本文へ移動
cccskills
無料GitHub で公開

power-automate-ops

Operate and verify Microsoft Power Automate cloud flows in the browser, and migrate them between environments. Use when creating, editing, testing, or troubleshooting Power Automate flows, Forms triggers, Teams connector posts/replies, Flow Checker errors, run history, or Power Automate UI automation; also when rebuilding a flow in another environment and stopping or deleting the old one, when DLP or connection limits block editing or saving, when adding co-owners, or when checking Dataverse for Teams retirement and upgrade. Triggers: フロー移行, 環境移行, 旧フロー削除, DLP で保存できない, 共同所有者, Dataverse for Teams アップグレード. Do not use for Logic Apps IaC or general browser automation unrelated to Power Automate.

日本語の概要は準備中です。原文の説明を表示しています。

aktsmm/Agent-Skillsスター 26(GitHub 26 + cccskills 0)

実行スコア 未検証

インストール方法を見る

含まれるファイル(6)

  • SKILL.md6.1 KB
  • LICENSE.txt235 B
  • references/forms-teams-flow.md2.8 KB
  • references/migration.md3.5 KB
  • references/power-automate-ui-gotchas.md2.4 KB
  • skill-license.json683 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Power Automate Ops

Use this skill for hands-on Power Automate cloud-flow work in the browser: create, edit, repair, test, and verify flows that integrate Microsoft Forms, Teams, Outlook, SharePoint, and similar Microsoft 365 connectors.

When to Use

  • User asks to create or edit a Power Automate cloud flow.
  • User mentions Power Automate, cloud flow, フロー作成, フロー修正, フローチェッカー, 実行履歴, Forms trigger, Teams connector, or Workflows app.
  • A flow posts visible content to Teams/email and needs safe preview, confirmation, testing, and run-history verification.
  • The task involves brittle Power Automate browser UI operations, dynamic content tokens, connector parameters, or action replacement.
  • A flow must be rebuilt in another environment and the old one stopped or deleted, DLP/ACP blocks editing or saving, a co-owner must be added, or Dataverse for Teams retirement/upgrade needs checking: follow references/migration.md.

Do Not Use

  • Do not use for Azure Logic Apps infrastructure-as-code or ARM/Bicep authoring.
  • Do not use for Power Apps app-building unless the task is specifically about an embedded Power Automate flow.
  • Do not re-teach browser automation mechanics. If Playwright/CDP/UI recovery is the main problem, treat general browser automation as a separate concern and keep this skill focused on Power Automate semantics.

Safety Gates

  1. Freeze the goal, trigger, destination, visible recipients, and done criteria before editing.
  2. For any action that sends or posts content visible to others, show the exact recipient/channel/thread and message content, then wait for explicit user confirmation before testing or sending.
  3. Treat Forms responses, email addresses, names, company names, and Teams/chat content as private user data. Do not move them outside the approved destination.
  4. If a UI step becomes ambiguous, stop before destructive actions such as deleting actions, changing connectors, or posting test messages.
  5. Deleting a flow, creating an environment, or changing permissions, sharing or DLP needs the exact target and impact shown and individual approval. If DLP/ACP rejects the same operation, do not retry or route around it; rebuild elsewhere.

Core Workflow

  1. Identify the flow type: new flow, existing-flow edit, failure triage, or test verification.
  2. Confirm connectors and target resources: trigger Form ID, Team, channel, parent message ID, recipient, response URL, and service account/user connection.
  3. Build or edit in small increments: trigger -> data lookup -> action -> Flow Checker -> save -> test.
  4. Use the Power Automate UI, but distrust generated actions until verified. Copilot can draft a flow, but it may choose the wrong Teams action or invent dynamic-content names.
  5. Run Flow Checker after structural edits. Require zero errors; warnings must be reviewed and either fixed or explicitly accepted.
  6. Save only after the checker is clean.
  7. Test with a real but clearly fake submission when the trigger requires external input. Verify the final destination, not just a green flow run.

High-Signal Gotchas

  • Teams thread replies: Use Reply with a message in a channel / チャネル内のメッセージで応答します. Do not add replyToId to generic Post message in a chat or channel; Flow Checker rejects it.
  • Parent message IDs: Hardcoded Teams parent message IDs are runtime dependencies. Verify the parent top-level message exists in the exact Team + channel before trusting the flow.
  • Forms dynamic content: The Forms trigger returns response IDs, not answers. Insert answer tokens from Get response details. In expressions, Forms answers usually become internal r... keys; do not rely on guessed short names.
  • Links in Teams: Long raw URLs can wrap and appear broken. Use HTML anchor text such as <a href="...">Forms回答一覧を開く</a>.
  • Forms response URLs: A Forms design/responses URL usually requires sign-in and edit/view permission. That is acceptable when the recipients are authorized, but do not describe it as public.
  • Flow Checker scope: Flow Checker validates schema, not runtime existence of a Teams message, channel permission, or whether recipients can open a link.

Common Runbooks

Done Criteria

  • Flow Checker has zero errors.
  • Flow is saved and testable.
  • Runtime test confirms the expected destination received the expected content.
  • For visible posts, user approved the exact test/send action.
  • Any unresolved risk is documented plainly, such as no failure branch, broad channel visibility, or permission-gated links.
  • For a migration, the migration runbook's own Done Criteria also hold.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

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'.

日本語の概要は準備中です。原文の説明を表示しています。

aktsmm/Agent-Skills262026年10月28日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

aktsmm/Agent-Skills262026年10月28日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

aktsmm/Agent-Skills262026年10月28日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

aktsmm/Agent-Skills262026年10月28日 更新

archify

無料

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.

日本語の概要は準備中です。原文の説明を表示しています。

aktsmm/Agent-Skills262026年10月28日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

aktsmm/Agent-Skills262026年10月28日 更新

aktsmm のスキルをすべて見る

このスキルの問題を報告する