flywheel技能：监控知识飞轮健康状况，优化AI代理学习流程与知识管理

flywheel by boshu2/agentops

258 周安装量

220 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/boshu2/agentops --skill flywheel

AI/机器学习监控知识管理

🇨🇳中文介绍

Flywheel Skill

监控知识飞轮的健康状况。

飞轮模型

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

速度 = 知识流经的速率摩擦 = 阻碍飞轮运转的瓶颈

执行步骤

给定 /flywheel 命令：

步骤 1：测量知识池

# 统计顶层工件文件（避免统计目录）
LEARNINGS=$(find .agents/learnings -maxdepth 1 -type f 2>/dev/null | wc -l)

PATTERNS=$(find .agents/patterns -maxdepth 1 -type f 2>/dev/null | wc -l)

RESEARCH=$(find .agents/research -maxdepth 1 -type f 2>/dev/null | wc -l)

RETROS=$(find .agents/retros -maxdepth 1 -type f 2>/dev/null | wc -l)

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

步骤 2：检查近期活动

# 近期学习成果（过去 7 天）
find .agents/learnings -maxdepth 1 -type f -mtime -7 2>/dev/null | wc -l

# 近期研究
find .agents/research -maxdepth 1 -type f -mtime -7 2>/dev/null | wc -l

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

步骤 3：检测陈旧性

# 旧工件（超过 30 天未修改）
find .agents/ -name "*.md" -mtime +30 2>/dev/null | wc -l

步骤 3.5：检查缓存健康状况

if command -v ao &>/dev/null; then
  # 获取引用报告（缓存指标）
  CITE_REPORT=$(ao metrics cite-report --json --days 30 2>/dev/null)
  if [ -n "$CITE_REPORT" ]; then
    HIT_RATE=$(echo "$CITE_REPORT" | jq -r '.hit_rate // "unknown"')
    UNCITED=$(echo "$CITE_REPORT" | jq -r '(.uncited_learnings // []) | length')
    STALE_90D=$(echo "$CITE_REPORT" | jq -r '.staleness["90d"] // 0')
    echo "Cache hit rate: $HIT_RATE"
    echo "Uncited learnings: $UNCITED"
    echo "Stale (90d uncited): $STALE_90D"
  fi
else
  # 无 ao 回退方案：根据文件计算近似指标
  echo "Cache health (ao-free fallback):"

  # 过去 30 天内修改的学习成果（活跃池）
  ACTIVE_30D=$(find .agents/learnings/ -name "*.md" -mtime -30 2>/dev/null | wc -l | tr -d ' ')
  echo "Active learnings (30d): $ACTIVE_30D"

  # 等待提升的 Forge 候选
  FORGE_PENDING=$(ls .agents/forge/*.md 2>/dev/null | wc -l | tr -d ' ')
  echo "Forge candidates pending: $FORGE_PENDING"

  # 引用跟踪（如果 citations.jsonl 存在）
  if [ -f .agents/ao/citations.jsonl ]; then
    CITATION_COUNT=$(wc -l < .agents/ao/citations.jsonl | tr -d ' ')
    UNIQUE_CITED=$(grep -o '"learning_file":"[^"]*"' .agents/ao/citations.jsonl 2>/dev/null | sort -u | wc -l | tr -d ' ')
    echo "Total citations: $CITATION_COUNT"
    echo "Unique learnings cited: $UNIQUE_CITED"
  else
    echo "No citation data (citations.jsonl not found)"
  fi

  # 会话结果（如果 outcomes.jsonl 存在）
  if [ -f .agents/ao/outcomes.jsonl ]; then
    OUTCOME_COUNT=$(wc -l < .agents/ao/outcomes.jsonl | tr -d ' ')
    echo "Session outcomes recorded: $OUTCOME_COUNT"
  fi
fi

步骤 4：检查 ao CLI 状态

if command -v ao &>/dev/null; then
  ao metrics flywheel status 2>/dev/null || echo "ao metrics flywheel status unavailable"
  ao status 2>/dev/null || echo "ao status unavailable"
  ao maturity --scan 2>/dev/null || echo "ao maturity unavailable"
  ao promote-anti-patterns --dry-run 2>/dev/null || echo "ao promote-anti-patterns unavailable"
  ao badge 2>/dev/null || echo "ao badge unavailable"

