Skip to content
Agentmart
Submit a tool

ateam-help

Guides users through mstack setup, /ateam-mode, and picking the skill, playbook, or principle for a task.

Skill by anhminhnguyenhoang

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying ateam-help?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/anhminhnguyenhoang-ateam-help

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Guides users through mstack setup, /ateam-mode, and picking the skill, playbook, or principle for a task. Type /ateam-help with a question.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ateam-help

What's inside

Skill name
ateam-help
Description
Guides users through mstack setup, /ateam-mode, and picking the skill, playbook, or principle for a task. Type /ateam-help with a question.
License
MIT
Instructions
158 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • prompting.md · references/
  • recipes.md · references/

SKILL.md (first lines)

# Ateam help

Answer the user's question about mstack, hand them a prompt they can send, and link the file the answer came from. For a help question, don't start the work. The user asked how, and an mstack run spends real tokens, so let them send the prompt.

A message that asks for work, such as "use mstack to fix this bug", is not a help question. Read [`ateam-mode`](../ateam-mode/SKILL.md), do the work under it, and mention once that a Custom Mode keeps it on.

This file maps questions to the skills and guide pages that hold the answers. Those files own the details. Read the file you route to before you quote it, and trust it when it disagrees with this map. The links here point into the installed plugin, which the user may not be able to open, so give the user the file's repo copy: the `homepage` field of the plugin's `plugin.json`, then `/blob/main/`, then the file's path.

## Find out what they need

Infer the need from the message and the conversation. A named situation, such as "which skill reviews a PR?", goes straight to its section. If the need is still unclear, ask one multiple-choice question with these options, then answer only the section they pick:

- Get set up
- Start a task with `/ateam-mode`
- Pick a skill for a situation
- Fix a run that went wrong
- Make mstack my own

Check the state that changes the answer, and mention it only when it does:

- No `~/.cursor/rules/mstack-models.mdc` means `/setup-mstack` hasn't run for this user, so every role uses its default model.
- No `~/.cursor/mstack/env.md` means the machine is not mapped, so every GPU run, container exec, and PR stops and asks. Give them `/setup-mstack env`. A `not set` optional resource (`kb`, `wavescope`, `refs`) only skips cited notes, the trace annotation loop, and peaks, and `/setup-mstack env` adds it.
- `/verify-gpu-kernel` runs one command on one locked GPU. A kernel library with no `verify-<lib>` skill has no map of what to run per op family. Mention `/create-verification-skill` when the question is about proving a library's ops work.

When the model rule is missing and it matters, ask whether the user wants to pick a model for each role and a reasoning budget now. It matters when the user is new, the question is about setup or cost, or the answer depends on which models run. Ask at most once per chat. If the need is also unclear, ask both questions together. Offer two choices:

- Now: give them `/setup-mstack` to type, and answer their question too.
- Later: answer their question, and add one line saying every role keeps its default model until they run `/setup-mstack`.

## Get set up

1. Install with `/add-plugin mstack` in chat, or from Customize in the sidebar.
2. Run [`/setup-mstack`](../setup-mstack/SKILL.md). It asks for a reasoning budget, maps a model to each role, and writes a rule. Then it maps the machine (hosts, containers, PR tool, Jira sites, GPU lock) and any local resources you have (repos, skills dir, ticket root, reference docs, and the optional knowledge base and WaveScope) into `~/.cursor/mstack/env.md`. It looks each one up by what it contains and asks only for what it did not find. Both apply to new chats.
3. Start a real task with `/ateam-mode`, a goal, and a check that can pass or fail.

Installing changes nothing until the user invokes a skill. Only `/setup-mstack` loads from the user's words. The [README](../../README.md) and [guide page 1](../../docs/guide/01-setup.md) have the details. Offer to word their first prompt with them, per [`references/prompting.md`](references/prompting.md).

