Ready to supercharge your AI agents?

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

Multi Agent Coordinator — measured AI agent skill | DecimalAI

stijnman/multi-agent-coordinator

SkillScore73Maintained

Coordinates multiple agents with role assignment and handoffs. Use for paral lel work or user says coordinate agents, multi agent team. Use when the user needs this capability. Triggers: coordinate agents, multi agent team, agent roles, delegate 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-coordinator

Get this skill — curl · raw file

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

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

—-33% tokens0% turns73% of whole cases pass with skill (16/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	77%	0%
case-05	✗→✓	▲ Improved	-14%	0%
case-06	✗→✓	▲ Improved	-12%	0%
case-07	✗→✓	▲ Improved	-71%	0%
case-11	✗→✓	▲ Improved	-33%	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-coordinator/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Multi Agent Coordinator

When to Use

User says coordinate agents or task matches this capability
User says multi agent team or task matches this capability
User says agent roles or task matches this capability
User says delegate agents or task matches this capability

Workflow

Define roles: planner, executor, reviewer (minimum).
Assign subtasks per role.
Establish handoff format between agents.
Merge outputs; run goal-verifier on combined result.

Integrations

multi-agent-orchestrator
desktop-subagent-connector
goal-verifier

Error Handling

| Failure | Response | |---------|----------| | Agent conflict | Reviewer role breaks tie. |

Gotchas

Max 5 parallel agents to avoid context sprawl.

Example

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

Want to see if stijnman/multi-agent-coordinator 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.