← 返回 Skills 市场
Self Improving Agent
作者
shenghoo123-png
· GitHub ↗
· v0.2.0
· MIT-0
90
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install selfgrowth-kay
功能描述
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolv...
安全使用建议
This skill is not obviously malicious, but it is inconsistent and potentially powerful: it claims to learn from every skill and to update other skills, yet the platform doesn't provide the global hooks it expects and it doesn't declare the credentials necessary to push changes. Before installing, ask the author how it will be triggered on your platform, what repository credentials (if any) it needs, and what explicit safeguards exist (e.g., ask-before-PR, sandboxed test runs, review-only mode). If you proceed, run it in an isolated workspace, do not grant global repo write tokens without manual review, and require that any PRs be human-reviewed before merging.
功能分析
Type: OpenClaw Skill
Name: selfgrowth-kay
Version: 0.2.0
The skill bundle implements a 'self-improving' architecture that instructs the AI agent to autonomously modify its own skill files and instructions based on interaction history. While the provided bash scripts (hooks/pre-tool.sh, hooks/post-bash.sh) are limited to logging, the core logic in SKILL.md and README.md encourages the agent to use 'Write' and 'Edit' tools to rewrite its own codebase and memory. This self-modification capability creates a significant attack surface where the agent's primary instructions could be subverted through interaction, though no explicit evidence of intentional malice or data exfiltration was found in the current files.
能力评估
Purpose & Capability
The skill's stated purpose is to observe every skill run and update skills automatically. However, OpenClaw does not support the Claude-style global hooks the skill expects (the included OPENCLAW_HOOKS.md even notes this). The skill includes local hook scripts and memory files, which is coherent for a local experiment, but the claim of automatic, platform-wide learning/updating is not supported by the declared requirements or platform capabilities. A mechanism to modify other skills (create PRs / auto updates) would normally require repository/git credentials and explicit platform hooks, which are not declared.
Instruction Scope
SKILL.md and README instruct the agent to extract experiences from 'Any Skill Completes', update skills, and create PRs. The allowed-tools list (Read, Write, Edit, Bash, Grep, Glob, WebSearch) gives the agent broad access to read and modify files and query the web. The three hook scripts present only log inputs/outputs to stderr (no external exfiltration), but the instructions expect capture and modification of other skills' artifacts—operations that could read sensitive workspace files or alter multiple skill codebases if invoked with write privileges. The skill's automatic behaviors are vague (e.g., what gets updated automatically vs. ask_first), granting the agent broad discretion.
Install Mechanism
No external install/download is specified (instruction-only plus bundled files). That keeps installation risk low because nothing is fetched from remote URLs. The included hooks and memory files are local and simple; hook scripts only echo inputs/outputs to stderr and are not obfuscated or downloading code.
Credentials
The skill declares no required environment variables or primary credential, but its stated behaviors (creating PRs, updating other skills) would normally require git/CI credentials and write access to repositories. Those credentials are not declared nor are the boundaries of file access limited. This mismatch is noteworthy: either it will prompt for credentials at runtime, or it expects the agent to already have repository write rights via the agent environment—both situations should be clarified.
Persistence & Privilege
always:false (no forced inclusion) and model invocation is allowed (normal). The skill intends to persist patterns in memory files (bundled under memory/) and to propose code changes (create-pr hook ask_first). While that behavior can be legitimate, granting Write/Edit permission plus web access could let the skill modify multiple skills or push changes if credentials are available. The skill does not request permanent platform privileges, but its design expects cross-skill visibility which increases blast radius if misused.
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 selfgrowth-kay - 安装完成后，直接呼叫该 Skill 的名称或使用
/selfgrowth-kay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
v0.2.0
Self-improving universal agent for skill evolution:
- Introduced multi-memory architecture (semantic, episodic, and working memory) to track and learn from all skill executions.
- Implemented hooks-based automation for experience logging, pattern extraction, and self-correction.
- Added structured experience extraction, feedback integration, and reusable pattern abstraction for continuous self-improvement.
- Auto-triggers on skill completion and errors to update knowledge and evolve skill guidance.
- Prioritizes improvements using an evolution priority matrix to keep skills up-to-date with new insights.
元数据
常见问题
Self Improving Agent 是什么？
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolv... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 90 次。
如何安装 Self Improving Agent？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install selfgrowth-kay」即可一键安装，无需额外配置。
Self Improving Agent 是免费的吗？
是的，Self Improving Agent 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Self Improving Agent 支持哪些平台？
Self Improving Agent 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？
由 shenghoo123-png（@shenghoo123-png）开发并维护，当前版本 v0.2.0。
推荐 Skills