Multi-Agent skills

2,460 tagged Multi-Agent, measured the same way as everything else here.

Browse within: agent-orchestration 321claude-code-plugin 259Orchestration 244local-first 181no-code 166agent-teams 122opencode-plugin 89multi-agent-systems 84crawler 75digital-employee 75makemoney 75mas 75llm-agents 69git-worktree 67

lofcz/LLMTornado

Skill Claude CodeCodex

Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.

not rated 638 18d ago A 20 tokens original MIT

verl-to-relax

26

redai-infra/Relax

Skill Claude CodeCodex

Migrate RL training recipes from verl to Relax framework. Use when user wants to port reward functions, tool environments, training scripts, or any recipe code from the verl (volcengine/verl) codebase to Relax. Handles reward, rollout, tool/env, dataset, and launch script conversion. Supports both colocate (default)…

not rated 580 7d ago A 78 tokens original Apache-2.0

solo-artifacts

27

solo-agent/solo

Skill Claude CodeCodex

Use when a Solo task or thread should become an interactive, reviewable, self-contained HTML artifact for progress/status, review/decision, or comparison/leaderboard work inside Solo.

not rated 544 3d ago A 40 tokens original MIT

multi-agent

28

shibing624/agentica

Skill Claude CodeCodex

Run work across more than one agent — choose between the task subagent, the delegate tool, and a second agentica CLI in tmux driven by peer messages (listagents / sendmessage). Use when a job wants parallel workers, its own terminal, coordination between sessions, or you are choosing among task, delegate, and a second…

not rated 351 yesterday A 72 tokens original Apache-2.0

ackman-quant

29

gameworkerkim/vibe-investing

Skill Claude CodeCodex

Analyzes a specific US or Korean stock (by ticker or company name) through Bill Ackman's investment persona using this repo's local Ackman Quant Engine (01.Trading Strategy/Awesome claude quant scripts/Ackman/quantengine) — a Python pipeline that pulls TOSS/DART/Yahoo Finance/news data, computes a…

not rated 329 yesterday A 211 tokens

app

30

jd-opensource/JoySafeter

Skill Claude CodeCodex

A skill-management module for storing, organising, sharing, and managing reusable skills, including their descriptions, content, tags, and files.

not rated 305 8d ago A 0 tokens original Apache-2.0

augur-lynch

31

BruceLanLan/augur

Skill Claude CodeCodex

Peter Lynch AI — GARP / PEG, consumer growth, everyday observations.

not rated 294 1mo ago A 20 tokens original MIT

skill-sublation

32

Sven-Mirana/sublation

Skill Claude CodeCodex

A governed workflow for improving agent skills through observations, proposed changes, testing, review, user approval, and a period of monitoring. “Sublation” means preserving useful existing behavior while adding a verified improvement.

not rated 277 9d ago A 91 tokens original MIT

orchestrate

33

varun29ankuS/shodh-memory

Skill Claude CodeCodex

This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.

not rated 275 yesterday A 67 tokens original Apache-2.0

labrat-operator

34

ProjectDXAI/labrat

Skill Claude CodeCodex

Use when operating a labrat lab with Codex: checking health, choosing the next phase prompt, supervising runtime cycles, auditing candidates, synthesizing recent evaluations, or writing checkpoint notes.

not rated 239 28d ago A 42 tokens original MIT

fusion-setup

35

mihneaptu/opencode-fusion

Skill Claude CodeCodex

Use when a user wants to set up, configure, install, or reconfigure the opencode Fusion agent team - a strong main/build agent that plans and reviews but cannot edit files, delegating all edits to a cheaper sidekick subagent, plus an explore search agent and optional research/design/reviewer/vision specialists.…

not rated 216 11d ago A 166 tokens original MIT archived

paper-graph

36

CamusGIT/EvoQuant

Skill Claude CodeCodex

Use this skill to map the genealogical lineage and historical progression of a research field. It is designed to visualize the evolutionary path of ideas, showing how technical challenges in earlier works were addressed by subsequent research improvements. The final deliverable is a Markdown file with embedded Mermaid…

not rated 215 +11 18d ago A 197 tokens original Apache-2.0

opencode-ensemble

37

hueyexe/opencode-ensemble

Skill Claude CodeCodex

Use when coordinating multiple coding agents, delegating independent software work, managing OpenCode Ensemble teams, choosing teammate roles or models, reviewing teammate output, or deciding whether parallel execution is appropriate.

