Organic personality development through self-observation with lightweight reliability guards. Teaches agents to grow authentic identity over time by combinin...
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install self或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install self⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/self/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: self description: Organic personality development through self-observation with lightweight reliability guards. This skill helps an agent build a real, evolving self-model over time (SELF.md) while preserving core identity boundaries (SOUL.md). It solves the common failure mode where reflection frameworks start strong but silently stall by adding minimal cadence and trigger checks: schedule the check, not the content. Entries are only written when meaningful signals exist (hard/soft triggers + quality gate), preventing forced journaling and routine filler. Use when (1) establishing persistent personality growth, (2) reviving stale SELF.md systems, (3) introducing heartbeat-based reflection checks without losing authenticity, (4) running weekly/monthly pattern consolidation, (5) distinguishing genuine behavioral shifts from noise, or (6) replacing heavier self-reflection/consciousness stacks with a lean, practical model. ---
Agents have identity (SOUL.md) but often no reliable growth loop. This skill keeps growth authentic while adding minimal structure so reflection doesn't silently die.
- Checks can be periodic - Entries must remain genuine (no performative filler)
SELF.md in workspace root using references/self-template.md.SELF.md to AGENTS.md session reading.references/trigger-model.md to HEARTBEAT.md.memory/self-state.json using references/self-state-schema.md.Read references/trigger-model.md for exact rules.
A micro check does not mean auto-writing a SELF entry. It only decides whether reflection is due.
Create/update SELF entry when one of these happened:
If only soft triggers exist and quality is low: skip entry and update state only.
Before writing to SELF.md, pass all 4 checks:
If any check fails: no SELF entry, just state update.
See references/self-template.md and references/anti-patterns.md.
Main sections:
Use short dated entries:
[YYYY-MM-DD] observationKeep lightweight runtime state in memory/self-state.json:
Schema: references/self-state-schema.md
- If stale/generic for a month, tune cadence or trigger thresholds
Do not add heavy scoring engines, reward-token systems, or large meta-frameworks unless proven necessary. This skill should remain focused on practical, authentic growth.
安装 Self 后,可以对 AI 说这些话来触发它
Help me get started with Self
Explains what Self does, walks through the setup, and runs a quick demo based on your current project
Use Self to organic personality development through self-observation with light...
Invokes Self with the right parameters and returns the result directly in the conversation
What can I do with Self in my product manager workflow?
Lists the top use cases for Self, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/self/ 目录(个人级,所有项目可用),或 .claude/skills/self/(项目级)。重启 AI 客户端后,用 /self 主动调用,或让 AI 根据上下文自动发现并使用。
Self 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Self 可免费安装使用。请查阅仓库了解许可证信息。
Organic personality development through self-observation with lightweight reliability guards. Teaches agents to grow authentic identity over time by combinin...
Self 属于「Product Manager」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my product manager tasks using Self
Identifies repetitive steps in your workflow and sets up Self to handle them automatically