  # 知识维护
  ao dedup --merge 2>/dev/null || true
  ao contradict 2>/dev/null || true
  ao constraint review 2>/dev/null || true
  ao curate status 2>/dev/null || true
  ao metrics health 2>/dev/null || true
  ao metrics cite-report --days 30 2>/dev/null || true

  # 主动修剪：归档陈旧内容，驱逐低效用内容
  ao maturity --expire --archive 2>/dev/null || true
  ao maturity --evict --archive 2>/dev/null || true
else
  echo "ao CLI not available — using file-based metrics"

  # 知识池清单
  echo "Pool depths:"
  for pool in learnings patterns forge knowledge research retros; do
    COUNT=$(ls .agents/${pool}/*.md 2>/dev/null | wc -l | tr -d ' ')
    echo "  $pool: $COUNT"
  done

  # 全局模式
  GLOBAL_COUNT=$(ls ~/.claude/patterns/*.md 2>/dev/null | wc -l | tr -d ' ')
  echo "  global patterns: $GLOBAL_COUNT"

  # 检查可提升的学习成果（参见 references/promotion-tiers.md）
  echo "See: skills/flywheel/references/promotion-tiers.md for tier definitions"
fi

步骤 4.5：处理指标（来自技能遥测）

如果 .agents/ao/skill-telemetry.jsonl 存在，使用 jq 提取：按技能分类的调用次数、每个技能的平均周期时间、关卡失败率。将其包含在健康报告（步骤 6）的 ## Process Metrics 部分。

步骤 5：验证工件一致性

交叉引用验证：扫描知识工件中损坏的内部引用。使用 scripts/artifact-consistency.sh（方法记录在 references/artifact-consistency.md 中）。默认白名单位于 references/artifact-consistency-allowlist.txt；使用 --no-allowlist 进行完整的原始审计。

健康指标：>90% = 健康，70-90% = 警告，<70% = 严重。

步骤 6：编写健康报告

写入文件： .agents/flywheel-status.md

# 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> |

## Velocity (Last 7 Days)
- Sessions with extractions: <count>
- New learnings: <count>
- New patterns: <count>

## Artifact Consistency
- References scanned: <count>
- Broken references: <count>
- Consistency score: <percentage>%
- Status: <Healthy/Warning/Critical>

## Cache Health
- Hit rate: <percentage>%
- Uncited learnings: <count>
- Stale (90d uncited): <count>
- Status: <Healthy/Warning/Critical>

## Health Status
<Healthy/Warning/Critical>

## Friction Points
- <issue 1>
- <issue 2>

## Recommendations
1. <recommendation>
2. <recommendation>

步骤 7：向用户报告

飞轮整体健康状况
知识池深度
近期活动
任何摩擦点
建议

指标	健康	警告	严重
每周学习成果	3+	1-2	0
陈旧工件	<20%	20-50%	>50%
研究/计划比率	>0.5	0.2-0.5	<0.2
缓存命中率	>80%	50-80%	<50%

阅读 references/cache-eviction.md 了解完整的驱逐流程（被动跟踪 → 置信度衰减 → 成熟度扫描 → 归档）。

定期监控 - 飞轮需要关注
解决摩擦 - 瓶颈会减缓复合效应
为飞轮提供动力 - 运行 /retro 和 /post-mortem
修剪陈旧知识 - 归档旧工件

用户输入： /flywheel — 统计知识池深度，检查近期活动，验证工件一致性，将健康报告写入 .agents/flywheel-status.md。

钩子触发： 在 /post-mortem 之后 — 比较当前与历史指标，标记速度下降和摩擦点。

问题	原因	解决方案
所有知识池计数为零	`.agents/` 目录缺失或为空	运行 `/post-mortem` 或 `/retro` 来填充知识池
速度始终为零	近期没有提取（过去 7 天）	运行 `/retro` 或 `/post-mortem` 来提取和索引学习成果
"ao CLI not available"	ao 命令未安装或不在 PATH 中	安装 ao CLI 或使用手动知识池计数回退方案
陈旧工件 >50%	距离上次会话时间过长或仓库不活跃	运行 `/provenance --stale` 来审计和归档旧工件

🇺🇸English

Flywheel Skill

Monitor the knowledge flywheel health.

