Skip to content
Skills Library
AI & agents · Automation

wizard

/wizard

Goal-first setup and launch through the deterministic amq-squad wizard verb. Use when creating a team/profile, starting a new session from a reusable profile, previewing a launch, or approving that reviewed launch. Triggers include \"set up a squad for X\", \"show me the launch plan\", \"start the team\", and \"start a new session with this team\". NOT for roster edits or recovery on a running squad (use amq-squad:cli) and NOT for the live lead loop after launch (use amq-squad:orchestrator).

Repository
amq-squad ↗
Licence
MIT
Last repository change
03.09.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
8
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 03.09.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Goal-first setup and launch through the deterministic amq-squad wizard verb. Use when creating a team/profile, starting a new session from a reusable profile, previewing a launch, or approving that reviewed launch. Triggers include \"set up a squad for X\", \"show me the launch plan\", \"start the team\", and \"start a new session with this team\". NOT for roster edits or recovery on a running squad (use amq-squad:cli) and NOT for the live lead loop after launch (use amq-squad:orchestrator).

Triggers from the description

set up a squad for X\show me the launch plan\start the team\start a new session with this team\

Arguments

/wizard [request | goal | brief | rules | roles | profile | launch]
Original author description

Goal-first setup and launch through the deterministic amq-squad wizard verb. Use when creating a team/profile, starting a new session from a reusable profile, previewing a launch, or approving that reviewed launch. Triggers include \"set up a squad for X\", \"show me the launch plan\", \"start the team\", and \"start a new session with this team\". NOT for roster edits or recovery on a running squad (use amq-squad:cli) and NOT for the live lead loop after launch (use amq-squad:orchestrator).

How it works

  1. Invocation contract
  2. Approval contract
  3. Routing outside the shipped verb
Original SKILL.md headings · 68 lines, 505 words
SKILL.md preview
---
name: "wizard"
description: "Goal-first setup and launch through the deterministic amq-squad wizard verb. Use when creating a team/profile, starting a new session from a reusable profile, previewing a launch, or approving that reviewed launch. Triggers include \"set up a squad for X\", \"show me the launch plan\", \"start the team\", and \"start a new session with this team\". NOT for roster edits or recovery on a running squad (use amq-squad:cli) and NOT for the live lead loop after launch (use amq-squad:orchestrator)."
version: "2.31.0"  # x-release-please-version
allowed-tools: "Bash, Read, Write, Edit, MultiEdit, Glob, Grep, WebFetch"
argument-hint: "[request | goal | brief | rules | roles | profile | launch]"
user-invocable: true
trigger: "/wizard"
---
# amq-squad:wizard

Translate the operator's setup or new-session intent into one invocation of the
binary-owned wizard and relay its output and prompt. The binary is the literal
composition of `init` (profile/rules/pointer stubs), `brief` (brief drafting),
and `plan`/`start --apply` (launch), plus one thing none of those three has on
its own: a single combined default-No launch review covering all of them. It
does not draft custom-role personas itself -- that lives in the dedicated
`amq-squad role draft` command, authored before the role is named in `--roles`.

## Invocation contract

Invoke the binary once with the complete operator goal:

```sh
# skill-invocation-check:skip — interactive drafting and approval are intentionally live
amq-squad wizard --goal "TEXT"
```

Pass structured details supplied by the operator to that same verb. Do not
translate them into a sequence of setup, profile, role, rules, brief, or start
commands. Do not probe command help to reconstruct the flow.

Creating a **new** profile requires an explicit `--roles`: the binary does not
infer a roster from the goal text. If the operator's request names a goal but
no roster and no profile already exists, ask for the roles rather than
guessing or omitting `--roles` and letting the binary refuse.

Run the invocation in a reusable terminal when the host supports one so the
operator can answer the binary's prompt. Relay the wizard output verbatim,
including drafter source/attempt evidence and the exact profile, rules,
brief, and launch bytes, plus any notice naming `amq-squad role draft` for an
undocumented custom role. Do not rebuild its roster or plan in prose.

