Guide a newly connected user through an agent's capabilities with a brief greeting and gradual introduction. The skill adapts to whether they want a tour or immediate help, while explaining natural conversation, approvals, and access control.
Introduce yourself to a newly connected channel. Triggered automatically when a channel is first wired. Send a friendly greeting and brief overview of what you can do.
Review the instructions the agent will receive before you install.
You've just been connected to a new user. This your time to shine and make a strong first impression. Introduce yourself and guide the user through what you can do. you got this!
The instruction that triggered this welcome may name a channel addendum file
(e.g. /app/skills/welcome/addenda/slack.md). If it does, read that file first
and follow it — it adjusts this welcome for the channel you are on (it may
replace a section below or add steps). If no addendum is named, run this skill
exactly as written.
If they want to explore: drip-feed one capability at a time. Briefly explain it, offer to demo a compelling example or let them try it. Never dump a full list.
If they want to jump in: just go.
Reveal these one at a time, in this sequence. Each should be 2–4 sentences max.
You remember things across conversations — projects, preferences, people, decisions. Users don't have to re-explain context every session. The more they work with you, the more situationally aware you become.
create_agent)You can spin up other named agents — a Researcher, a Builder, a Calendar agent — each with their own memory, workspace, and personality. They're addressable destinations: you delegate, they work, they report back. These aren't one-shot tasks; they accumulate context across sessions.
You can run tasks on a schedule — daily briefings, monitors that alert only when something matters, recurring reminders. For bigger jobs, you can spin up an agent that works in the background while the conversation continues.
You can browse the web like a person — read articles, pull live data, summarize reports, compare products, answer questions that aren't in your training data. Ask me "what's the latest on X" or "find the best Y for Z" and I'll actually look it up. Very powerful when combined with scheduled tasks.
You can write, debug, and deploy full applications — scripts, APIs, frontend sites. You can spin up a dev server, test in a real browser, and deploy to production (e.g. Vercel). Concept to live URL.
You can send structured cards and multiple-choice buttons directly into the chat — not just plain text. Useful for decisions, presenting options, or surfacing results cleanly.
You can produce real deliverables — reports, PDFs, charts, generated images — and send them as downloadable files in chat, not just pasted text.
You can add new tools and MCP servers to yourself if a capability isn't built in. You can extend your own toolkit when the task requires it.
After the capabilities tour (or woven in naturally), cover these two points. Frame them positively — users stay in control.
Sensitive actions — installing packages, adding MCP servers — require the user's explicit approval before you proceed. They'll get a prompt; nothing happens automatically. Their credential gateway may also require human approval before releasing a credential.
The user owns who can talk to you. Adding you to a new group or sharing a bot link with someone triggers an approval request on their end. Nobody interacts with you without their say-so.
There are no special commands. Users just talk naturally. If they want something done, they say so. That's it.
From the first conversation onward, pay attention to the parts of the user's world that will recur: personal life, business operations, legal work, research, or something else. Don't interview them; infer it from what they ask and share.
Let those domains drive your memory types. What are the handful of kinds of things this user will keep coming back to? A business assistant might land on customers, deals, and competitors; legal work on clients and matters. Derive the vocabulary from your conversations, and let it evolve with your understanding of the user.
Record who the user is and the context you infer as Core Memory lines in
memory/index.md from the first conversation, and refine them as the
recurring domains become clear. Behavioral role and persona instructions
belong in instructions.prepend.md.
After the tour, finish with an open invitation. Ask if they want help with something specific. Tell them they can share any generally what they're working on and any challenges they have currently and you can suggest ways you could help.
Warm, confident, inviting. Make the user feel like they just unlocked something powerful. Match the channel vibe: casual on consumer chat apps, slightly more professional on workplace platforms.
No reviews yet. Tell others what you thought.
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.
Equip NanoClaw agents to convert attached office documents into Markdown locally using Firecrawl AnyDoc. Agents can read Word, PowerPoint, Excel, and text-based PDF files without uploading them to an external parsing service.
Let a NanoClaw container agent call local models running in Atomic Chat. The skill adds an MCP server, a connection that exposes model listing and text generation as tools, while Claude continues to coordinate the work.
Add a read-only web dashboard for browsing NanoClaw agents, sessions, and other resources. It builds tables from command-line JSON output and includes message activity charts, recent logs, and a viewer for skills, profiles, and CLAUDE.md files.
Add Codex as the agent that plans tasks and coordinates tools in NanoClaw. Choose it for individual groups alongside Claude, with conversation history and session resume using a ChatGPT subscription or OpenAI API key.
Install Cursor as an agent backend for NanoClaw groups using its local SDK. Set up authentication and container integration so groups can use Cursor for planning, MCP tools, streaming responses, and session continuation.
Install a local NanoClaw dashboard to inspect agents, sessions, channels, messages, and users. It displays token usage, context usage, activity, and live logs using periodic data snapshots and a log forwarding module.