Multi Agent Orchestration

Use when deciding whether to spawn subagents, choosing sequential vs fan-out vs supervisor vs debate vs dynamic DAG, designing a coding-agent workflow with write-scope isolation, or when extra agents may waste tokens without independent evidence. Trigger on multi-agent, orchestration, fan-out, worktree, blackboard, verifier, AgentTask, or "should I parallelize this".

423 stars 6 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add mizchi/skills --skill multi-agent-orchestration
Manual install
git clone --depth 1 https://github.com/mizchi/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/multi-agent-orchestration ~/.claude/skills/multi-agent-orchestration

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Multi-Agent Orchestration

Do not add agents. Add independently verifiable work: a dependency graph, parallel only on independent nodes, integrate through shared state and a verifier.

## When to use

- About to spawn 2+ subagents, a research fan-out, a debate/jury, or a "programmer + reviewer" pair
- Designing a coding-agent DAG, worktree split, or long-running parallel implementation
- Tempted to scale agent count because the task "feels hard"

When not to use:

- One tightly sequential transform (read → patch → test) with no independent parts
- Same model, same input, same tools, only the role name changes — run multiple turns on one agent instead

## Gate

Default to a **single agent**. Go multi only if **(1) or (2)** holds **and** (4) is positive.

**3 is not a reason to spawn.** It is how a multi run stops. A unit test the same agent can run is a success criterion, not a second agent. If 3 is weak, stay single or add a rubric/schema so artifacts become checkable — do not add agents to compensate.

1. Independent parts that can run in parallel — including parts that become independent after a short frozen contract artifact (types, HTTP shape, fixture). A call or runtime edge is not an automatic stay-single.
2. Agents would have different information, models, tools, or permissions
Read the full skill on GitHub

Details

Skill name
multi-agent-orchestration
Repository
mizchi/skills
Path
multi-agent-orchestration/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Multi Agent Orchestration skill do?

Use when deciding whether to spawn subagents, choosing sequential vs fan-out vs supervisor vs debate vs dynamic DAG, designing a coding-agent workflow with write-scope isolation, or when extra agents may waste tokens without independent evidence. Trigger on multi-agent, orchestration, fan-out, worktree, blackboard, verifier, AgentTask, or "should I parallelize this".

How do I install the Multi Agent Orchestration skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mizchi/skills --skill multi-agent-orchestration. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Multi Agent Orchestration popular?

It lives in mizchi/skills, which has 423 GitHub stars and 6 forks.

Related skills

Actions CI Tuning

423

mizchi/skills

Use when auditing or improving GitHub Actions workflows for a project. Covers cache setup (npm/pnpm/yarn), job parallelism, shard-based test splitting, artifact handling pitfalls, and Playwright-specific patterns. Trigger on: slow CI, cache miss, flaky shard jobs, merge-reports failures, or an explicit 'tune CI' request.

Testing & QA

AI Index

423

mizchi/skills

Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English. Two layers — a deterministic lint for removable surface tells (scripts/slopscore.py, no API) and a judgment layer of typed probabilistic questions (Jev noul/score) for the tells that survive editing. Includes measured human/AI baselines, a gap-first calibration procedure, and labeled fixtures. Use when building or calibrating an AI-likeness score, or when a draft needs a defensible number rather than a vibe. For writing guidance use natural-writing-ja / natural-writing-en instead.

AI, LLMs & Agents

Apm Usage

423

mizchi/skills

Reference for APM manifests, installation, targeted updates, deployment paths and lockfiles. Invoke when the user explicitly asks about APM or apm.yml, or an unfamiliar APM command/error needs exact CLI details. Do not automatically invoke for every project that happens to have installed skills.

DevOps & Cloud

Publish Agent Skill

423

mizchi/skills

Package, publish, verify and update an agent skill through a Claude Code plugin marketplace, APM or the npx skills CLI. Use when preparing skill distribution or diagnosing installation, missing resources and stale updates.

AI, LLMs & Agents

Formal Methods Drift Guard

423

mizchi/skills

Use after a formal model or verifier check already exists and the user wants to maintain it over time. Helps Codex compare specs/docs, implementation code/tests/config/logs, and formal models or CI checks for drift; classify whether the drift is in the spec, code, model abstraction, harness, or unresolved domain decision; run or plan verifier checks; and translate SAT/UNSAT changes, counterexample traces, proof failures, stale models, and CI results into domain-language review questions and ledger entries.

AI, LLMs & Agents

Retrospective Codify

423

mizchi/skills

Pair "what failed first" with "what finally worked" and codify the should-have-known-it insight as an ast-grep rule, a skill, or a CLAUDE.md rule. Meta-skill: invoke ONLY when the user explicitly says "codify today's lessons," "make it a skill," "drop it into lint," or asks to extract a reusable rule from a trial-and-error fix. Do NOT auto-invoke at every task completion. Spares future-you (or another agent) the same trap.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.