メニュー
The AGENT-facing description. This is what the model reads to decide WHEN to invoke the skill, so describe the trigger precisely (e.g. "Use this skill whenever the user asks to … BEFORE calling …"). Keep it action-oriented.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/microsoft/cat-agent-skills --skill my-great-skillコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Diagnose a live Microsoft Copilot Studio agent from its analytics and transcripts, find why it is underperforming, and produce a prioritized improvement backlog tied to specific topics, knowledge sources and tools. Use when an agent is already in production and someone asks why resolution or engagement is low, why users escalate or abandon, what the top unanswered questions are, how to improve an agent's containment or CSAT, or wants a post-launch review, health check or optimization sprint for a deployed agent.
Run an adversarial assurance review of a Microsoft Copilot Studio agent you own — generate and execute test cases for indirect prompt injection, oversharing and authorization bypass, data leakage, scope escape and tool misuse — then score the findings and map each one to a concrete Copilot Studio control. Use when someone asks to red team, pen test, adversarially test, jailbreak-test or security-review an agent, wants a prompt injection or data leakage assessment before go-live, or needs security sign-off and a risk report for an agent handling sensitive data.
Produces narrated educational explainer videos (MP4, 1080p, burned-in captions) that teach a concept, tool, process or policy — researching the subject where facts matter, generating office b-roll, and framing screenshots the user attaches. Use when the user asks to "make a video", "create an explainer video", "produce a training video", "a video explaining X", "turn this into a video", "video walkthrough", "demo video", "record a narrated overview", or asks to change a video this skill produced ("re-render with a longer script", "swap the b-roll"). Always writes the narration script and scene list and waits for approval before rendering. Do NOT use for slide decks with no narration or video (use pptx), for standalone images (use image-operations), or for audio-only podcasts (use PodcastGenerate directly).
SOC 職業分類に基づく
SKILL.md を表示中
| name | my-great-skill |
| description | The AGENT-facing description. This is what the model reads to decide WHEN to invoke the skill, so describe the trigger precisely (e.g. "Use this skill whenever the user asks to … BEFORE calling …"). Keep it action-oriented. |
Write the agent-facing instructions here as Markdown — this body becomes the
"Instructions" section on the detail page (when there's no README.md) and the
downloadable skill.md. The body loads only after the agent has already
decided to use the skill, so don't restate when to use it here — that belongs
in the frontmatter description. Go straight into how to do the task, in the
imperative (address the agent, not the skill — avoid "You are the … skill").
The voice the agent should adopt.
