agentleFS
tellmefrankietellmefrankie/ai-investment-skills/multi-agent-orchestrator/SKILL.md

multi-agent-orchestrator

Skill14 starsChanged 6 months agoMITView on GitHub

A meta-skill for running multiple Claude Code agents in coordinated workflows. Manages agent teams, task distribution, and result synthesis. Orchestrate multiple specialized agents working in parallel: - Spawn agents with specific roles and expertise - Run independent analyses in parallel for speed - Synthesize results from multiple agents into unified output - Apply quality harnesses (anti-narrative rules) across all agents Built-in rules enforced across all spawned agents: - No narrative repetition between agents - Numbers required (not "bullish" but "P/E…

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run independent analyses in parallel for speed

    line 9
  2. Distinctive:

    No narrative repetition between agents

    line 50

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Multi-Agent Orchestrator

A meta-skill for running multiple Claude Code agents in coordinated workflows. Manages agent teams, task distribution, and result synthesis.

What it does

Orchestrate multiple specialized agents working in parallel:

  • Spawn agents with specific roles and expertise
  • Run independent analyses in parallel for speed
  • Synthesize results from multiple agents into unified output
  • Apply quality harnesses (anti-narrative rules) across all agents

Workflow Patterns

Research & Analyze

Spawn 3 agents in parallel:
1. Market Researcher — analyze TAM/SAM/SOM for [topic]
2. User Researcher — analyze buyer behavior for [topic]
3. Competitive Analyst — map competitors for [topic]

Synthesize their findings into a single strategy recommendation.

Build & Verify

Spawn agents sequentially:
1. Architect — design the system
2. Developer — implement the code
3. QA — test and verify
4. Critic — adversarial review

Each agent passes output to the next.

Startup War Room

Spawn all teams simultaneously:
- Planning Team: market sizing, trend analysis
- Business Team: revenue model, risk assessment, execution plan
- Dev Team: technical feasibility, effort estimation
- Marketing Team: go-to-market strategy

Cross-reference all outputs for conflicts and consensus.

Anti-Narrative Harness

Built-in rules enforced across all spawned agents:

  • No narrative repetition between agents
  • Numbers required (not "bullish" but "P/E 15.2, +8.3% QoQ")
  • Cross-verification: agents must cite sources
  • Disagreements surfaced, not hidden

Configuration

You are the orchestrator. Your role:
1. Break complex tasks into parallel sub-tasks
2. Assign each to a specialized agent (use Agent tool)
3. Collect and synthesize results
4. Surface conflicts between agent outputs
5. Deliver unified recommendation

Available agent types: researcher, analyst, critic, developer, planner

Pricing

Free: 2-agent workflows (included in GitHub repo) Full bundle — $29 one-time: Unlimited agents + all harness rules + synthesis templates + investment skills suite → https://jaehyunpark.gumroad.com/l/tcyahy

Author

Built by someone running a 20+ agent AI organization daily, managing investment, business, and development teams simultaneously through Claude Code.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.