The Flywheel Model

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

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

Execution Steps

Given /flywheel:

Step 1: Measure Knowledge Pools

# Count top-level artifact files (avoid counting directories)
LEARNINGS=$(find .agents/learnings -maxdepth 1 -type f 2>/dev/null | wc -l)

PATTERNS=$(find .agents/patterns -maxdepth 1 -type f 2>/dev/null | wc -l)

RESEARCH=$(find .agents/research -maxdepth 1 -type f 2>/dev/null | wc -l)

RETROS=$(find .agents/retros -maxdepth 1 -type f 2>/dev/null | wc -l)

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

Step 2: Check Recent Activity

# Recent learnings (last 7 days)
find .agents/learnings -maxdepth 1 -type f -mtime -7 2>/dev/null | wc -l

# Recent research
find .agents/research -maxdepth 1 -type f -mtime -7 2>/dev/null | wc -l

Step 3: Detect Staleness

# Old artifacts (> 30 days without modification)
find .agents/ -name "*.md" -mtime +30 2>/dev/null | wc -l

Step 3.5: Check Cache Health

if command -v ao &>/dev/null; then
  # Get citation report (cache metrics)
  CITE_REPORT=$(ao metrics cite-report --json --days 30 2>/dev/null)
  if [ -n "$CITE_REPORT" ]; then
    HIT_RATE=$(echo "$CITE_REPORT" | jq -r '.hit_rate // "unknown"')
    UNCITED=$(echo "$CITE_REPORT" | jq -r '(.uncited_learnings // []) | length')
    STALE_90D=$(echo "$CITE_REPORT" | jq -r '.staleness["90d"] // 0')
    echo "Cache hit rate: $HIT_RATE"
    echo "Uncited learnings: $UNCITED"
    echo "Stale (90d uncited): $STALE_90D"
  fi
else
  # ao-free fallback: compute approximate metrics from files
  echo "Cache health (ao-free fallback):"

  # Learnings modified in last 30 days (active pool)
  ACTIVE_30D=$(find .agents/learnings/ -name "*.md" -mtime -30 2>/dev/null | wc -l | tr -d ' ')
  echo "Active learnings (30d): $ACTIVE_30D"

  # Forge candidates awaiting promotion
  FORGE_PENDING=$(ls .agents/forge/*.md 2>/dev/null | wc -l | tr -d ' ')
  echo "Forge candidates pending: $FORGE_PENDING"

  # Citation tracking (if citations.jsonl exists)
  if [ -f .agents/ao/citations.jsonl ]; then
    CITATION_COUNT=$(wc -l < .agents/ao/citations.jsonl | tr -d ' ')
    UNIQUE_CITED=$(grep -o '"learning_file":"[^"]*"' .agents/ao/citations.jsonl 2>/dev/null | sort -u | wc -l | tr -d ' ')
    echo "Total citations: $CITATION_COUNT"
    echo "Unique learnings cited: $UNIQUE_CITED"
  else
    echo "No citation data (citations.jsonl not found)"
  fi

  # Session outcomes (if outcomes.jsonl exists)
  if [ -f .agents/ao/outcomes.jsonl ]; then
    OUTCOME_COUNT=$(wc -l < .agents/ao/outcomes.jsonl | tr -d ' ')
    echo "Session outcomes recorded: $OUTCOME_COUNT"
  fi
fi

Step 4: Check ao CLI Status

if command -v ao &>/dev/null; then
  ao metrics flywheel status 2>/dev/null || echo "ao metrics flywheel status unavailable"
  ao status 2>/dev/null || echo "ao status unavailable"
  ao maturity --scan 2>/dev/null || echo "ao maturity unavailable"
  ao promote-anti-patterns --dry-run 2>/dev/null || echo "ao promote-anti-patterns unavailable"
  ao badge 2>/dev/null || echo "ao badge unavailable"

  # Knowledge maintenance
  ao dedup --merge 2>/dev/null || true
  ao contradict 2>/dev/null || true
  ao constraint review 2>/dev/null || true
  ao curate status 2>/dev/null || true
  ao metrics health 2>/dev/null || true
  ao metrics cite-report --days 30 2>/dev/null || true

  # Active pruning: archive stale, evict low-utility
  ao maturity --expire --archive 2>/dev/null || true
  ao maturity --evict --archive 2>/dev/null || true
else
  echo "ao CLI not available — using file-based metrics"

  # Pool inventory
  echo "Pool depths:"
  for pool in learnings patterns forge knowledge research retros; do
    COUNT=$(ls .agents/${pool}/*.md 2>/dev/null | wc -l | tr -d ' ')
    echo "  $pool: $COUNT"
  done