If cost is the worry, say where the tokens go and how to spend fewer. mstack spends extra tokens on subagents and review groups. Rerun `/setup-mstack` and pick a smaller budget or cheaper models. A role set to `auto` or `inherit-parent` runs on the chat's model, which saves tokens when the chat runs on Auto or a cheaper model. A role with a shorter list runs fewer subagents, one for each entry. Save `/ateam-mode` for work that needs rigor.

mstack is built for Cursor. Its skills use the Agent Skills format, so other tools can read them. But most workflow skills, including `/ateam-mode`, `/how`, `/why`, and `/teach`, spawn Cursor subagents with per-role models, and Custom Modes and `/loop` are Cursor features, so those parts may not work there.

## Start a task with `/ateam-mode`

`/ateam-mode` matches the task to a playbook, copies the playbook's steps into the todo list, and runs the other skills as the steps need them. A step it skips stays in the list as `skip: <reason>`. A good prompt states the goal and how to tell it's done. It doesn't list skills, because a hand-written sequence tends to drop or reorder steps the playbook would keep. Read [`references/prompting.md`](references/prompting.md) before you help word one. [Guide page 2](../../docs/guide/02-ateam-mode.md) has examples.

Whether `/ateam-mode` stays on depends on how the user starts it:

- Enter on `/ateam-mode` attaches the skill to one message. It stops applying as the chat moves on.
- Option+Enter on Mac or Alt+Enter on Windows, or Use as Mode from the skill entry, makes it a Custom Mode. It stays in context every turn until the user exits the mode, and it stays out of casual turns.
- Cursor's docs list Custom Modes in the Agents Window and the CLI. Elsewhere, start each new task with `/ateam-mode`.

Link [Cursor's skills docs](https://cursor.com/docs/skills) when this comes up. Mid-chat, "new task" makes the mode match a fresh playbook. `/ateam-mode` already uses `ateam-agent` for the subagents its playbook steps spawn. To get the same style from a subagent of your own, spawn it with `subagent_type: "ateam-agent"`.

## Pick a skill

The default answer is `/ateam-mode`, which runs most of the others when its steps need them. Name a skill directly when the user wants more or less of something than the playbook gives. Read the skill before you recommend it, and give one example prompt.

| The user wants to | Skill |
|---|---|
| Do any non-trivial task with rigor | [`/ateam-mode`](../ateam-mode/SKILL.md) |
| Know how code works now, or where new code should live | [`/how`](../how/SKILL.md) |
| Know why code is shaped this way, or where a number came from | [`/why`](../why/SKILL.md) |
| Understand a kernel or a kernel change, explained plainly | [`/teach`](../teach/SKILL.md) |
| Catch up on their own recent work on a topic | [`/recall`](../recall/SKILL.md) |
| Catch up on everything in this chat since their last message, with enough context to decide each action item | [`/ketchup`](../ketchup/SKILL.md) |
| Check that the agent understood their goal and the problem before it starts | [`/in-your-own-words`](../in-your-own-words/SKILL.md) |
| Get a prompt rewritten deeper, not bigger, before sending it: what a top professional would add, their raw material and methods, and an outside check. It returns the prompt and doesn't do the task | [`/sharpen`](../sharpen/SKILL.md) |
| Know what a small diff could break outside itself | [`/blast-radius`](../blast-radius/SKILL.md) |
| Settle types and module shape before code that crosses a function boundary | [`/architect`](../architect/SKILL.md) |
| Get several attempts at one brief, merged into the best one | [`/arena`](../arena/SKILL.md) |
| Run parallel checks over slices, or race workers, locally | `/ateam-mode`, which follows its parallel fan-out rule |
| Have different models review a diff and try to break it | [`/interrogate`](../interrogate/SKILL.md) |
| Review someone's aiter, FlyDSL, or Triton PR by number or URL, with GPU evidence, and post it with line comments after approval | `/ateam-mode review PR 123`, the [PR review](../ateam-mode/playbooks/pr-review.md) playbook |
| Fix a bug test-first when a cheap local test exists | [`/tdd`](../tdd/SKILL.md) |
| Strip comments before review, using a reviewer that didn't write them | [`/no-comments`](../no-comments/SKILL.md) |
| Clean AI tells out of prose | [`/unslop`](../unslop/SKILL.md) |
| Write docs, an RFC, a README, a PR description, or a commit message to a standard | [`/technical-writing`](../technical-writing/SKILL.md) |
| Hear the last reply again without kernel jargon | [`/bro`](../bro/SKILL.md) |
| Get a quoted line, term, number, kernel, design, optimization, lever, idea, or concept explained in plain words | [`/explain`](../explain/SKILL.md) |
| Give a kernel library a scripted way to prove its ops (correctness, perf, ISA) | [`/create-verification-skill`](../create-verification-skill/SKILL.md) |
| Bring a kernel library's verification skill and its feature map back in line with its tests | [`/maintain-verification-skill`](../maintain-verification-skill/SKILL.md) |
| Start from a Jira ticket key and set up its ticket folder | [`/ticket-init`](../ticket-init/SKILL.md) |
| Run, reproduce, or benchmark a kernel on the real GPU | [`/verify-gpu-kernel`](../verify-gpu-kernel/SKILL.md) |
| Vet a performance number before reporting or acting on it | [`/benchmark-checklist`](../benchmark-checklist/SKILL.md) |
| Find the domain skill for a kernel step: write, optimize, debug, trace, or ship | The skill function bindings in [`skill-functions.md`](../ateam-mode/references/skill-functions.md) |
| Run a large or cross-cutting change, or one to review after stepping away | [`/figure-it-out`](../figure-it-out/SKILL.md) |
| Keep a decision log during a run, and review it afterward | [`/show-me-your-work`](../show-me-your-work/SKILL.md) |
| Pick a model for each role and a reasoning budget | [`/setup-mstack`](../setup-mstack/SKILL.md) |
| Map the GPU hosts, containers, repo remotes, Jira sites, and optional local resources for this machine | `/setup-mstack env` |
| Turn what a finished task taught into skill edits | [`/reflect`](../reflect/SKILL.md) |
| Stop agents from repeating the same mistakes in this repo | [`/correct`](../correct/SKILL.md) |
| Find their way around mstack | `/ateam-help` |

