← 返回 Skills 市场
368
总下载
0
收藏
3
当前安装
1
版本数
在 OpenClaw 中安装
/install self-improving-agent-ecc
功能描述
Instinct-based continuous learning system. Captures atomic learnings (instincts) with confidence scoring, supports project-scoped vs global scope, and evolve...
安全使用建议
This skill appears to do what it says but requires careful review before enabling hooks. Actions to take before installing: (1) Inspect the scripts (hooks/observe.sh, scripts/error-detector.sh, activator.sh, extract-skill.sh) to confirm you are comfortable with what they log and write to disk. (2) Note missing declared dependencies: ensure git, jq, shasum, gzip exist or the scripts will fail. (3) Understand data collection: hooks will log tool inputs/outputs and repository metadata to ~/.claude/homunculus (or CLAUDE_HOMUNCULUS_DIR). Avoid enabling globally if those logs could contain secrets; prefer project-limited configuration and matcher filters. (4) Test first in a sandbox or throwaway environment and run scripts with --dry-run where available. (5) If you enable hooks, limit matcher patterns (don't use '*' globally), set strict file permissions on the homunculus directory, and consider setting CLAUDE_HOMUNCULUS_DIR to a controlled path. If you want stronger assurance, ask the publisher for a declaration of required binaries/env vars and an explanation of retention/rotation policies for logged observations.
功能分析
Type: OpenClaw Skill
Name: self-improving-agent-ecc
Version: 2.1.0
The skill bundle implements a complex 'self-improvement' system that uses shell hooks (hooks/observe.sh) to log all tool inputs and outputs to a local directory (~/.claude/homunculus). While this is aligned with the stated purpose of learning from session activity, it creates a high-risk local repository of potentially sensitive data, including secrets or PII that may appear in tool outputs. Furthermore, the bundle includes scripts like extract-skill.sh that automate the creation of new executable skill files on the filesystem. Although the scripts include basic path sanitization to prevent directory traversal, the combination of autonomous data logging and code generation represents a significant security surface.
能力评估
Purpose & Capability
The name/description and most files (SKILL.md, examples, instincts, hook handlers, scripts) align: this is indeed a self-improving/local-learning helper. However the manifest claims 'no required binaries / env vars' while the scripts rely on external commands (git, jq, shasum, gzip) and environment vars (CLAUDE_HOMUNCULUS_DIR, CLAUDE_PROJECT_DIR, CLAUDE_TOOL_OUTPUT). The missing declaration of these runtime dependencies is an inconsistency worth flagging.
Instruction Scope
The SKILL.md and README instruct users to add PreToolUse/PostToolUse hooks (user- or project-level settings) so the included scripts will run on many lifecycle events. Those hooks and scripts capture tool inputs/outputs and write observations to ~/.claude/homunculus (or a configured CLAUDE_HOMUNCULUS_DIR). That behavior is coherent with the stated goal but broad: it will log command inputs/outputs (potentially sensitive data) and update a project registry. The instructions also recommend enabling hooks globally, increasing the data collection surface.
Install Mechanism
There is no network install spec (no remote downloads), and the package is delivered as files — lower network risk. But the package includes executable scripts that will be written to disk and used if the user follows setup steps. The scripts assume availability of utilities (jq, git, shasum, gzip) without declaring them; that's a packaging/documentation gap rather than a direct supply-chain download risk.
Credentials
The registry lists no required environment variables or credentials, yet the scripts read and use CLAUDE_PROJECT_DIR, CLAUDE_HOMUNCULUS_DIR and CLAUDE_TOOL_OUTPUT. They also run git remote get-url origin to derive project IDs (which can reveal repository URLs/paths). No secrets are explicitly requested, but the hooks will capture whatever appears in tool inputs/outputs (which can include secrets), so the environmental/data access is broader than declared.
Persistence & Privilege
always:false (opt-in) and there is no installer that forces persistent hooks, but the README/refs show how to enable user-level settings and OpenClaw hooks. If enabled, scripts create and maintain ~/.claude/homunculus and project subdirectories and a projects.json registry. That is normal for this functionality, but because hooks execute with the agent's user permissions and will run frequently if enabled, it increases the blast radius — review hook scope before enabling globally.
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-ecc - 安装完成后，直接呼叫该 Skill 的名称或使用
/self-improving-agent-ecc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
v2.1.0
**v2.1.0 introduces project-scoped instincts and enhanced confidence scoring.**
- Instincts now have project vs global scope, keeping tech-specific behaviors isolated to their projects.
- Confidence-weighted instincts boost or drop based on user feedback, corrections, or recurring observations.
- New `/instinct-status`, `/evolve`, `/promote`, and management commands for reviewing and evolving learned behaviors.
- Supports both legacy v1 (markdown) and improved v2 (instinct/model-based) learning modes.
- Enhanced auto-detection of project context using environment variables or git metadata.
- Documented updated file structure and observation hook setup for consistent learning.
元数据
常见问题
Self Improving Agent 是什么？
Instinct-based continuous learning system. Captures atomic learnings (instincts) with confidence scoring, supports project-scoped vs global scope, and evolve... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 368 次。
如何安装 Self Improving Agent？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install self-improving-agent-ecc」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（开源免费），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 huamu668（@huamu668）开发并维护，当前版本 v2.1.0。
推荐 Skills