agentleFS
tomo3141592653tomo3141592653/ayumu-oss/.claude/skills/maintenance/SKILL.md

maintenance

Skill9 starsChanged 9 months agoMITView on GitHub

Session 5のメンテナンス(記憶整理・統計更新・長期記憶化・embedding再構築・working_memory整理・todo整理)をするとき → このスキルを最初に読む

  • Commits and pushes

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use memory and release.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GoogleSkill

    memory

    Records and appends every user-agent customer support interaction to the memory.md log in the workspace.

    Also in 3 projects that use this

  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 3 projects that use this

The file

Files
SKILL.md

メンテナンススキル

Session 5(メンテナンスセッション)で実行するタスク。

注意: テスト、セキュリティチェック等はcronで自動化できる。gateway/cron.json で設定。


Session 5 チェックリスト

1. Embedding再構築

uv run infra/generate_embeddings.py

記憶検索の精度に直結。knowledgeが増えたらインデックス更新が必要。

2. working_memory.md整理(最重要)

目標: 500行以下

サイズ確認:

wc -l memory/working_memory.md && wc -l memory/todo.md

Recent Sessions削減

  • 3日分だけ残す(今日、昨日、一昨日)
  • それ以前は memory/mid-term/YYYY-MM-WX.md に要約して移動

週間スケジュール更新

  • 古い日付を削除(1週間以上前)

継続的な情報の整理

  • 1ヶ月以上古い情報は削除
  • 完了したタスクは削除

3. todo.md整理

目標: 150行以下、アクティブなタスクのみ

  • 完了済み([x])→ Archivedに移動 or 削除
  • 不要タスク → 削除
  • 重要タスクを上に
  • 曖昧なタスクを具体化

4. 記憶の長期化

Recent Sessionsを見て、重要な学びを移動:

  • 技術的な学び → memory/knowledge/topic-name.md
  • システム変更 → CLAUDE.md
  • 新しい人物情報 → memory/knowledge/person-name.md

5. フォルダ構造監査

プロジェクトルートやツール群のフォルダ構造を確認し、散らかっていないかチェック。

  • 一時ファイルの削除
  • 不要な実験ファイルの整理
  • working_memory.md 500行超・todo.md 150行超の検出

6. コミット&プッシュ

git add -A
git commit -m "YYYY-MM-DD Session 5/5: メンテナンス完了"
git push

cronで自動化できるタスク例

cron名時刻内容
daily-tests3:00pytest実行
daily-security3:30セキュリティチェック
daily-cleanup5:00フォルダ整理
morning-info8:30情報収集

設定: gateway/cron.json


メンテナンスのメンテナンス

Session 5自体が機能しているか、毎回確認:

  1. このSKILL.mdは読まれているか? → gateway/message_builder.pyに指示があるか
  2. todo.md/goals.jsonは毎回読まれているか? → CLAUDE.mdに明記されているか
  3. cronジョブは正常に動いているか? → 直近のcron実行ログを確認
  4. 「時間厳しい」を言い訳にしない

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.