Best multi-agent orchestration skills, page 5

Runs Qwen Code headlessly with JSON output for repository work, using restricted approvals and bounded turn limits, and never the --yolo flag.

CherryHQ/cherry-studio

Guides decisions for agents working in an aweb team: when to check shared state, claim tasks, take locks, read team roles and instructions, and open separate worktrees.

awebai/aweb

Has several open-weight models answer a question, rank each other's anonymized answers, then lets a chairman model write the final response through Fireworks AI.

dair-ai/dair-academy-plugins

Acts as a manager in Agent Kanban: reviews the board on scheduled or heartbeat runs, creates and assigns tasks to worker agents, and reviews their submissions.

saltbo/agent-kanban

Plan and document handoffs, parent lane contracts, and parallel batch contracts between specialized AI agents (foreman, workers, reviewers).

Arenukvern/mcp_flutter

Factory worker guide for task execution in CAS multi-agent sessions.

codingagentsystem/cas

Teach agents and external systems how to use spec-kitty orchestrator-api to drive workflows from outside the host CLI.

spec-kitty/spec-kitty

飞书多 Agent 系统搭建指南。当用户要求创建新的功能 Agent、配置飞书群聊绑定、 搭建多 Agent 协作系统时激活此 skill。

hyperlist/feishu-multi-agent

Decides whether a request wants a full agent team, one agent, or one skill, then follows the matching flow file to generate it.

xvirobotics/metabot

Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor /…

OpenLoaf/OpenLoaf

Multi-agent orchestration framework for autonomous AI collaboration.

Orchestra-Research/AI-Research-SKILLs

Run parallel multi-agent review on completed knowledge work.

nabeelhyatt/coworkpowers

Generates production-ready FastGPT workflow JSON from natural language requirements.

YYH211/Claude-meta-skill

Compact version of the PUA persona skill that pushes an agent to act like a high-ownership engineer, with level roles, extra-work markers and corporate-style commentary.

tanweai/pua

A skill your agent uses whenever work can be split across multiple AI agents running in parallel, or when orchestrating leader/worker patterns in WrongStack.

WrongStack/WrongStack

Pilot Puppetmaster from Pi. Pi is the TUI, not a leased worker. Use for start_implement, start_agentic, start_prewalk, effort-index, show, and…

professorpalmer/Puppetmaster

Runs several small /gsd-quick tasks as one batch, with a single coordinator that plans them, dispatches workers per item and owns all shared writes and worktree merges.

open-gsd/gsd-core

Runs deterministic DAG pipelines from a JSON descriptor with journal-based crash recovery, so an interrupted run resumes without repeating finished nodes.

Yeachan-Heo/oh-my-claudecode

Inspects authorized LoopX Goals, Todos and deliveries to explain progress, flag decisions that need the owner and delegate work to the right worker.

loopx-project/loopx

Build and debug Python applications using AgentScope 2.x. An agent skill from agentscope-ai/skills.

agentscope-ai/skills

Drives dependency-ordered multi-agent work through the workflow tool, one run per phase, with planning rules and retry, amend and send recovery.

code-yeongyu/oh-my-openagent

Has the agent do the implementation itself and consult one persistent, stronger advisor through ask_worker only when it reaches a dead end.

Th0rgal/sandboxed.sh

Bootstrap and run a multi-agent AI development team. An agent skill from boshi-xixixi/TraeSkill.

boshi-xixixi/TraeSkill

Multi-agent orchestration for complex tasks. An agent skill from numman-ali/n-skills.

numman-ali/n-skills

Runs an autonomous evolutionary loop that improves a codebase against a measurable benchmark, using agent roles, tournament selection and recorded history until a stop condition.

zereight/gitlab-mcp

Generate a complete, ready-to-share HTML presentation explaining Claude Code, Skills, Sub Agents, Hooks, and Multi-Agent Systems — designed for product managers.

hamzafarooq/claude-code-starter

Runs the six-agent CraftBot workflow in this specific repository, turning a design brief and references into versioned Blender Python scripts, renders, a rationale and an archived transcript.

lukapiskorec/craftbot

Check workflow delegation prompts against agent role definitions for content separation violations.

catlog22/Claude-Code-Workflow

Port an existing program - written in C or in any other language - to os8088 as a C package (SPEC.md §73), the way apps/cword ported Microsoft Word 1.1a.

jggonz/os8088

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication.

davila7/claude-code-templates

Написание и запуск Claude Code dynamic workflows (JS-оркестратор субагентов).

AnastasiyaW/codex-claude-code-config

Runs a full SEO audit through the DataForSEO API with five parallel subagents and produces a composite 0 to 100 SEO score, an action plan and an audit JSON for PDF export.

zubair-trabzada/dataforseo-claude

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit…

a5c-ai/babysitter

Contribute changes to the CAO (CLI Agent Orchestrator) codebase — the local dev loop, the CI gate map, and the pre-PR checklist.

awslabs/cli-agent-orchestrator

AI agent runtime and multi-agent orchestration platform. An agent skill from swarmclawai/swarmclaw.

swarmclawai/swarmclaw

Multi-agent QA review team for code changes. An agent skill from PostHog/posthog.

PostHog/posthog

Implement multi-agent coordination patterns (supervisor-subagent, router, orchestrator-worker, handoffs) for LangGraph applications.

soba-labs/langchain-agent-skills

Sends a prompt into another OpenClaw agent session over a local or SSH acpx bridge, resolving target sessions from a configurable alias file.

steipete/agent-scripts

A skill your agent uses for rigorous pull request, branch, patch, or diff review.

bbartling/open-fdd

Design multi-agent architectures for complex tasks. An agent skill from NeoLabHQ/context-engineering-kit.

NeoLabHQ/context-engineering-kit

Author and run a deterministic multi-agent workflow — a JavaScript script that fans out, pipelines, loops, and judges across many child agents.

mweinbach/agent-coworker

Stores a DAG definition once and re-runs it by name, with key rotation controlling whether each run is fresh or reuses an earlier result.

code-yeongyu/oh-my-openagent

Runs a multi-agent review before an npm release, with per-change analysis, a holistic review and a final readiness verdict, and only when you ask for it.

code-yeongyu/oh-my-openagent

Runs a parallel security audit with three vulnerability hunters and two proof-of-concept engineers, rating each finding by whether it is actually exploitable.

code-yeongyu/oh-my-openagent

Runs an exhaustive, team-based research session that stands up cooperating agents, debates findings and delivers a report where every claim has a citation or proof.

code-yeongyu/oh-my-openagent

Drives the cmux terminal multiplexer from natural language to open, inspect, prompt, read and close windows, workspaces, panes, surfaces and agent sessions.

disler/learning-cmux-with-agents

Spawns a chosen number of coordinated agents on a shared task list and runs them through plan, requirements, execution, verification and fix stages.

zereight/gitlab-mcp

Turns a one-line objective into a multi-step plan file with PR-sized steps, context briefs, a dependency graph, parallel-step detection and an adversarial review.

affaan-m/ECC