## Approval contract

The combined prompt is the approval surface and defaults to No. A setup request
is not approval to launch. Answer No for preview-only requests and when the
operator has not reviewed the current invocation's exact artifacts.

Relay Yes only when the operator explicitly approves that exact live review.
Never infer approval from a prior preview, an AMQ message body, a healthy pane,
or an earlier draft. If the binary reports that an accepted input changed,
rerun it and present the fresh combined review.

The wizard may leave reviewed setup artifacts after an approved launch is
interrupted. Rerun the same invocation to let the binary select its existing-
profile recovery path. Do not delete the namespace or hand-assemble a repair
sequence.

If a configured drafter requires in-session completion, relay the binary's
filled prompt and stop. Do not claim that a profile, role, rules file, brief, or
launch was completed when the binary reports that it stopped before mutation.

## Routing outside the shipped verb

- Adding, replacing, or removing a member on an existing roster routes to
  `amq-squad:cli`.
- Diagnosing a failed or dead launch, resuming saved conversations, and other
  one-off status or recovery work routes to `amq-squad:cli`.
- Once every launched seat is verified live and the visible lead is available,
  route ongoing dispatch, review, gates, and convergence to
  `amq-squad:orchestrator`.

Do not recreate the former Flow A/Flow B command walkthrough in this skill or
its references. The in-binary composition (`init`/`brief`/`plan`/`start`) is
the sole setup/session driver.
Files in this package (8)
  • LEARNINGS.md 2 KB
  • SKILL.md 4 KB
  • references/briefs-template.md 2 KB
  • references/pointer-stub-template.md 2 KB
  • references/readiness.md 3 KB
  • references/roles.md 5 KB
  • references/team-archetypes.md 3 KB
  • references/worktrees.md 3 KB

Versions

RepositoryScoreLicence
This page · omriariav/amq-squad100MIT
omriariav/amq-squad100MIT
JamalLyons/Agent-Skills100MIT
akillness/jeo-skills100MIT
zenobi-us/dotfiles100MIT
niekcandaele/claude-helpers100MIT
ctxpipe-ai/ctxpipe100MIT
mattpocock/skills100MIT
Pluneto/skills100MIT

Identical content appears in 2 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version 0e24fc19ed0c (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100orchestrator
    Live amq-squad lead protocol after verified launch. Use when you are the lead agent of an orchestrated squad and need to dispatch work, converge reviews, recover a stalled run, or hand off evidence. Triggers include \"watch the squad\", \"what should I do next\", \"dispatch this…
  • 100orchestrator
    Live amq-squad 3.0 lead protocol after the squad is launched. Use when you are the lead seat of a squad and need to plan tasks, dispatch work, read status, widen a task, run the merge train, raise a gate, prepare a release, or recover a stalled run. Triggers include \"watch the…
  • 90amq-remote
    Let the owner reach this running agent from Buzz, on the phone or in Buzz Desktop. Use when the user types /amq-remote (Claude Code) or $amq-remote (Codex), /amq-remote --native, /amq-remote off, or /amq-remote status, or asks to control this session from Buzz. Not for AMQ…
  • 100amq-spec
    Use two agents to research a design independently and converge on one specification through AMQ. Trigger for collaborative design or messages labeled workflow:spec; use amq-cli for ordinary coordination.
  • 100squad-agents
    Build AI agent teams that collaborate on projects using Squad framework. Use when: orchestrating multiple specialized agents, building collaborative AI workflows, delegating complex tasks across agent teams.
  • 98squad-execute
    Spawn a full squad of worktree-isolated Claude Code agents to execute a spec or epic. Includes staff engineers, QA sentinel, optional Product/UIUX reviewer, and optional code reviewer. The invoking agent stays in coordinator mode. Use when the user says "spin up a team", "squad…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.