メニュー
Greet the user with a short, friendly welcome message when a new project/agent is first started. Invoked automatically as the first message from the minds desktop client.
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。
SOC 職業分類に基づく
Run the background harden pass for one artifact -- crystallize, update, or heal a skill, a service, or the system interface in an isolated worktree, then report back. Invoke when your task file hands you an artifact to harden; it names the operation and artifact to compose.
Promote the just-finished work into a new, reusable, committed, tested skill. Use when that process would recur with new inputs -- especially something you figured out through research or debugging -- or when the user says 'crystallize this'.
Fetch data from somewhere (an external service, an API, a third-party source), process it, and show it to the user -- the "go get all this stuff, do something to it, and put it in front of me" task. Use when the ask is to retrieve real data, transform/summarize/classify it, and surface the result. Validates auth first, confirms a real sample covering every data shape, then crystallizes the pipeline in the background while building surfaces.
Use when writing or reasoning about code that calls Claude -- an AI-driven service, an AI integration, or a skill's scripted model step. Covers the three scenarios (one-shot completion, one-shot agentic task, full agent) and the cost / credentialing model.
Fix an existing artifact that errored or delivered a wrong result. This applies to skills or web services. Invoke at turn-end, after you worked around the failure to satisfy the user's request.
Create a sub-agent to perform a larger task. Use when work is large enough to warrant a separate context, involves multi-file changes, or benefits from isolation.
| name | welcome |
| description | Greet the user with a short, friendly welcome message when a new project/agent is first started. Invoked automatically as the first message from the minds desktop client. |
This skill has two parts: the opening greeting you always send first, and a list of suggestions you offer only if the user asks for ideas.
Output the following welcome message to the user, verbatim, as your entire response. Do NOT call any tools, do NOT look at the codebase, and do NOT add anything else:
I'm an AI operating system built to extend you — so you can do your best work.
I can take on tasks for you, build custom AI tools you can easily edit, connect to the tools you already use to pull in information, or just brainstorm ways to make your work better.
Let's get started
Already have something in mind? Tell me what you'd like to work on below. If not, I'm happy to suggest a few ways to get started.
That is the entire opening message. Stop after printing it.
After the opening message the user replies. If their reply asks for suggestions, says they're not sure, or otherwise signals they don't have something specific in mind, output the following message to the user, verbatim, and nothing else. (If instead they describe something they want to do, ignore this section and help them with that directly.)
Here are some popular ways people get started with Minds. Pick whichever fits, and we can build on it as a starting point.
