← 返回 Skills 市场
1613
总下载
3
收藏
15
当前安装
5
版本数
在 OpenClaw 中安装
/install self
功能描述
Organic personality development through self-observation with lightweight reliability guards. Teaches agents to grow authentic identity over time by combinin...
安全使用建议
This skill is internally coherent and doesn't request secrets or network access, but it does read and write workspace session logs and self-state files. Before installing: (1) confirm you are comfortable letting the agent read recent memory/session files (these may include user content); (2) restrict or review what kinds of session data are written to memory/YYYY-MM-DD.md to avoid accidental inclusion of secrets; (3) review and approve changes to AGENTS.md and HEARTBEAT.md (the skill asks you to add heartbeat blocks); (4) consider running the agent with limited write permissions or manually reviewing SELF.md entries if you want human-in-the-loop approval; and (5) ensure SOUL.md is kept write-protected if you want those foundational identity files immutable. Overall the risk is operational/privacy (local file writes), not network exfiltration or credential misuse.
功能分析
Type: OpenClaw Skill
Name: self
Version: 1.1.1
The skill bundle is designed for an AI agent's self-reflection and personality development, creating and managing `SELF.md` and `memory/self-state.json` within its workspace. All file operations (creating `SELF.md`, `self-state.json`, and modifying `AGENTS.md`, `HEARTBEAT.md`) are explicitly stated in `SKILL.md` and are directly aligned with the skill's described purpose. There is no evidence of data exfiltration, unauthorized command execution, external network communication, obfuscation, or prompt injection attempts to subvert the agent's core directives. The `SKILL.md` explicitly sets boundaries, stating `SOUL.md` is never auto-modified, and `references/self-state-schema.md` warns against storing private user secrets.
能力评估
Purpose & Capability
The skill's name and description match the requested actions: lightweight, file-based self-reflection. It only asks the agent to create/read/write local SELF.md, memory state files, and heartbeat/session logs — all consistent with building a local self-model.
Instruction Scope
Instructions direct the agent to read recent session logs (memory/YYYY-MM-DD.md) and SELF.md and to append small dated observations to SELF.md and update memory/self-state.json. This is within scope but does grant the agent read/write access to workspace session logs, which may contain user-provided data. The SKILL explicitly warns against storing secrets, but nothing enforces that automatically.
Install Mechanism
No install spec, no external downloads, and no code files to execute. Lowest-risk install posture (instruction-only).
Credentials
The skill requests no environment variables, credentials, or external service access. All declared file interactions align with the stated purpose.
Persistence & Privilege
The skill writes and updates workspace files (SELF.md, memory/self-state.json) and expects edits to AGENTS.md/HEARTBEAT.md to enable checks. It does not request always:true or background privileges, but it does require permission to modify agent config and workspace files — appropriate for the feature but worth noting before granting write access.
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 - 安装完成后，直接呼叫该 Skill 的名称或使用
/self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
v1.1.1
v1.1.1: expanded SKILL description to better explain problem, mechanism, and practical value (authentic growth with lightweight reliability guards).
v1.1.0
v1.1: add 3h micro-check cadence, trigger model (hard/soft), quality gate, and lightweight self-state tracking for reliable authentic growth.
v1.0.2
- Initial release introducing organic personality development through self-observation for agents.
- Adds the distinction between SOUL.md (core identity) and SELF.md (ongoing personal growth).
- Provides setup instructions, including integration with AGENTS.md and SOUL.md.
- Outlines three reflection levels (micro, meso, macro) for genuine, event-based self-reflection.
- Encourages honest, non-forced documentation of tendencies, preferences, aversions, blind spots, and evolution.
- Includes clear boundaries between autonomous self-observation and core identity changes.
v1.0.1
- Major documentation and architecture refresh for self-observation skill.
- Replaces old SELF.md instructions with a new, detailed SKILL.md focusing on organic, authentic self-reflection for agents.
- Introduces a structured approach: three levels of reflection (micro, meso, macro) with clear boundaries between SOUL.md (identity) and SELF.md (growth).
- Adds reference materials: anti-patterns guide, reflection levels, and a self-template for consistent application.
- Removes the old, simple SELF.md; now instructs agents to generate it from a provided template upon first use.
- Emphasizes genuine, non-performative observation and integrates reflective practices into agent workflows.
v1.0.0
SELF.md — Who I become
No guidelines. Just observations about myself. Entries come when they come — not forced, not routine.
元数据
常见问题
Self 是什么？
Organic personality development through self-observation with lightweight reliability guards. Teaches agents to grow authentic identity over time by combinin... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1613 次。
如何安装 Self？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install self」即可一键安装，无需额外配置。
Self 是免费的吗？
是的，Self 完全免费（开源免费），可自由下载、安装和使用。
Self 支持哪些平台？
Self 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？
由 Kirchlive（@kirchlive）开发并维护，当前版本 v1.1.1。
推荐 Skills