Best multi-agent orchestration skills, page 4

Lets one Codex thread run a batch of GitHub issues through separate worker threads, each with its own worktree, branch, tested pull request and gated merge.

owainlewis/blueprint

Guided MARM MCP setup. An agent skill from Lyellr88/marm-memory.

Lyellr88/marm-memory

Cross-runtime playbook for multi-agent collaboration, agent teams, swarm orchestration, parallel task distribution, capability discovery, and quality gates on Claude Code, Codex, OpenClaw, and Cursor.

KimYx0207/Kim_Service

異なるproviderのAI（Codex/Claude/Grok/Cursor/Antigravity等）から独立意見を集め、共通論点で相互検討して統合する。最初に利用可能エージェントを検出する。「みんなで考えて」「マルチエージェントで分析して」「複数のAIでレビューして」と言われたら使う。

karaage0703/ai-assistant-workspace

Sketches types, signatures and module boundaries with stub bodies before real code, compares at least two designs, then implements against the chosen sketch.

cursor/plugins

Runs one read-only reviewer subagent per configured model against a diff to challenge a change, then synthesizes a single verdict without applying any fixes.

cursor/plugins

Teaches Hermes to monitor and steer long-running sandboxed.sh missions: spot where a model is stuck, switch backends or models between turns, and send targeted hints.

Th0rgal/sandboxed.sh

Run a structured debate between agent CLIs (claude, codex, agy, grok) and the user's configured API or local models (OpenAI, Anthropic, Google, xAI, OpenRouter, Ollama and more) through the Quorum…

Detrol/quorum-cli

Create a new CLI agent provider for CAO (CLI Agent Orchestrator).

awslabs/cli-agent-orchestrator

Documents the unified `metabot` CLI for personal memory, the skill hub, durable agent messaging, the agent registry, T5T status and scheduling.

xvirobotics/metabot

Autonomous framework engineer — reads VibeHQ post-run analysis, understands root causes of multi-agent coordination failures, then designs and implements real code changes (new features, refactors…

0x0funky/vibehq-hub

A skill your agent uses when Codex is facing a large, ambiguous, cross-module, high-risk, or parallelizable project and should use qiushi/workflows preflight before delegating work.

vannyben7/edict-agent

Reviews pull requests in this repository for the defect classes a mechanical checklist misses: documentation that outlived the code it describes, reaction and retry state that leaks or clobbers a…

sortie-ai/sortie

A skill your agent uses when a task should run through Hydra's Lead-driven workflow for multi-agent orchestration, or when an existing workflow must be inspected or cleaned up.

blueberrycongee/termcanvas

Orchestrate DeepSeek Oracle multi-agent workflows by routing user intents to specialist oracle skills, enforcing safety gates, and composing one unified answer with follow-up questions and action…

Bald0Wang/DeepSeek-Oracle

Execute explicitly authorized Ultracode / Ultra Mode requests: optimize for exhaustive, correct answers within the user's stated scope by using any available independent-work mechanism (ODW…

xz1220/open-dynamic-workflows

A skill your agent uses to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource removal.

aws/agent-toolkit-for-aws

Configures agystack's model tiers per role and its execution runtime, choosing between local subagents and Cloud Run jobs for large parallel swarms.

jtaroreh/agystack

Guide a new AgentUse user from a confirmed project to one validated first agent and its first CLI or Web UI run.

agentuse/agentuse

Hands a bounded repository task to the DeepSeek Harness CLI (dsh) in headless mode, then checks the exit code and the diff before reporting back.

CherryHQ/cherry-studio

Define a multi-agent team for ANY task on ANY system as an explicit deployment topology - pick the shape from the task's dominant risk, specify the runtime/communication/trust layers, place model…

Cotal-AI/Cotal

Runs several parallel attempts at the same task, picks the strongest as a base, grafts the best ideas from the others into it, then verifies the merged result.

cursor/plugins

Picks the smallest useful set of cloud OS and architecture runners to verify a change after local checks pass, then fans out child runs and aggregates the results.

warpdotdev/warp

Factory supervisor guide for multi-agent EPIC orchestration.

codingagentsystem/cas

A skill your agent uses when a single agent demonstrably cannot handle the task and multi-agent coordination is justified.

sharpdeveye/maestro

Review Logseq code changes, PRs, patches, commit ranges, or implementation plans through one main-agent orchestration workflow that routes read-only subagents across independent review passes, then…

logseq/logseq

A skill your agent uses when customizing Deep Researcher Agent behavior through Jinja2 prompt templates or per-agent model selection — editing prompts under src/deepresearcheragent/agents//prompts/…

NVIDIA-AI-Blueprints/deep-researcher-agent

Gives patterns for generating a minimal, valid Omnigent agent directory: the config.yaml fields, the right executor type, and the files each agent needs.

omnigent-ai/omnigent

Resolves ready MCP work items into a run plan, shows it to you, then executes it through the Workflow tool or direct subagent dispatch, with post-run verification.

jpicklyk/task-orchestrator

Defines exhaustive solo review, Self-Review, and solo repository-wide issue-discovery rounds for nestia.

samchon/nestia

Autonomous multi-agent performance optimization loop for Chromium and V8.

nwjs/chromium.src

Delegates multi-step coding or research tasks to isolated sandboxed.sh container missions through its MCP tools, each with a chosen workspace, agent profile and prompt.

Th0rgal/sandboxed.sh

Designs orchestrator-and-subagent hierarchies for a repository — splitting agents by exclusive write surface, pairing every producer with an independent auditor, and enforcing the split with a…

cbrock84/headcount

Launches many parallel cloud workers on slices of a task or on the same brief, waits for them all, and returns one aggregated report.

cursor/plugins

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

loulanyue/awesome-claude-notes

Bootstraps a new multi-agent repository from the RepoBrain template via initagentrepo.

study8677/repobrain

Reports which OMG modes are active, such as autopilot, ralph, team, ultraqa and self-improve, with phase, story or cycle progress read from their state files.

zereight/gitlab-mcp

Set up and manage Paperclip Routines — recurring scheduled tasks that replace expensive always-on heartbeats.

Yesterday-AI/paperclip-plugin-company-wizard

Adds one optional external Codex critique that tries to break a council's decision draft, sent to OpenAI only after you consent.

affaan-m/ECC

A skill your agent uses when applying oh-my-claude workflow guidance, ultrawork modes, agent orchestration, plan execution, or plugin configuration.

TechDufus/oh-my-claude

Breaks a research question into two to five facets and sends parallel document-specialist agents to search the web and documentation, then merges the results.

Yeachan-Heo/oh-my-claudecode

Rules for several agents sharing one repository: an orchestrator tracks work in two tiers, workers write to scratch files, and every handoff leaves a pointer to an artifact.

dralgorhythm/claude-agentic-framework

Multi-agent orchestrator for Claude Code. An agent skill from numman-ali/n-skills.

numman-ali/n-skills

Lists recent sessions of peer coding agents such as Codex, OpenClaw or Copilot CLI, or your own past sessions, so you can act on their work without copying between terminals.

tma1-ai/tma1

Runs a multi-task implementation plan by sending each task to a fresh implementer subagent, reviewing it independently, then reviewing the whole branch.

HoangNguyen0403/agent-skills-standard

Read-only, multi-agent audit of the leanSpec codebase. An agent skill from leanEthereum/leanSpec.

leanEthereum/leanSpec

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