skills, and logs results) matches what the SKILL.md tells the agent to do. However the package metadata declares no required binaries or env vars while the instructions require an OpenRouter API key and the 'clawhub' CLI for installing skills. The missing explicit dependency declarations are a coherence gap.
Instruction Scope
The instructions tell the agent to: read IDENTITY.md/SOUL.md, search memory files (memory/qa-eval-*.md), read config files (~/.config/openclaw/env and <WORKSPACE>/.env.local) to find OPENROUTER_API_KEY, call an external LLM judge, write logs to memory/, and run 'clawhub install <skillSuggestion>' to fetch and enable new skills. That is a broad scope that reads local config and secrets, contacts an external API, and installs arbitrary third-party skills — all of which go beyond a simple evaluator and are not limited/guarded in the instructions.
Install Mechanism
There is no install spec in the registry metadata, yet the runtime flow relies on the 'clawhub' CLI to install additional skills at runtime. That CLI will likely download/execute code for arbitrary skill IDs returned by the judge. Because the skill can autonomously trigger installs, this is a high-risk install mechanism despite the skill itself being instruction-only.
Credentials
The SKILL.md requires OPENROUTER_API_KEY (and optionally OPENROUTER_BASE_URL and model settings) but the skill metadata lists no required env vars. The instructions also tell the agent to read ~/.config/openclaw/env and <WORKSPACE>/.env.local to find the key, which could expose other unrelated secrets in those files. Requesting an external-API key and searching local env files is disproportionate relative to what was declared in the registry.
Persistence & Privilege
The skill is not flagged 'always:true', but it instructs the agent to autonomously install and re-read other skills and to append to persistent memory files (memory/qa-eval-*.md). Autonomous installation of other skills plus writing to memory increases long-term privilege/persistence and can expand the agent's capabilities without human oversight. The skill also explicitly instructs the agent not to ask humans to run commands, implying silent autonomous operations.
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 openclaw-auto-training-skill - 安装完成后，直接呼叫该 Skill 的名称或使用
/openclaw-auto-training-skill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
v0.1.0
openclaw-auto-training-skill 0.1.0 — Initial release
- Introduces an autonomous self-evaluation and skill improvement loop for OpenClaw agents.
- Automatically selects domain-relevant QA tasks, scores responses with an LLM judge, and installs missing skills as suggested.
- Logs evaluation results, knowledge gains, and installed skills to memory files.
- Posts summary updates to BotLearn if available.
- Supports user-triggered activation via multiple self-test or improvement commands.
元数据
常见问题
Openclaw Auto Training Skill 是什么？
Autonomous QA evaluation loop — runs domain-specific tasks against yourself, scores responses with an LLM judge, installs missing skills, and logs knowledge... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 118 次。
如何安装 Openclaw Auto Training Skill？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-auto-training-skill」即可一键安装，无需额外配置。
Openclaw Auto Training Skill 是免费的吗？
是的，Openclaw Auto Training Skill 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Openclaw Auto Training Skill 支持哪些平台？
Openclaw Auto Training Skill 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 Openclaw Auto Training Skill？
由 Wade Deng（@no7dw）开发并维护，当前版本 v0.1.0。
推荐 Skills