بنقرة واحدة
setup-check
Verify Maestro plugin prerequisites — Agent Teams flag, jq, trace MCP, PSM tools, directories, and hooks.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Verify Maestro plugin prerequisites — Agent Teams flag, jq, trace MCP, PSM tools, directories, and hooks.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
UI/UX design intelligence with searchable database
Generate comprehensive implementation plans through systematic discovery, synthesis, verification, and decomposition into beads. Use when asked to plan a feature, create a roadmap, design an implementation approach, or decompose work into trackable issues. Do NOT use for simple one-step tasks, quick fixes, or when the user just wants to execute an existing plan — use the work skill instead.
Execute a plan or direct task with worker delegation and verification.
Deep investigation mode. Gather context, analyze, synthesize recommendations without making code changes.
Fetch up-to-date library documentation via Context7 MCP. Use when working with external libraries, APIs, or frameworks.
Start interview-driven planning with Prometheus. Asks clarifying questions before generating implementation plan.
| name | setup-check |
| description | Verify Maestro plugin prerequisites — Agent Teams flag, jq, trace MCP, PSM tools, directories, and hooks. |
| allowed-tools | Read, Bash, Glob, Write, AskUserQuestion |
| disable-model-invocation | true |
Run through each check below. Report PASS or FAIL for each item with details.
Read ~/.claude/settings.json and verify it contains:
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
On FAIL: Show the user the exact JSON needed. Note: Cannot safely auto-edit global settings — provide instructions:
Add the following to
~/.claude/settings.jsonand restart Claude Code:{ "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" } }
Run which jq — hooks require jq for JSON processing.
On FAIL: Detect OS and show install command:
AskUserQuestion(
questions: [{
question: "jq is not installed. Install it now?",
header: "Install jq",
options: [
{ label: "Show command", description: "Display the install command for your OS" },
{ label: "Skip", description: "Continue without jq (hooks may not work)" }
],
multiSelect: false
}]
)
If user wants to install, show: brew install jq (macOS) or sudo apt-get install jq (Linux). Re-check after install.
Verify trace toolbox prerequisites exist:
toolboxes/trace/ directorytoolboxes/trace/trace.js entrypointUse Glob checks. PASS only if both exist.
On FAIL: Report missing paths and instruct user to run setup/build for the trace toolbox before enabling trace MCP.
Run which tmux — /psm requires tmux sessions.
On FAIL: Detect OS and show install command:
brew install tmuxsudo apt-get install tmuxRun which gh — /psm uses GitHub CLI for PR/issue operations.
On FAIL: Detect OS and show install command:
brew install ghsudo apt-get install ghAlso remind user to authenticate after install:
gh auth login
Verify these directories exist:
.maestro/plans/.maestro/drafts/.maestro/wisdom/.maestro/research/On FAIL:
AskUserQuestion(
questions: [{
question: "Missing .maestro directories. Create them now?",
header: "Fix dirs",
options: [
{ label: "Yes, create", description: "Run mkdir -p .maestro/plans .maestro/drafts .maestro/wisdom .maestro/research" },
{ label: "Skip", description: "Continue without creating directories" }
],
multiSelect: false
}]
)
If yes: Bash("mkdir -p .maestro/plans .maestro/drafts .maestro/wisdom .maestro/research"). Re-check to confirm.
Check that all symlinks in .claude/scripts/ point to valid targets:
ls -la .claude/scripts/
Report any broken symlinks. No auto-fix for symlinks — they require manual attention.
Validate the plugin manifest parses correctly:
cat .claude-plugin/plugin.json | jq .
Validate hooks config parses correctly:
cat .claude/hooks/hooks.json | jq .
Verify all scripts in scripts/ are executable:
ls -la scripts/*.sh
On FAIL:
AskUserQuestion(
questions: [{
question: "Some scripts are missing execute permission. Fix now?",
header: "Fix perms",
options: [
{ label: "Yes, fix", description: "Run chmod +x scripts/*.sh" },
{ label: "Skip", description: "Continue without fixing permissions" }
],
multiSelect: false
}]
)
If yes: Bash("chmod +x scripts/*.sh"). Re-check to confirm.
End with a summary:
## Setup Status
- Agent Teams: PASS/FAIL
- jq: PASS/FAIL
- Trace MCP toolbox: PASS/FAIL
- tmux: PASS/FAIL
- gh CLI: PASS/FAIL
- Directories: PASS/FAIL
- Symlinks: PASS/FAIL
- Plugin manifest: PASS/FAIL
- Hooks config: PASS/FAIL
- Script permissions: PASS/FAIL
Overall: READY / NOT READY (N issues to fix)