orchestrate — for Claude Code orchestrate, steadywrk, community, for Claude Code, ide skills, oh-my-ag agent:spawn, language, Native, Adaptation, subagents

v1.0.0
GitHub

Über diesen Skill

Geeigneter Einsatz: Ideal for AI agents that need claude code native adaptation. Lokalisierte Zusammenfassung: Automatic parallel multi-agent orchestration (includes Review Loop) # /orchestrate Claude Code Native Adaptation Spawn .claude/agents/ subagents via Task tool instead of CLI (oh-my-ag agent:spawn).

Funktionen

Claude Code Native Adaptation
Spawn .claude/agents/ subagents via Task tool instead of CLI (oh-my-ag agent:spawn).
Task tool returns synchronously, so no polling needed.
Check if .agents/plan.json exists
If not: Guide user to run /plan first

# Kernthemen

for Claude Code oh-my-ag agent:spawn language Native Adaptation subagents
karimalsalah karimalsalah
[0]
[0]
Aktualisiert: 3/21/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

Geeigneter Einsatz: Ideal for AI agents that need claude code native adaptation. Lokalisierte Zusammenfassung: Automatic parallel multi-agent orchestration (includes Review Loop) # /orchestrate Claude Code Native Adaptation Spawn .claude/agents/ subagents via Task tool instead of CLI (oh-my-ag agent:spawn).

Warum diese Fähigkeit verwenden

Empfehlung: orchestrate helps agents claude code native adaptation. Automatic parallel multi-agent orchestration (includes Review Loop) # /orchestrate Claude Code Native Adaptation Spawn .claude/agents/ subagents via Task tool instead of CLI (oh-my-ag agent:spawn).

Am besten geeignet für

Geeigneter Einsatz: Ideal for AI agents that need claude code native adaptation.

↓ Handlungsfähige Anwendungsfälle for orchestrate

Anwendungsfall: Applying Claude Code Native Adaptation
Anwendungsfall: Applying Spawn .claude/agents/ subagents via Task tool instead of CLI (oh-my-ag agent:spawn)
Anwendungsfall: Applying Task tool returns synchronously, so no polling needed

! Sicherheit & Einschränkungen

  • Einschraenkung: Requires repository-specific context from the skill documentation
  • Einschraenkung: Works best when the underlying tools and dependencies are already configured

About The Source

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Labs-Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ und Installationsschritte

These questions and steps mirror the structured data on this page for better search understanding.

? Häufige Fragen

Was ist orchestrate?

Geeigneter Einsatz: Ideal for AI agents that need claude code native adaptation. Lokalisierte Zusammenfassung: Automatic parallel multi-agent orchestration (includes Review Loop) # /orchestrate Claude Code Native Adaptation Spawn .claude/agents/ subagents via Task tool instead of CLI (oh-my-ag agent:spawn).

Wie installiere ich orchestrate?

Führen Sie den Befehl aus: npx killer-skills add karimalsalah/steadywrk. Er funktioniert mit Cursor, Windsurf, VS Code, Claude Code und mehr als 19 weiteren IDEs.

Wofür kann ich orchestrate verwenden?

Wichtige Einsatzbereiche sind: Anwendungsfall: Applying Claude Code Native Adaptation, Anwendungsfall: Applying Spawn .claude/agents/ subagents via Task tool instead of CLI (oh-my-ag agent:spawn), Anwendungsfall: Applying Task tool returns synchronously, so no polling needed.

Welche IDEs sind mit orchestrate kompatibel?

Dieser Skill ist mit Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer kompatibel. Nutzen Sie die Killer-Skills CLI für eine einheitliche Installation.

Gibt es Einschränkungen bei orchestrate?

Einschraenkung: Requires repository-specific context from the skill documentation. Einschraenkung: Works best when the underlying tools and dependencies are already configured.

↓ So installieren Sie den Skill

  1. 1. Terminal öffnen

    Öffnen Sie Ihr Terminal oder die Kommandozeile im Projektverzeichnis.

  2. 2. Installationsbefehl ausführen

    Führen Sie aus: npx killer-skills add karimalsalah/steadywrk. Die CLI erkennt Ihre IDE oder Ihren Agenten automatisch und richtet den Skill ein.

