agentleFS
morodomimorodomi/dev-crew/skills/learn/SKILL.md

learn

Skill1 starsChanged 26 days agoMITView on GitHub

セッションからパターンを抽出し instinct として蓄積する。「learn」「パターン抽出」「セッション振り返り」で起動。

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-anydoc, add-clidash and 10 more.

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.
  • TomGranotSkill

    add-anydoc

    Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.

    Also in 5 projects that use this

  • TomGranotSkill

    add-clidash

    Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.

    Also in 5 projects that use this

  • seek888Skill

    open-gstack-browser

    Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

    Also in 11 projects that use this

  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • MicrosoftSkill

    add-codex

    Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

    Also in 6 projects that use this

  • MicrosoftSkill

    add-deltachat

    Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.

    Also in 6 projects that use this

  • +5 more from TomGranot
  • +1 more from microsoft

The file

Files
SKILL.md

Learn - セッションパターン抽出

セッションの作業パターンを検出し、instinct (構造化パターン) として蓄積する。

前提

  • プロジェクトディレクトリ内で実行すること
  • Git 管理下であること (git log / git diff を使用)

実行手順

Step 1: 初回チェック (Empty State)

蓄積先ディレクトリを確認。存在しない場合は自動作成しオンボーディングメッセージを表示:

dev-crew learn へようこそ。
learn はセッションの作業パターンを記録し、evolve でスキルに進化させます。
初回セットアップを実行しました。
mkdir -p ${CLAUDE_PLUGIN_DATA}/instincts/

Step 2: 入力ソース収集 + TF-IDF サマリ計算

以下の情報を収集する:

ソースコマンド
Cycle docls -t docs/cycles/*.md 2>/dev/null | head -1
変更履歴git log --oneline -20
変更ファイルgit diff --name-only HEAD~5..HEAD
observationscat ${CLAUDE_PLUGIN_DATA}/observations/log.jsonl 2>/dev/null

TF-IDF サマリ計算

scripts/tfidf-summary.sh で observations (log.jsonl) からセッション横断の TF-IDF スコアを算出し、tfidf_summary として observer に渡す。

TFIDF_JSON="$(bash scripts/tfidf-summary.sh)"

空配列 [] が返った場合 (ブートストラップ期間 or データなし)、observer に tfidf_summary を渡さない。

詳細: reference.md

Step 3: ユーザー補足情報

AskUserQuestion で確認:

  • 「このセッションで気づいたパターンはありますか?」
  • 選択肢: エラー解決 / ワークフロー改善 / ツール選好 / 特になし

Step 4: observer エージェントに委譲

Task tool で observer を起動し、収集した入力ソースを渡す:

Task(subagent_type: "dev-crew:observer", prompt: "...")

Step 5: 品質フィルタ + 保存

observer の出力から instinct を選別:

confidence判定
>= 0.5保存 (${CLAUDE_PLUGIN_DATA}/instincts/ に JSONL 追記)
< 0.5破棄 (理由付きで報告)

confidence >= 0.8 の instinct は MEMORY.md 昇格候補としてユーザーに提示する。棲み分けルール詳細: reference.md

Step 6: 結果報告

N 件のパターンを保存しました。
現在の蓄積: X 件。evolve 可能まであと Y 件。

保存成功後、タイムスタンプを更新:

date -u +"%Y-%m-%dT%H:%M:%SZ" > ${CLAUDE_PLUGIN_DATA}/observations/.last-learn-timestamp

Reference

詳細: reference.md

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.