not rated 212 +1 10d ago A 42 tokens original MIT

Zhenyu98/codex-chatgpt-bridge

Skill Claude CodeCodex

Use when Codex needs to coordinate ChatGPT, Chrome, Cloudflare tunnels, verified bridge Restart/Reboot recovery, or task routing between local code execution and ChatGPT reasoning/review. Handles the bridge controller and scheduled task, start/off/status/doctor/rotate flows, Worker KV refresh, ChatGPT app setup…

not rated 199 +9 1mo ago A 97 tokens original MIT

opc

39

iamtouchskyer/opc

Skill Claude CodeCodex

OPC — One Person Company. Digraph-based task pipeline with independent multi-role evaluation. Builds, reviews, analyzes, and brainstorms with specialist agents. Every path ends with evaluation. /opc , /opc -i , /opc [role...].

not rated 194 +1 11d ago A 59 tokens original MIT

use-v4-flash-worker

40

Utopia-V/mixagents

Skill Claude CodeCodex

Use the DeepSeek-backed v4flashworker through the installed one-shot plaintext SubagentStart Hook. Use whenever Codex considers spawning, continuing, or troubleshooting this worker; it governs task suitability, plaintext staging, native forkturns=none spawning and return, one-shot state recovery, and the configured…

not rated 181 18d ago A 74 tokens original MIT

doc-sync

41

fancyboi999/open-tag

Skill Claude CodeCodex

Reconcile docs with code after a change (or as a periodic audit). Use before calling any change "done", at the end of every PR, or when asked to audit doc/code drift. Enforces this repo's hard rule: code change = doc change in the same commit.

not rated 181 +5 13d ago A 60 tokens original Apache-2.0

setup-routines

42

Yesterday-AI/paperclip-plugin-company-wizard

Skill Claude CodeCodex

Analyze a Paperclip company's issue history, agent health, recurring failure patterns, and project architecture to design and provision tailored routines with cron/webhook triggers. Replaces expensive always-on heartbeats with targeted, data-driven scheduled runs. Use when setting up routines for a new or existing…

not rated 171 4mo ago A 71 tokens original MIT

tubecreate/tubecli

Skill Claude CodeCodex

AI-powered Video Editor with trimming, merging, effects, overlays, and export.

not rated 167 yesterday A 21 tokens original MIT

django-patterns

44

deepelementlab/clawcode

Skill Claude CodeCodex

Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.

not rated 163 3mo ago A 32 tokens GPL-3.0

fabric-exec

45

monotykamary/pi-fabric

Skill Claude CodeCodex

Troubleshooting and advanced API reference for fabricexec TypeScript programs, dynamic providers, agents, and schema recovery. Routine pi. coding calls are documented by ambient guidance; load this skill only after an argument-shape error or when an advanced surface needs exact contracts.

not rated 177 changed yesterday A 61 tokens original MIT

orch

46

oxgeneral/ORCH

Skill Claude CodeCodex

AI agent orchestrator — manage teams of AI agents that work on your codebase in parallel. Use when the user wants to: run multiple agents, coordinate AI work, deploy agent teams, manage tasks/goals/agents, check orchestrator status, or mentions 'orch', 'orchestry', 'agents team', 'agent orchestration'.

not rated 159 1mo ago A 71 tokens original MIT

migration-wizard

48

bobmatnyc/claude-mpm

Skill Claude CodeCodex

General protocol for executing migration skill wizards - service installation and configuration guides.

not rated 149 4d ago A 18 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: