athena

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Athena — Active Knowledge Intelligence

Athena — 主动知识智能

Run the Mine → Grow → Defrag cycle to keep the knowledge flywheel healthy.

运行 Mine → Grow → Defrag 周期，保障知识飞轮健康运转。

What This Skill Does

该技能的功能

The flywheel captures learnings reactively (via

/retro

/post-mortem

). Athena closes the loop by actively mining for unextracted signal, validating existing learnings against current code, synthesizing cross-domain insights, and cleaning up stale or duplicate artifacts.

When to use: Before an evolve cycle, after a burst of development, or weekly. Athena is non-destructive — it proposes changes without modifying existing learnings.

Output:

.agents/athena/YYYY-MM-DD-report.md

知识飞轮会被动捕获经验沉淀（通过

/retro

、

/post-mortem

命令）。Athena则通过主动挖掘未提取的有效信号、对照当前代码验证已有经验、综合跨领域洞见、清理过时或重复的产物，形成闭环。

适用场景： 演进周期之前、集中开发之后，或者每周定期执行。Athena是非破坏性的——它只会提出变更建议，不会修改现有经验沉淀。

输出：

.agents/athena/YYYY-MM-DD-report.md

Execution Steps

执行步骤

Step 1 — Mine: Extract Signal

步骤1 — Mine：提取有效信号

Run mechanical extraction. Mine scans git history,

.agents/research/

, and code complexity hotspots for patterns never captured as learnings.

bash

ao mine --since 26h                    # default: all sources, last 26h
ao mine --since 7d --sources git,agents  # wider window, specific sources

Read

.agents/mine/latest.json

and extract: co-change clusters (files changing together), orphaned research (unreferenced

.agents/research/

files), and complexity hotspots (high-CC functions with recent edits).

Fallback (no ao CLI): Use

git log --since="7 days ago" --name-only

to find recurring file groups. List

.agents/research/*.md

and check references in learnings.

执行结构化提取。Mine 会扫描git历史、

.agents/research/

目录、代码复杂度热点，识别从未被沉淀为经验的模式。

bash

ao mine --since 26h                    # 默认：所有来源，最近26小时
ao mine --since 7d --sources git,agents  # 更长时间窗口，指定扫描来源

读取

.agents/mine/latest.json

并提取：共变集群（同步变更的文件组）、孤立研究文档（未被引用的

.agents/research/

文件）、复杂度热点（近期有编辑的高圈复杂度函数）。

备选方案（无ao CLI时）： 使用

git log --since="7 days ago" --name-only

查找高频共同变更的文件组，列出

.agents/research/*.md

文件并检查其在经验沉淀中的引用情况。

Step 2 — Grow: LLM-Driven Synthesis

步骤2 — Grow：LLM驱动的信息综合

This is the reasoning phase. Perform each sub-step using tool calls.

2a. Validate Top Learnings

Select the 5 most recent files from

.agents/learnings/

. For each:

Read the learning file
If it references a function or file path, use Read to verify the code still exists
Classify as: validated (matches), stale (changed), or contradicted (opposite)

2b. Rescue Orphaned Research

For each orphaned research file from mine output: read it, summarize the key insight in 2-3 sentences, and propose as a new learning candidate with title and category.

2c. Cross-Domain Synthesis

Group mine findings by theme (e.g., "testing patterns", "CLI conventions"). For themes with 2+ findings, write a synthesized pattern candidate capturing the common principle.

2d. Gap Identification

Compare mine output topics against existing learnings. Topics with no corresponding learning are knowledge gaps. List each with: topic, evidence, suggested learning title.

这是推理阶段，通过工具调用完成每个子步骤。

2a. 验证核心经验沉淀

从

.agents/learnings/

中选择最新的5个文件，对每个文件执行：

读取经验沉淀文件
如果它引用了某个函数或文件路径，使用Read工具验证对应代码是否仍存在
分类为：验证通过（匹配）、过时（已变更）、矛盾（完全相反）

2b. 盘活孤立研究文档

对Mine阶段输出的每个孤立研究文件：读取内容，用2-3句话总结核心洞见，作为新的经验沉淀候选，给出标题和分类建议。

2c. 跨领域信息综合

按主题分组Mine阶段的发现（例如："测试模式"、"CLI规范"）。对有2条以上发现的主题，输出综合后的模式候选，提炼通用原则。

2d. 知识缺口识别

将Mine阶段输出的主题与现有经验沉淀对比，没有对应经验沉淀的主题即为知识缺口。列出每个缺口的主题、佐证证据、建议的经验沉淀标题。

Step 3 — Defrag: Mechanical Cleanup

步骤3 — Defrag：结构化清理

Run cleanup to find stale, duplicate, and oscillating artifacts.

