⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
multi-agent-orchestration
Use when three or more AI agents are available and a task needs coordinated execution, role assignment, independent verification, risk controls, or lower token/API cost. Activation is configurable: global, keyword-triggered, or manual.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
// README
Multi-Agent Orchestration Skill
A portable, capability-first protocol for coordinating three or more AI agents with explicit ownership, independent verification, risk-based execution, and token-aware routing.
Features
- discovers capabilities instead of assuming agent names imply roles
- assigns coordinator, implementer, verifier, environment, and domain roles
- enforces one primary writer per file or resource
- adds a stronger pipeline for user-marked important or critical work
- stops on failed gates and requires evidence before completion claims
- reduces token and API cost with compact packets, bounded outputs, caching, parallel read-only checks, and model escalation
It does not provide an absolute guarantee; it makes failures visible, recoverable, and less likely.
Activation (when to use)
The skill engages in one of three modes, configured under activation: in config/agents.example.yaml:
- global - engages for every task
- keyword - engages only when the task text matches configured keywords (default; token-saving)
- manual - engages only when the user explicitly invokes it
For keyword mode, run the trigger detector before starting:
node scripts/detect-trigger.mjs --text "<task text>" --config config/agents.example.yaml
Exit code 0 means ENGAGED (use the skill); 1 means NOT_ENGAGED. Exclude keywords veto engagement even when a trigger matched.
Install
Option A: one-click installer (auto-detects common skill dirs).
Windows PowerShell:
powershell -ExecutionPolicy Bypass -File scripts/install.ps1
Linux/macOS shell:
./scripts/install.sh
Option B: clone and copy SKILL.md, references, and config into the skill directory supported by your host.
Validate your config locally:
node scripts/validate-config.mjs
Host adapter
Implement these five primitives: discover_agents, dispatch, lock, record, and approve. If a primitive is unavailable, use a documented manual fallback and record the limitation.
Usage
This is important. Three agents are available. Assign the best implementation agent, have another independently test it, and do not deploy.
Expected: capability inventory, role assignment, task packet, ownership lock, implementation evidence, independent verification, acceptance report, and awaiting_user_approval for deployment.
License
MIT.
// HOW IT'S BUILT
KEY FILES