  # Global patterns
  GLOBAL_COUNT=$(ls ~/.claude/patterns/*.md 2>/dev/null | wc -l | tr -d ' ')
  echo "  global patterns: $GLOBAL_COUNT"

  # Check for promotion-ready learnings (see references/promotion-tiers.md)
  echo "See: skills/flywheel/references/promotion-tiers.md for tier definitions"
fi

Step 4.5: Process Metrics (from skill telemetry)

If .agents/ao/skill-telemetry.jsonl exists, use jq to extract: invocations by skill, average cycle time per skill, gate failure rates. Include in health report (Step 6) under ## Process Metrics.

Step 5: Validate Artifact Consistency

Cross-reference validation: scan knowledge artifacts for broken internal references. Use scripts/artifact-consistency.sh (method documented in references/artifact-consistency.md). Default allowlist lives at references/artifact-consistency-allowlist.txt; use --no-allowlist for a full raw audit.

Health indicator: >90% = Healthy, 70-90% = Warning, <70% = Critical.

Step 6: Write Health Report

Write to: .agents/flywheel-status.md

# 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> |

## Velocity (Last 7 Days)
- Sessions with extractions: <count>
- New learnings: <count>
- New patterns: <count>

## Artifact Consistency
- References scanned: <count>
- Broken references: <count>
- Consistency score: <percentage>%
- Status: <Healthy/Warning/Critical>

## Cache Health
- Hit rate: <percentage>%
- Uncited learnings: <count>
- Stale (90d uncited): <count>
- Status: <Healthy/Warning/Critical>

## Health Status
<Healthy/Warning/Critical>

## Friction Points
- <issue 1>
- <issue 2>

## Recommendations
1. <recommendation>
2. <recommendation>

Step 7: Report to User

Tell the user:

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

Health Indicators

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
Cache hit rate	>80%	50-80%	<50%

Cache Eviction

Read references/cache-eviction.md for the full eviction pipeline (passive tracking → confidence decay → maturity scan → archive).

Key Rules

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

Examples

User says: /flywheel — Counts pool depths, checks recent activity, validates artifact consistency, writes health report to .agents/flywheel-status.md.

Hook trigger: After /post-mortem — Compares current vs historical metrics, flags velocity drops and friction points.

Troubleshooting

Problem	Cause	Solution
All pool counts zero	`.agents/` directory missing or empty	Run `/post-mortem` or `/retro` to seed knowledge pools
Velocity always zero	No recent extractions (last 7 days)	Run `/retro` or `/post-mortem` to extract and index learnings
"ao CLI not available"	ao command not installed or not in PATH	Install ao CLI or use manual pool counting fallback
Stale artifacts >50%	Long time since last session or inactive repo	Run to audit and archive old artifacts

Reference Documents

Weekly Installs

207

Repository

boshu2/agentops

GitHub Stars

197

First Seen

Feb 2, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykPass

Installed on

codex204

github-copilot203

opencode202

amp202

kimi-cli202

gemini-cli202

超能力技能使用指南：AI助手技能调用优先级与工作流程详解

41,800 周安装

/provenance --stale

flywheel技能：监控知识飞轮健康状况，优化AI代理学习流程与知识管理

🇨🇳中文介绍

Flywheel Skill

飞轮模型

执行步骤

步骤 1：测量知识池

步骤 2：检查近期活动

相关 Skills

步骤 3：检测陈旧性

步骤 3.5：检查缓存健康状况

步骤 4：检查 ao CLI 状态

步骤 4.5：处理指标（来自技能遥测）

步骤 5：验证工件一致性

步骤 6：编写健康报告

步骤 7：向用户报告

健康指标

缓存驱逐

关键规则

示例

故障排除

参考文档

🇺🇸English

Flywheel Skill

The Flywheel Model

Execution Steps

Step 1: Measure Knowledge Pools

Step 2: Check Recent Activity

Step 3: Detect Staleness

Step 3.5: Check Cache Health

Step 4: Check ao CLI Status

Step 4.5: Process Metrics (from skill telemetry)

Step 5: Validate Artifact Consistency

Step 6: Write Health Report

Step 7: Report to User

Health Indicators

Cache Eviction

Key Rules

Examples

Troubleshooting

Reference Documents

最新 Skills