flywheel

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Flywheel Skill

Monitor the knowledge flywheel health.

监控知识飞轮的健康状态。

The Flywheel Model

飞轮模型

Sessions → Transcripts → Forge → Pool → Promote → Knowledge
     ↑                                               │
     └───────────────────────────────────────────────┘
                    Future sessions find it

Velocity = Rate of knowledge flowing through Friction = Bottlenecks slowing the flywheel

Sessions → Transcripts → Forge → Pool → Promote → Knowledge
     ↑                                               │
     └───────────────────────────────────────────────┘
                    Future sessions find it

流转速度 = 知识在系统中的流动速率 摩擦阻力 = 拖慢飞轮运转的瓶颈

Execution Steps

执行步骤

Given

/flywheel

当触发

/flywheel

指令时：

Step 1: Measure Knowledge Pools

步骤1：统计知识存储池

bash

undefined

bash

undefined

Count learnings

LEARNINGS=$(ls .agents/learnings/ 2>/dev/null | wc -l)

Count patterns

PATTERNS=$(ls .agents/patterns/ 2>/dev/null | wc -l)

Count research

RESEARCH=$(ls .agents/research/ 2>/dev/null | wc -l)

Count retros

RETROS=$(ls .agents/retros/ 2>/dev/null | wc -l)

echo "Learnings: $LEARNINGS" echo "Patterns: $PATTERNS" echo "Research: $RESEARCH" echo "Retros: $RETROS"

undefined

RETROS=$(ls .agents/retros/ 2>/dev/null | wc -l)

echo "Learnings: $LEARNINGS" echo "Patterns: $PATTERNS" echo "Research: $RESEARCH" echo "Retros: $RETROS"

undefined

Step 2: Check Recent Activity

步骤2：检查近期活动

bash

undefined

bash

undefined

Recent learnings (last 7 days)

find .agents/learnings/ -mtime -7 2>/dev/null | wc -l

Recent research

find .agents/research/ -mtime -7 2>/dev/null | wc -l

undefined

find .agents/research/ -mtime -7 2>/dev/null | wc -l

undefined

Step 3: Detect Staleness

步骤3：检测内容陈旧性

bash

undefined

bash

undefined

Old artifacts (> 30 days without modification)

find .agents/ -name "*.md" -mtime +30 2>/dev/null | wc -l

undefined

find .agents/ -name "*.md" -mtime +30 2>/dev/null | wc -l

undefined

Step 4: Check ao CLI Status

步骤4：检查ao CLI状态

bash

ao forge status 2>/dev/null || echo "ao CLI not available"

bash

ao forge status 2>/dev/null || echo "ao CLI not available"

Step 5: Write Health Report

步骤5：生成健康报告

Write to:

.agents/flywheel-status.md

markdown

undefined

写入路径：

.agents/flywheel-status.md

markdown

undefined

Knowledge Flywheel Health

Date: YYYY-MM-DD

Pool Depths

Pool	Count	Recent (7d)
Learnings	<count>	<count>
Patterns	<count>	<count>
Research	<count>	<count>
Retros	<count>	<count>

Pool	Count	Recent (7d)
Learnings	<count>	<count>
Patterns	<count>	<count>
Research	<count>	<count>
Retros	<count>	<count>

Velocity (Last 7 Days)

Sessions with extractions: <count>
New learnings: <count>
New patterns: <count>

Sessions with extractions: <count>
New learnings: <count>
New patterns: <count>

Health Status

Friction Points

<issue 1>
<issue 2>

<issue 1>
<issue 2>

Recommendations

<recommendation>
<recommendation>

undefined

<recommendation>
<recommendation>

undefined

Step 6: Report to User

步骤6：向用户汇报

Tell the user:

Overall flywheel health
Knowledge pool depths
Recent activity
Any friction points
Recommendations

向用户告知以下内容：

飞轮整体健康状态
知识存储池深度
近期活动情况
存在的摩擦阻力点
优化建议

Health Indicators

健康指标

Metric	Healthy	Warning	Critical
Learnings/week	3+	1-2	0
Stale artifacts	<20%	20-50%	>50%
Research/plan ratio	>0.5	0.2-0.5	<0.2

指标	健康状态	警告状态	严重状态
每周新增学习内容	3+	1-2	0
陈旧内容占比	<20%	20-50%	>50%
研究/计划占比	>0.5	0.2-0.5	<0.2

Key Rules

核心规则

Monitor regularly - flywheel needs attention
Address friction - bottlenecks slow compounding
Feed the flywheel - run /retro and /post-mortem
Prune stale knowledge - archive old artifacts

定期监控 - 飞轮需要持续关注
消除阻力 - 瓶颈会减缓知识复利效应
补充飞轮动力 - 执行/retro和/post-mortem指令
清理陈旧知识 - 归档旧的内容资产