Skip to content
cccskills
FreePublished on GitHub

export-knowledge

Reusable learnings: セッション中の再利用知見を構造化し、ドメイン別(microsoft / copilot など)に振り分けて出力。Use when: knowledge, lessons learned, 知見化。

作業ログは export-session-log、対話再現は export-copilot-session-dialogue を使う

The English summary is being prepared. Showing the original description.

Works withAzure
See how to install

Files included (2)

  • SKILL.md4.9 KB
  • LICENSE.txt5.2 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

<!-- syncToGlobal: true --> <!-- author: aktsmm --> <!-- repository: https://github.com/aktsmm/Agent-Customization --> <!-- license: CC BY-NC-SA 4.0 --> <!-- copyright: Copyright (c) 2025 aktsmm -->

export knowledge

このセッションで得られた知見を構造化してエクスポートします。 ドメインを自動判定し、適切な出力先に振り分けます。

Core Contract

  • セッション知見を microsoft または copilot ドメインへ振り分ける
  • primary category を 1 つ選び、残りは tags に回す
  • Markdown と index の両方を更新する
  • 判定に迷う場合だけユーザー確認する

Domain Routing

出力先の優先順は、ユーザー指定 > 環境変数 > 明示された workspace/local > 確認。

ドメインキーワード
microsoftAzure, M365, Entra ID, Intune, Defender, Power Platform, Windows Server, SQL Server, Dynamics 365, Copilot Studio
copilotGitHub Copilot, MCP, Agent, Prompt, VS Code 拡張, VS Code, Workflow, Skills, Context Engineering
ドメイン環境変数
microsoft$env:EXPORT_KNOWLEDGE_MICROSOFT_DIR\{category}\
copilot$env:EXPORT_KNOWLEDGE_COPILOT_DIR\{category}\
  • 判定に迷う場合はユーザーに確認
  • 1セッションで両ドメインの知見がある場合は、それぞれ個別にエクスポート
  • 対応する環境変数が未設定または path が存在しない場合は、workspace/local が明示されたときだけ {workspace}/_output-knowledge/{domain}/{category}/ を使い、それ以外は作成前に確認する

出力先の上書き

条件出力先
デフォルト上記ドメイン別の環境変数。未設定または path 不在なら、workspace/local の明示がない限り確認
「workspace」「ローカル」等{workspace}/_output-knowledge/{domain}/{category}/
パス指定あり指定パス

Categories

microsoft ドメイン

azure-compute / azure-networking / azure-storage / azure-security / azure-identity / azure-monitoring / azure-migration / azure-arc / m365 / intune / defender / entra-id / power-platform / licensing / architecture / troubleshooting / lessons-learned

copilot ドメイン

prompts / agents / workflows / subagent / context / mcp / skills / debugging / automation / evaluation / vscode-settings / lessons-learned / templates

Workflow

  1. セッションから知見を抽出(技術的発見、エラー解決、設計判断、参照 URL)
  2. ドメインを判定(microsoft or copilot)
  3. カテゴリを1つ選定、他はタグに
  4. 以下の形式でMarkdownファイルを作成
  5. ファイル名: {YYYYMMDD}-{topic-slug}.md
  6. インデックス更新(ドメインに応じた _index フォルダ)

Output Requirements

必須要素:

  • frontmatter: title, datetime, domain, primaryCategory, tags
  • references
  • ## 知見
  • ## 具体例
  • microsoft ドメインなら products と ## 顧客への影響

テンプレート:

---
title: "知見のタイトル"
datetime: { エクスポート時刻 }
domain: microsoft | copilot
primaryCategory: { カテゴリ }
tags: [tag1, tag2]
products: [製品名] # microsoft ドメインのみ
references:
  - url: https://...
    title: ドキュメントタイトル
---

## 知見

(本文)

## 具体例

(コード例・構成例があれば)

## 顧客への影響

(microsoft ドメインで該当する場合:影響範囲・対応推奨)

Index Targets

各ドメインで解決した <resolved-root>\_index\knowledge-index.json を使う。

resolved-root は Markdown の出力 root と同じ場所を使う。root が決まるまでファイル作成と index 更新を開始しない。

ルール

  • エクスポート前に Get-Date -Format "yyyy-MM-ddTHH:mm:ss" を実行し、その結果を datetime に使用する
  • microsoft ドメイン: 公式ドキュメント URL(learn.microsoft.com)を必ず含める
  • microsoft ドメイン: Azure Updates の情報がある場合は updates URL も含める
  • microsoft ドメイン: 顧客対応で得た知見は個人情報・社名をマスクしてから記録する

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Design, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or hook before escalating to multi-agent design. Use for .agent.md / .instructions.md / .prompt.md / AGENTS.md work, workflow architecture, orchestration planning, scheduled automation model allocation, or when agent workflows may be overkill. Triggers on 'agent workflow', 'create agent', 'automation models', 'ワークフロー設計', 'orchestrator'.

The English summary is being prepared. Showing the original description.

aktsmm/Agent-Skills26Updated Oct 19, 2026

Design, run, and review fair performance, token, and cost comparisons across GitHub Copilot CLI, Codex CLI, and direct model APIs. Use for AI CLI benchmark, Copilot vs Codex, prompt-cache diagnosis, cache read/write analysis, fresh-process latency measurement, token-cost comparison, or when a benchmark must separate provider caching from local CLI caches.

The English summary is being prepared. Showing the original description.

aktsmm/Agent-Skills26Updated Oct 19, 2026

Analyze historical VS Code GitHub Copilot Chat sessions by model, reasoning effort, AIU, time, reliability, workflow behavior, and external quality evidence, or safely prune workspace-scoped local chat history by age. Use for session analysis, repeated-task retrospectives, model evaluation, cost/performance analysis, and old session cleanup.

The English summary is being prepared. Showing the original description.

aktsmm/Agent-Skills26Updated Oct 19, 2026

Create reproducible animated infographic GIFs from structured data or measured results, with audience-language labels, explicit timing semantics, representative-frame QA, and a static fallback. Use when asked for GIF生成, animated infographic, 動的インフォグラフィック, 結果が流れる図, animated benchmark, or a blog/SNS animation whose displayed metrics must remain traceable to source data.

The English summary is being prepared. Showing the original description.

aktsmm/Agent-Skills26Updated Oct 19, 2026

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid. Also use for Archify, interactive or animated HTML diagrams, インタラクティブ図, 動く構成図. When an editable .drawio file is required, use the draw.io workflow instead and treat Archify HTML only as a supplement.

The English summary is being prepared. Showing the original description.

aktsmm/Agent-Skills26Updated Oct 19, 2026

Generate ASCII-art text banners for terminals, READMEs, and CLI startup messages. Use when a user asks for an ASCII banner, text art, バナー, アスキーアート, or a decorative header for a script/README.

The English summary is being prepared. Showing the original description.

aktsmm/Agent-Skills26Updated Oct 19, 2026

See all skills by aktsmm

Report a problem with this skill