If a skill directory next to this one is missing from the table, read its frontmatter and route by its description. The `principle-*` directories are covered under principles below.

Close calls:

- `/how` explains what the code does. `/why` explains the reasons. `/teach` runs one or both and explains the result plainly.
- `/arena` gives every worker the same brief and merges the best parts. `/ateam-mode` fans out local workers over slices or a race and returns one table of issues and gaps.
- `/architect` implements right after it settles the design. Add "with checkpoint" to review the design before it writes code.
- `/interrogate` has adversaries try to break a local diff and keeps only the findings a run proves. The PR review playbook reviews a PR by number. It checks repo rules and GPU evidence, runs the same review group, and writes a draft that the human posts. `/blast-radius` looks for breakage outside the diff and proves the one fact that makes the change safe.
- `/recall` rebuilds context across recent chats. `/ketchup` covers only this chat since the user's last message. Resuming one specific chat or branch is the Session pickup playbook.
- `/figure-it-out` designs one rigorous run. A program of many stacked PRs is a Multi-phase plan, run by an Autopilot playbook. The Autonomous run playbook drives one task to a finish condition.

Not in mstack:

- A UI or browser control skill. mstack ships none. For GPU runs, use `verify-gpu-kernel`.
- `/loop` and `/create-skill` are Cursor built-ins.

## Playbooks and principles

Playbooks are step lists inside `/ateam-mode`, not skills, so they have no slash command. Inside `/ateam-mode`, describing the task picks one, and these phrases name one directly:

- "babysit this pr" or "check on pr 123" runs Babysit. It drives the PR to merge-ready and stops there. It doesn't merge unless the user asks to merge, land, or ship.
- "land the stack" runs Shipping.
- "take over this branch" runs Session pickup.
- "pause safely" runs Pause safely.
- "full autopilot on this queue" runs Autopilot-full. "autopilot, don't merge" runs Autopilot-stack.
- "run the eval playbook" runs Eval.

From anhminhnguyenhoang/mstack, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Oct 13, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get ateam-help running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying ateam-help?

CallGet help
Cite this page

ateam-help skill. Agent Mart. https://agentmart.dev/skills/anhminhnguyenhoang-ateam-help (last updated 2026-10-24)