Topic · Automation and Agents
Subagents and Multi-Agent Orchestration skills for Claude Code and Codex
Skills for splitting work across subagents and coordinating multiple agents: dispatching parallel agents, subagent-driven development with review between tasks, judge and debate patterns, multi-agent architecture guides, and delegation to external coding agents such as Jules, Grok Build, Manus and Codex. They give the main agent a method for when to fan out and how to merge results.
Highest-scoring subagent skills in the October 22, 2026 snapshot: slicing-code-context from trailofbits/skills (89/100), grok-build from sanjay3290/ai-skills (87/100) and multi-agent-patterns from muratcankoylan/Agent-Skills-for-Context-Engineering (86/100). Scores come from the Suede Skill Check.
- 40 listed skills
- 19 repositories
- 14 with full pages
10 from official publishers. 11 bundle scripts. 2 connect to an outside service. Listed in AI Agents and LLM Engineering (36), Developer Tools and Frameworks (2), Security (1), Product Management (1).
All 40 subagent skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| agent-experience 74/100 · C | browserbase/skills | Audits the developer experience of a product, SDK, or docs site by sending Claude subagents at it with only a tiny task prompt. |
| coding-agent 75/100 · C | swarmclawai/swarmclaw | Delegates coding tasks to external coding agents such as Claude Code, Codex, Pi, and OpenCode via shell, including new features, PR reviews, and refactoring. |
| dispatching-parallel-agents 82/100 · B | obra/superpowers | Guides splitting two or more independent tasks, with no shared state or sequential dependencies, across parallel agents. |
| efficient-dispatch 82/100 · B | Necmttn/ax | Routes mechanical subagent work to an explicit cheaper model while the main frontier model keeps judgment and review, and ax measures whether routing worked. |
| ensemble-solving 81/100 · B | mhattingpete/claude-skills-marketplace | Generates multiple diverse solutions in parallel and selects the best, for architecture decisions, code generation with several valid approaches, or creative tasks. |
| executing-plans 83/100 · B | obra/superpowers | Guides executing an implementation plan inline in the current session as the implementer, when inline execution is chosen or no subagent tool is available. |
| grok-build 87/100 · B | sanjay3290/ai-skills | Delegates well-specified implementation tasks to xAI's Grok Build CLI running headlessly while the assistant writes task specs, reviews every diff, and owns the result. |
| manus 87/100 · B | sanjay3290/ai-skills | Delegates complex, long-running tasks to the Manus AI agent for autonomous execution, such as deep web research, market analysis, product comparisons, and stock analysis. |
| multi-agent-patterns 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides design of multi-agent systems with context isolation, supervisor or swarm coordination, explicit handoffs, and parallel execution, including whether multiple agents are justified. |
| multi-agent-patterns 75/100 · C | NeoLabHQ/context-engineering-kit | Guides designing multi-agent architectures for complex tasks, useful when single-agent context limits are exceeded, tasks decompose into subtasks, or specialized agents improve quality. |
| project-development 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides project-level decisions for LLM-powered systems, including whether an LLM fits the task, token and cost estimation, and single-agent versus multi-agent choices. |
| slicing-code-context 89/100 · B | trailofbits/skills | Selects bounded, graph-informed source slices with Trailmark and delegates focused code analysis or patch-proposal work to a smaller subagent. |
| subagent-driven-development 78/100 · C | NeoLabHQ/context-engineering-kit | Executes implementation plans by dispatching a fresh subagent per independent task, with code review between tasks to enable fast iteration with quality gates. |
| utility-pm-workflow-builder 83/100 · B | product-on-purpose/pm-skills | Guides a contributor from a workflow idea to a Workflow Implementation Packet, running overlap analysis against existing workflows and helping select and sequence skills. |
| agent-development 86/100 · B | anthropics/claude-plugins-official | This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use… |
| agent-orchestration-advisor 70/100 · C | deanpeters/Product-Manager-Skills | Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized… |
| agents-build 83/100 · B | aws/agent-toolkit-for-aws | Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or… |
| context-engineering-collection 76/100 · C | muratcankoylan/Agent-Skills-for-Context-Engineering | A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems… |
