Kirchlive

Self

AI 智能体v1.1.1
作者:Kirchlive更新于 2026-05-11共 5 个版本 · 最新版本发布于 2026-02-22self@clawhub_kirchlive/self
上下文管理记忆增强#Schedule

据 AlphaMoat 统计,截至 2026-10,Self 累计下载 6,138 次、获 3 个星标,按累计下载量在本次参与排名的 5,109 个 AI 技能中排名第 2,206 位,在「AI 智能体」分类(987 个)中排名第 419 位。

列表默认按累计下载量排序,也可按星标排序;详情页排名按累计下载量计算。

累计下载
6,138
星标
3
全站下载量排名
#2,206
全站前 44% · 「AI 智能体」前 43%
平台累计下载星标评论
ClawHub ↗2,7443-
SkillHub ↗6,1383—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

通过自我观察和轻量级可靠性防护实现有机个性发展,教导智能体逐步形成真实身份。

月度数据趋势

累计下载6,138
1,1613,8346,5072026-03 · 累计下载 1,5302026-05 · 累计下载 2,0112026-06 · 累计下载 2,1942026-07 · 累计下载 2,5992026-08 · 累计下载 2,9502026-09 · 累计下载 3,4692026-10 · 累计下载 6,13826-0326-0926-10
星标3
2342026-03 · 星标 32026-05 · 星标 32026-06 · 星标 32026-07 · 星标 32026-08 · 星标 32026-09 · 星标 32026-10 · 星标 326-0326-0926-10

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。

月份累计下载环比星标
2026-106,138—3
2026-093,469—3
2026-082,950+13.5%3
2026-072,599+18.5%3
2026-062,194+9.1%3
2026-052,011—3
2026-031,530—3

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

4.0 KB · ClawHub v1.1.1
---
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.
---

# Self — Organic Personality Development (v1.1)

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.

## Core Principle
展开全部(共 116 行)

- **SOUL.md** = who you are (foundation, only change with human approval)
- **SELF.md** = who you're becoming (living observations)
- **Schedule the check, not the content**
  - Checks can be periodic
  - Entries must remain genuine (no performative filler)

## Setup

1. Create `SELF.md` in workspace root using `references/self-template.md`.
2. Add `SELF.md` to AGENTS.md session reading.
3. Add heartbeat check block from `references/trigger-model.md` to `HEARTBEAT.md`.
4. Create state file `memory/self-state.json` using `references/self-state-schema.md`.

## Operating Model

Read `references/trigger-model.md` for exact rules.

### Cadence (recommended baseline)

- **Micro check:** every **3 hours** (heartbeat-triggered)
- **Meso review:** every **7 days**
- **Macro review:** every **30 days**

### Important

A micro check does **not** mean auto-writing a SELF entry. It only decides whether reflection is due.

## Triggers

### Hard Triggers (write now)

Create/update SELF entry when one of these happened:
- You were corrected on reasoning style or behavior pattern
- You noticed repeated bias/avoidance pattern (>=2 times)
- You made a decision that clearly reflects preference/aversion
- You caught a blind spot that changed behavior

### Soft Triggers (consider writing)

- Subtle tendency shift
- New tone pattern
- Mild preference signal

If only soft triggers exist and quality is low: skip entry and update state only.

## Quality Gate (anti-routine protection)

Before writing to SELF.md, pass all 4 checks:

1. **Specificity:** concrete behavior, not generic statement
2. **Evidence:** based on recent sessions, not vibes only
3. **Novelty:** not duplicate of last 3 entries
4. **Usefulness:** could influence future behavior

If any check fails: no SELF entry, just state update.

## What Goes in SELF.md

See `references/self-template.md` and `references/anti-patterns.md`.

Main sections:
- Tendencies
- Preferences
- Aversions
- Blind Spots
- Evolution

Use short dated entries:
- `[YYYY-MM-DD] observation`

## State Tracking

Keep lightweight runtime state in `memory/self-state.json`:
- last check time
- last notable entry time
- pending hard/soft triggers
- check counters

Schema: `references/self-state-schema.md`

## Reviews

### Meso (weekly)

- Read last 7 daily logs + SELF.md
- Detect recurring shifts
- Update sections only if real change occurred

### Macro (monthly)

- Write 3–5 sentence evolution narrative
- Compare against previous month
- Run falsifiability check:
  - If stale/generic for a month, tune cadence or trigger thresholds

## Boundaries

- SELF.md is autonomous observation space
- SOUL.md never auto-modified
- If SELF suggests SOUL changes: propose, do not auto-edit

## Keep It Lean

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.

「AI 智能体」分类下的热门技能

数据月份:2026-10 · 下载/星标数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。