Best multi-agent orchestration skills, page 6

Facilitates a read-only standup between git worktrees, branches or PRs, where each acts as an agent in a shared markdown chat to agree one consolidation plan.

thedotmack/claude-mem

Coordinates a delegated review of a Moraine PR or local change by seven focused reviewer subagents, merges their findings and follows up on the fixes.

eric-tramel/moraine

Runs a project on one Kanban board shared by people and AI agents, where a dispatcher splits goals into tasks and any task can go to either a human or an agent.

Hermes-brasil/hermes-brasil

Sets the rules for a worker agent spawned by a boss mission: stay in scope, verify before finishing, report blockers quickly and end with a clear status.

Th0rgal/sandboxed.sh

Keeps plans, decisions, evidence and reviewer verdicts in small files so long multi-phase tasks survive context compaction and session resumes.

ZaxbyHub/opencode-swarm

Run scalable, isolated live QA for nac development. An agent skill from arcee-ai/nac.

arcee-ai/nac

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

NeoLabHQ/context-engineering-kit

A skill your agent uses when creating or editing an agent.yaml (or .yml/.hcl) configuration file for Docker Agent (cagent), including defining agents, models/providers, built-in or MCP toolsets…

docker/skills

Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions.

awslabs/cli-agent-orchestrator

Forms a decisive, evidence-based verdict on an external tool, a document or a set of approaches for your project, optionally reconciling other models' opinions.

EveryInc/compound-engineering-plugin

Carries out a plan, spec or clear build request end to end with local verification, then hands off to shipping or returns a structured result to a caller.

EveryInc/compound-engineering-plugin

Orchestrate multiple AI agents for construction workflows: estimator, scheduler, document, QA and safety agents coordinated by a supervisor agent, with human checkpoints.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

Execute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is…

a5c-ai/babysitter

Manage your SwarmClaw agent fleet — agents, tasks, chats, chatrooms, goals, schedules, memory, wallets, connectors, autonomy, and 40+ more command groups.

swarmclawai/swarmclaw

Runs the local OpenClaw main agent once with a JSON message and judges success from the returned payload, not only from the exit code.

CherryHQ/cherry-studio

Runs the Pi agent in sessionless JSON mode and limits it to read-only tools for analysis, since Pi has no approval prompt of its own.

CherryHQ/cherry-studio

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

ArgentOS development operations workflow — Linear tracking, CodeRabbit reviews, Blacksmith CI, GitHub branch protection, and inter-agent handoff protocol.

ArgentAIOS/argentos-core

Lets another AI agent drive your browser: one command creates a setup key and prints connection instructions for the remote agent.

garrytan/gstack

Gives a fast orientation to OpenRig for an agent that just booted into a seat, covering rigs, topologies, layers and where context and skills come from.

mvschwarz/openrig

A skill your agent uses when orchestrating a multi-agent biomarker discovery workflow that requires coordinating database queries, pathway analysis, literature review, statistical modeling, and…

aws-samples/amazon-bedrock-agents-healthcare-lifesciences

Lets two or more NanoClaw Slack bots and a human share a group DM, with an allowlist of rooms and a hop limit that stops bots looping on each other.

nanocoai/nanoclaw

Extends a Slack-connected NanoClaw agent so it can create new agents that each appear in Slack as their own bot, with an operator DM and a shared three-way room.

nanocoai/nanoclaw

Defines the explicitly parallel variants of nestia review and issue campaigns.

samchon/nestia

Defines the agent roles, prompts and output schemas for a two-layer validation of a plan, ending in a PASS, CONDITIONAL or BLOCKED verdict.

withkynam/vibecode-pro-max-kit

Spawns subagents that each model one opponent or player in a strategic scenario, then merges their JSON moves for wargames and multi-party analysis.

NovusEdge/palpatine

Meta-agent skill for orchestrating complex tasks through autonomous sub-agents.

NeverSight/learn-skills.dev

Runs a builder-and-evaluator cycle that scores a design draft on four dimensions and escalates when the score stalls.

modu-ai/moai-cowork

Sends tasks, inspects skill execution history, and tests OmniRoute's JSON-RPC 2.0 agent-to-agent server from the command line.

diegosouzapw/OmniRoute

Multi-agent workflow patterns: parallel dispatch, pipelines, QC gates, retries.

xiaolai/nlpm

Fans a task out into independent units that run on a separate Gemini-based agent pool, while the current session only coordinates.

yzhao062/anywhere-agents

Guides step-by-step coordination of PM, frontend, backend, mobile and QA agents on a complex project, with priority tiers, contract checks and QA review.

first-fluke/oh-my-agent

HomeRail DAG review and execution best practices. An agent skill from xiaotianfotos/homerail.

xiaotianfotos/homerail

Runs agency-orchestrator YAML workflows inside the current agent session, with the session's own model playing each role in turn and no API key needed.

jnMetaCode/superpowers-zh

Builds Agent-to-Agent (A2A) servers and clients following Google's open protocol for agent interoperability.

internet-court/internet-court-skill

Runs a multi-source investigation with parallel sub-agents and built-in web tools, then writes one cited report. Meant for open-ended topics, not quick lookups.

XiaomiMiMo/MiMo-Code

Generates several independent candidate solutions in parallel worktrees, judges them once against one explicit rubric, and applies the winning candidate only after it passes verification.

codewhale-hq/Codewhale

Acts as a persistent read-only advisor that maps the repository once, then answers a cheaper executor agent's questions concisely across a long session.

Th0rgal/sandboxed.sh

Repo adapter that runs the investigation step of the ForgeDock work-on pipeline on a GitHub issue and posts a FORGE:INVESTIGATOR report comment.

RapierCraftStudios/ForgeDock

Splits work across Grok, Claude and Codex with the current session as controller, in fast, review, race and scout modes, and checks results itself instead of trusting a model's report.

imraywang/rayskills

Creates VS Code custom agent files (.agent.md) for specialized AI personas with tools, instructions, and handoffs.

dotnet/skills

Reviews GitHub pull requests with a swarm of specialized agents covering security, performance, architecture, style and accessibility, driven by the gh CLI and ruv-swarm.

ruvnet/agentic-flow

Add Agent Swarm (Teams) support to Telegram. An agent skill from sbusso/claudeclaw.

sbusso/claudeclaw

Reference for writing briefs to a subagent or a fork: what context to include, what never to delegate, and how a custom subagent's definition limits the prompt.

QwenLM/qwen-code

Runs one operation across many files with parallel worker agents: finds files by glob pattern, splits them into chunks, launches workers and summarizes the results.

QwenLM/qwen-code

A skill your agent uses when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent orchestration, optimizing cost, or adding AI safety…

kid-sid/claude-spellbook

Coordinates several coding agents in parallel through the Superset CLI, each in its own workspace, with a dependency table, bounded worker prompts and structured results.

superset-sh/superset

Managing shared context, memory, and state across multiple agents.

Owl-Listener/ai-design-skills