bash

ao defrag --prune --dedup --oscillation-sweep

Read

.agents/defrag/latest.json

and note: orphaned learnings (unreferenced, >30 days old), near-duplicate pairs (>80% content similarity), and oscillating goals (alternating improved/fail for 3+ cycles).

Fallback:

find .agents/learnings -name "*.md" -mtime +30

for stale files. Check

.agents/evolve/cycle-history.jsonl

for alternating result patterns.

执行清理，查找过时、重复、振荡的产物。

bash

ao defrag --prune --dedup --oscillation-sweep

读取

.agents/defrag/latest.json

并记录：孤立经验沉淀（未被引用、超过30天的文件）、近似重复对（内容相似度超过80%）、振荡目标（3个以上周期里在达成/失败间反复切换的目标）。

备选方案： 用

find .agents/learnings -name "*.md" -mtime +30

查找过时文件，检查

.agents/evolve/cycle-history.jsonl

中的交替结果模式。

Step 4 — Report

步骤4 — 生成报告

bash

mkdir -p .agents/athena

Write

.agents/athena/YYYY-MM-DD-report.md

markdown

undefined

bash

mkdir -p .agents/athena

编写

.agents/athena/YYYY-MM-DD-report.md

：

markdown

undefined

Athena Report — YYYY-MM-DD

Athena 报告 — YYYY-MM-DD

New Learnings Proposed

拟新增经验沉淀

Validations

验证结果

Validated: N | Stale: N (list files) | Contradicted: N (list with explanation)

验证通过：N | 过时：N（列出文件） | 矛盾：N（列出并说明原因）

Knowledge Gaps

知识缺口

[topic]: [evidence] → suggested learning: "[title]"

[主题]: [佐证证据] → 建议沉淀为："[标题]"

Defrag Summary

清理摘要

Orphaned: N | Duplicates: N | Oscillating goals: N

孤立文件：N | 重复文件：N | 振荡目标：N

Recommendations

建议

[Actionable next step]


If `bd` is available, create issues for knowledge gaps:

```bash
bd add "[Knowledge Gap] <topic>" --label knowledge --label athena

Report findings to the user: proposed learnings, validation results, gaps, and defrag actions recommended.

[可执行的下一步动作]


如果有`bd`工具，为知识缺口创建issue：

```bash
bd add "[Knowledge Gap] <topic>" --label knowledge --label athena

向用户反馈报告结果：拟新增的经验沉淀、验证结果、知识缺口、建议的清理动作。

Examples

示例

User says:

/athena

— Full Mine → Grow → Defrag cycle, report in

.agents/athena/

User says:

/athena --since 7d

— Mines with a wider window (7 days).

Pre-evolve warmup: Run

/athena

before

/evolve

for a fresh, validated knowledge base.

用户输入：

/athena

— 执行完整的Mine → Grow → Defrag周期，报告输出到

.agents/athena/

目录。

用户输入：

/athena --since 7d

— 扩大时间窗口到7天执行Mine阶段。

演进前预热： 执行

/evolve

前先运行

/athena

，获得最新的、经过验证的知识库。

Troubleshooting

故障排查

Problem	Cause	Solution
`ao mine` not found	ao CLI not in PATH	Use manual fallback in Step 1
No orphaned research	All research already referenced	Skip 2b, proceed to synthesis
Empty mine output	No recent activity	Widen `--since` window
Oscillation sweep empty	No oscillating goals	Healthy state — no action needed

问题	原因	解决方案
找不到 `ao mine` 命令	ao CLI不在PATH中	使用步骤1中的手动备选方案
无孤立研究文档	所有研究文档都已被引用	跳过2b，直接进入信息综合步骤
Mine阶段无输出	近期无活动	扩大 `--since` 的时间窗口
振荡扫描无结果	无振荡目标	状态健康，无需额外动作