| create-workflow-command 68/100 · D | NeoLabHQ/context-engineering-kit | Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts |
| crewai-multi-agent 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex… |
| deep-agents-orchestration 69/100 · D | langchain-ai/langchain-skills | INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL… |
| do-in-parallel 64/100 · D | NeoLabHQ/context-engineering-kit | Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge… |
| do-in-steps 64/100 · D | NeoLabHQ/context-engineering-kit | Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge… |
| google-cloud-solution-agentic-ai-bidirectional-streaming 87/100 · B | google/skills | Guides agents to interactively discover customer requirements for live, bidirectional multi-agent AI systems that process continuous streams of… |
| google-cloud-solution-build-deploy-agents 87/100 · B | google/skills | Designs, builds, and deploys AI agents or multi-agent systems on Google Cloud. Provides an interactive workflow to gather requirements, recommend a… |
| google-cloud-solution-multi-agent-security 86/100 · B | google/skills | Designs, deploys, and secures Google Cloud Agent Gateway solutions. Use when the user needs to configure multi-agent security, ingress… |
| judge 66/100 · D | NeoLabHQ/context-engineering-kit | Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation |
| judge-with-debate 66/100 · D | NeoLabHQ/context-engineering-kit | Evaluate solutions through multi-round debate between independent judges until consensus |
| jules 84/100 · B | sanjay3290/ai-skills | Delegate coding tasks to Google Jules AI agent for asynchronous execution. Use when user says: 'have Jules fix', 'delegate to Jules', 'send to… |
| latent-briefing 87/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context"… |
| launch-sub-agent 70/100 · C | NeoLabHQ/context-engineering-kit | Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and… |
| long-horizon-prompting 76/100 · C | muratcankoylan/Agent-Skills-for-Context-Engineering | This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent… |
| structured-autonomy-generate 65/100 · D | github/awesome-copilot | Structured Autonomy Implementation Generator Prompt |
| subagent-driven-development 68/100 · D | obra/superpowers | Use when executing implementation plans with independent tasks in the current session |
| Suede AI Agent Teams Skills 93/100 · A | JasonColapietro/suede-creator-skills | Suede AI Agent Teams Skills. Use when asked to "split this work across agents" or run coordinated shared changes in lanes with exclusive file… |
| swarm 71/100 · C | langchain-ai/langchain-skills | Dispatches many independent items in parallel: create a table, fan out to subagents, aggregate results. One row = one unit of work. |
| utility-pm-changelog-curator 80/100 · B | product-on-purpose/pm-skills | Draft CHANGELOG entries from git log via the pm-changelog-curator sub-agent, applying the repo hygiene rules (describe what changed, public paths… |
| utility-pm-critic 75/100 · C | product-on-purpose/pm-skills | Run adversarial review on a PM artifact via the pm-critic sub-agent. Returns findings graded P0/P1/P2/P3 with a concrete fix suggestion per finding… |
| utility-pm-skill-auditor 83/100 · B | product-on-purpose/pm-skills | Run a repo-wide cross-cutting governance audit via the pm-skill-auditor sub-agent. Aggregates the enforcing validator suite, re-derives aggregate… |
| workflow-builder 79/100 · C | infrasity-labs/dev-gtm-claude-skills | Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool. Use when a user wants… |
How to choose subagent skills
Choose one orchestration method and stay with it. obra/superpowers and NeoLabHQ's context-engineering-kit each ship a complete set (parallel dispatch, step-by-step execution, judges), and mixing their rules in one session produces conflicting instructions.
Delegation skills hand tasks to a separate product. Jules, Grok Build and Manus each need their own account and CLI or API key, listed under Before you install, and they run outside your local session.
Use the design guides (multi-agent-patterns, agent-orchestration-advisor) before you write a workflow script. They cover context isolation, handoffs and when one agent is enough, which saves tokens on tasks that do not split cleanly.
Related topics
AI Agent Builders 56Code Assistants 21Codex, Cursor and Coding Agents 23Context Engineering and Agent Memory 31Google Cloud 146Claude Code Setup and Hooks 31Evals and Benchmarks 27Prompt Engineering 28
Find your next useful skill
Explore Rising Skills with quality scores and source reports, or search from inside your agent.
Get Rising Skills by email · Read Rising Skills · Install the finder · State of Agent Skills