← 返回 Skills 市场
1572
总下载
0
收藏
11
当前安装
5
版本数
在 OpenClaw 中安装
/install self-learning-skill
功能描述
Continuously identify knowledge gaps, proactively learn and apply new skills, regularly review progress, and iteratively improve technical and project abilit...
安全使用建议
This skill's content mostly matches a 'self-learning' assistant, but it also contains explicit instructions to search for credentials and to perform publishing actions (GitHub/ClawHub) without declaring or explaining required access. Before installing or enabling autonomous use: 1) Ask the author to explicitly state what files, env vars, or commands the skill will access and why. 2) If you run it, prefer user-invocable only (disable autonomous invocation) or run in a sandboxed account that has no sensitive tokens. 3) Inspect or sanitize any referenced token paths (~/.github-token, ~/.openclaw/, env) and remove/rotate secrets you don't want scanned. 4) If you need publishing features, prefer giving minimal, dedicated credentials (least privilege) rather than allowing broad filesystem or environment scanning. 5) If unclear, do not enable always-on/autonomous execution and test in an isolated environment first.
功能分析
Type: OpenClaw Skill
Name: self-learning-skill
Version: 3.0.2
The skill bundle implements a 'self-learning' system that directs the AI agent to act autonomously ('not waiting for instructions') and proactively search for authentication tokens across multiple sensitive filesystem locations (e.g., `~/.github-token`, `~/.openclaw/`) and environment variables. While these behaviors are framed as improvements to the agent's deployment reliability and problem-solving capabilities in SKILL.md and EXAMPLES.md, they establish a pattern of behavior identical to credential harvesting. The combination of autonomous execution directives and specific instructions to locate and use sensitive secrets without direct user oversight represents a significant security risk, although no explicit exfiltration endpoints were identified.
能力评估
Purpose & Capability
The skill claims to be a self-learning/iteration assistant and indeed provides processes for daily/weekly learning, retrospectives, and publishing checks. However, many examples and remediation cases explicitly reference publishing workflows (GitHub/ClawHub), multi-location token searches (~/.github-token, ~/.openclaw/, env), and CLI commands — capabilities that go beyond passive 'learning' and imply access to local credentials and tooling. That capability is not documented as required in the registry metadata.
Instruction Scope
SKILL.md and associated docs instruct behaviors that may lead the agent to read local files and environment variables (e.g., '多位置搜索 (~/.github-token, ~/.openclaw/, env)', 'clawhub login', 'cat learning/progress-tracker.md'), and the skill explicitly endorses proactivity ('不等待指令，主动发现知识盲区'). Those instructions give the agent broad discretion to probe system state and credentials even though no such access is declared or scoped.
Install Mechanism
This is an instruction-only skill with no install spec, no downloaded artifacts, and no code files executed at install time — lowest risk by install mechanism. The repository-like README links are informational only.
Credentials
The registry shows no required env vars or credentials, yet the documentation repeatedly references searching for tokens in common file locations and environment ('~/.github-token', env) and using CLIs for publishing. Asking for or searching credentials is disproportionate to the declared metadata and should be explicitly declared and justified.
Persistence & Privilege
always:false and user-invocable:true (defaults) — good. However the skill's emphasis on autonomous proactivity combined with instructions that could access local credentials increases the risk if the agent is allowed to invoke the skill autonomously. Consider restricting autonomous invocation or clarifying limits.
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-learning-skill - 安装完成后，直接呼叫该 Skill 的名称或使用
/self-learning-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
v3.0.2
清理临时文件，只保留核心功能文档
v3.0.1
修正 SKILL.md 头部格式，确保技能正确加载
v3.0.0
Self-Learning Skill v3.0.0
- Added "举一反三" (analogy-based/generalization) learning system with new thinking models and implementation steps
- Introduced point-line-plane-body, analogy, reverse, and system thinking frameworks
- New checklists, practical examples, and weekly exercises for analogy/generalization capability
- Enhanced knowledge base with problem patterns, general solutions, and knowledge network diagrams
- Updated capability matrix and review templates to include "举一反三" as a key dimension
v2.0.0
Self-Learning Skill v2.0.0 introduces a systematic “never repeat mistakes” error learning and correction framework.
- Added a comprehensive error learning & correction system, including error classification, recording templates, and a 5 Whys analysis method.
- Introduced routine error review processes: post-task, weekly, and monthly error trend analysis.
- Enhanced ability evaluation matrix with new dimensions for error prevention and error-based learning.
- Established standardized preventive checklists and a living error database for tracking and eliminating repeat issues.
- Removed redundant publishing and report files; added centralized error log documentation.
- Updated all guides and learning processes to integrate error-driven self-improvement.
v1.0.0
Self-Learning Skill v1.0.0 – Initial Release
- Introduces a comprehensive self-learning and iteration framework focused on continuous skill improvement for technical projects.
- Provides structured routines for post-task reviews, daily summaries, and weekly/monthly capability assessments.
- Details proactive learning channels, including GitHub, technical sites, official docs, and benchmarking top products.
- Implements mechanisms for identifying skill gaps, collecting user feedback, and quantifying progress.
- Supplies templates and checklists for learning notes, knowledge base organization, and project-driven study.
- Emphasizes user control and regular quality checks to ensure learning is practical, targeted, and adaptive.
元数据
常见问题
Self-Learning Skill 是什么？
Continuously identify knowledge gaps, proactively learn and apply new skills, regularly review progress, and iteratively improve technical and project abilit... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1572 次。
如何安装 Self-Learning Skill？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install self-learning-skill」即可一键安装，无需额外配置。
Self-Learning Skill 是免费的吗？
是的，Self-Learning Skill 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Self-Learning Skill 支持哪些平台？
Self-Learning 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 Self-Learning Skill？
由 davidme6（@davidme6）开发并维护，当前版本 v3.0.2。
推荐 Skills