Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Multi Agent Orchestrator — measured AI agent skill | DecimalAI

stijnman/multi-agent-orchestrator

SkillScore86Maintained

Orchestrates complex multi-agent pipelines with DAG execution. Use for large projects or user says orchestrate agents, agent pipeline. Use when the user needs this capability. Triggers: orchestrate agents, agent pipeline, multi step agents.

by stijnman

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

decimalai skills pull stijnman-multi-agent-orchestrator

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-multi-agent-orchestrator/SKILL.md

Raw file: /s/stijnman-multi-agent-orchestrator/SKILL.md ↗ · machine-readable summary at /s/stijnman-multi-agent-orchestrator.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +32% lift-30% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-15	✗→✓	▲ Improved	-46%	0%
case-02	✗→✓	▲ Improved	-38%	0%
case-11	✗→✓	▲ Improved	-55%	0%
case-12	✗→✓	▲ Improved	-54%	0%
case-14	✗→✓	▲ Improved	-60%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/multi-agent-orchestrator/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Multi Agent Orchestrator

When to Use

User says orchestrate agents or task matches this capability
User says agent pipeline or task matches this capability
User says multi step agents or task matches this capability

Workflow

Build task DAG via adaptive-workflow-composer.
Spawn agents per node with scoped context.
Execute topological order; parallelize independent nodes.
Aggregate; run self-refine-loop on final output.

Integrations

multi-agent-coordinator
parallel-tool-orchestrator
self-refine-loop

Error Handling

| Failure | Response | |---------|----------| | DAG cycle | Break cycle; serialize conflicting nodes. |

Gotchas

Integrates self-refine-loop as skeptic reviewer agent.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Want to see if stijnman/multi-agent-orchestrator would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.