  3. 3. Skill verwenden

    Der Skill ist jetzt aktiv. Ihr KI-Agent kann orchestrate sofort im aktuellen Projekt verwenden.

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

orchestrate

Install orchestrate, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.

SKILL.md
Readonly
Upstream Repository Material
The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

/orchestrate

Claude Code Native Adaptation

Spawn .claude/agents/ subagents via Task tool instead of CLI (oh-my-ag agent:spawn). Task tool returns synchronously, so no polling needed.

Step 1: Load Plan

  • Check if .agents/plan.json exists
  • If not: Guide user to run /plan first

Step 2: Initialize Session

  1. Load .agents/config/user-preferences.yaml
  2. Response language follows language setting in .agents/config/user-preferences.yaml
  3. Generate session ID (format: session-YYYYMMDD-HHMMSS)
  4. Show agent routing (based on skill-routing.md)

Step 3: Spawn Agents (Parallel Task tool calls)

Spawn agents by priority tier:

  • Multiple Task tool calls in same message = true parallel execution
  • Each agent: Use .claude/agents/{agent}.md definition
  • Include in prompt: Task description, API contract, context
  • Include API contracts from .agents/skills/_shared/api-contracts/ if they exist
  • Load only task-relevant context (check codebase structure around affected domains)

Agent mapping:

DomainSubagent File
backend.claude/agents/backend-impl.md
frontend.claude/agents/frontend-impl.md
mobile.claude/agents/mobile-impl.md
db.claude/agents/db-impl.md
qa.claude/agents/qa-reviewer.md
debug.claude/agents/debug-investigator.md
pm.claude/agents/pm-planner.md

Step 4: Monitoring

Task tool returns results directly → No polling needed. Check status, files changed, issues in each agent result.

Step 5: Agent-to-Agent Review Loop (Native Loop)

Main agent directly controls this loop. Maintain iteration counter.

iteration = 0
MAX_SELF = 3, MAX_CROSS = 2, MAX_TOTAL = 5

LOOP:
  iteration += 1
  if iteration > MAX_TOTAL → FORCE_COMPLETE (include quality warning)

  [1] Self-Review:
      Check self-review section in implementation agent results
      PASS → Proceed to [2]
      FAIL (self_count < MAX_SELF) → Re-spawn Task tool (with feedback) → LOOP
      FAIL (self_count >= MAX_SELF) → Force proceed to [2]

  [2] Automated Verification:
      Run lint/type-check/tests via Bash tool
      PASS → Proceed to [3]
      FAIL → Feed output back to agent as correction context (max 2 retries) → re-run [2]
      FAIL (retries exhausted) → Proceed to [3] with verification failure noted

  [3] Cross-Review:
      Spawn `qa-reviewer` subagent via Task tool
      Parse QA results: PASS / FAIL
      PASS → ACCEPT
      FAIL (cross_count < MAX_CROSS) → Feedback format:
        ## Review Feedback (iteration {n}/{MAX_TOTAL})
        **Reviewer**: qa-reviewer
        **Verdict**: FAIL
        **Issues**: [Specific file:line references]
        **Fix instruction**: [How to fix]
      → Re-spawn implementation agent Task tool (include feedback) → LOOP
      FAIL (cross_count >= MAX_CROSS) → Report to user with review history

Step 6: Collect Results

After all agents complete:

  • Collect .agents/results/result-{agent}.md
  • Organize completed/failed tasks, changed files, remaining issues

Step 7: Final Report

Session summary:

  • Completed tasks
  • Failed tasks (if failed after retries, include error details)
  • Next step suggestions: Manual fix, re-run specific agent, /review QA

$ARGUMENTS

Verwandte Fähigkeiten

Looking for an alternative to orchestrate or another community skill for your workflow? Explore these related open-source skills.

Alle anzeigen

openclaw-release-maintainer

Logo of openclaw
openclaw

Lokalisierte Zusammenfassung: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 333.8k
⑂ 0
Künstliche Intelligenz

widget-generator

Logo of f
f

Lokalisierte Zusammenfassung: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code

★ 149.6k
⑂ 0
Künstliche Intelligenz

flags

Logo of vercel
vercel

Lokalisierte Zusammenfassung: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 138.4k
⑂ 0
Browser

pr-review

Logo of pytorch
pytorch

Lokalisierte Zusammenfassung: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 98.6k
⑂ 0
Entwickler