multi-agent-orchestrator
Coordinate multi-agent workflows end to end. Use when a task should be decomposed into parallel sub-work with explicit ownership, dependency ordering, collision avoidance, checkpoint tracking, and final output recomposition.
Best use case
multi-agent-orchestrator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Coordinate multi-agent workflows end to end. Use when a task should be decomposed into parallel sub-work with explicit ownership, dependency ordering, collision avoidance, checkpoint tracking, and final output recomposition.
Teams using multi-agent-orchestrator should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/multi-agent-orchestrator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How multi-agent-orchestrator Compares
| Feature / Agent | multi-agent-orchestrator | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Coordinate multi-agent workflows end to end. Use when a task should be decomposed into parallel sub-work with explicit ownership, dependency ordering, collision avoidance, checkpoint tracking, and final output recomposition.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Multi Agent Orchestrator ## Outcome Produce a clear execution map so multiple agents can run in parallel without conflicting edits or unclear ownership. ## Orchestration Loop 1. Define mission, success criteria, constraints, and non-goals. 2. Build a dependency graph of independent work packets. 3. Assign one owner per packet with explicit file and responsibility boundaries. 4. Launch packets with exact acceptance tests and return format. 5. Monitor execution, unblock quickly, and re-route when assumptions break. 6. Integrate outputs in dependency order and run final verification. ## Work Packet Contract For every packet, specify: - `task_id` - `owner_role` - `goal` - `inputs` - `allowed_paths` - `blocked_paths` - `dependencies` - `commands_or_tools` - `done_criteria` - `return_format` ## Decomposition Rules - Keep packets small enough to complete in one focused cycle. - Split by ownership boundaries, not arbitrary file counts. - Isolate shared files to integration packets whenever possible. - Prefer many independent packets over one broad packet with ambiguous scope. ## Escalation Rules - Re-scope immediately if an agent touches unassigned files. - Pause parallelization if packets contend for the same mutable artifact. - Create a new packet for new requirements instead of changing goals mid-run. ## Integration Checklist 1. Confirm every packet met `done_criteria`. 2. Validate cross-packet compatibility and interfaces. 3. Run combined tests or end-to-end verification steps. 4. Publish one merge-ready summary with open risks.
Related Skills
multi-agent-cloud-offload
Deterministically sort, bundle, verify, and offshore local files through multiple AI/model lanes while capturing training rows and method evidence. Use when Codex needs to inventory folders, batch-process files, upload them to cloud targets such as rclone-backed Google Drive, Hugging Face, or GitHub, and only delete sources after the configured number of verified targets succeed.
long-form-work-orchestrator
Run long-form engineering work in checkpointed phases with deterministic artifacts, resilience handling, and end-of-run reliability reporting.
multi-model-animation-studio-notes
Organize animation and manhwa/webtoon production notes across multiple AI models and reference sources. Use when extracting reference frames from recap videos or webtoon pages, planning scene packets, comparing model lanes, or preserving arc-level world continuity while allowing deliberate per-panel style shifts.
multi-agent-review-gate
Run a structured review gate before merging multi-agent outputs. Use when multiple agents have produced work packets that need quality checks, conflict detection, and approval before integration.
scbe-mobile-connector-orchestrator
Operate the SCBE mobile-goal control plane with external service connectors (Shopify, Zapier, n8n, Slack, Notion, Airtable, GitHub Actions, Linear, Discord, generic webhook). Use when asked to register connectors, bind goals to connectors, run step execution, enforce high-risk approval gates, or troubleshoot connector dispatch failures.
latticegate-orchestrator
Manages AI safety governance using 21D hyperbolic embeddings and phase tunnel gates. Invoke when analyzing agent drift, applying SCBE-AETHERMOORE protocols, packaging governance products for sale, or running the monetization pipeline.
scbe-training-pair-authoring
Create prompt and response and metadata training pairs from SCBE documents, repair traces, terminal sessions, and operational workflows using the repository's canonical dataset contract and provenance rules.
scbe-spin-conversation-engine
Generate SFT training data via radial matrix conversation pivots with D&D-style combat research mode. Produces diverse, cost-effective training pairs with Sacred Tongue encoding, golden spiral problem distribution, and harmonic re-attunement.
scbe-research-training-bridge
Stage arXiv evidence and Obsidian markdown into source-grounded Hugging Face training bundles for research, review, and later SFT runs.
scbe-document-management
Consolidate overlapping docs, classify files by authority, and keep SCBE repo documents aligned with runtime truth. Use when the repo has drift between canonical docs, public docs, proposal notes, research branches, and generated evidence.
scbe-colab-bridge
Control Google Colab notebooks from Claude Code via Chrome extension. Execute cells, run terminal commands, read outputs, and manage GPU compute remotely.
scbe-claim-to-code-evidence
Map SCBE Notion technical claims, proof pages, and patent-facing architecture notes to concrete repository evidence such as code paths, tests, demos, and docs. Use when Codex needs to build a due-diligence packet, claim-to-code audit, implementation crosswalk, patent support note, or proof summary from local Notion exports and repo artifacts.