mgiovani/ai-arsenal / skills/orchestrate
orchestrate
VerifiedTurn any task into a model-tiered multi-agent plan, decompose it into subtasks, classify each as research, implementation, planning, or synthesis, map every subtask to the right subagent and model (haiku for research/exploration/finding, opus for planning, sonnet for everything else), then run independent tracks in parallel under strict one-owner-per-file discipline before synthesizing the result yourself. Use for "act as orchestrator", "spawn subagents for this", "delegate this with the right models", "run this in parallel", or any task large enough to fan out across multiple independent workstreams. Not for a single well-scoped feature with a known shape (use implement-feature), and not for pure task breakdown with no execution (use project-planner).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.3 KB |
| evals/evals.json | config | 2.7 KB |
| evals/trigger-eval.json | config | 1.8 KB |
evals/trigger-eval.json
View on GitHub[
{"query": "act as orchestrator and spawn subagents for this", "should_trigger": true},
{"query": "delegate this with the right models across parallel agents", "should_trigger": true},
{"query": "run this in parallel with separate subagents, one per file", "should_trigger": true},
{"query": "I need you to fan this out — decompose it and assign the right model to each piece", "should_trigger": true},
{"query": "spawn haiku for research and sonnet for implementation on this task", "should_trigger": true},
{"query": "break this into parallel workstreams with strict file ownership and orchestrate it", "should_trigger": true},
{"query": "orchestrate a research sweep across these five topics using subagents", "should_trigger": true},
{"query": "set up a model-tiered plan and run these subtasks in parallel", "should_trigger": true},
{"query": "can you orchestrate the migration of these 12 modules with subagents", "should_trigger": true},
{"query": "act as an orchestrator: decompose, assign models, parallelize, synthesize", "should_trigger": true},
{"query": "implement OAuth2 login for this app", "should_trigger": false},
{"query": "review this PR for correctness bugs", "should_trigger": false},
{"query": "break this project into a dependency-ordered task list with a Mermaid diagram", "should_trigger": false},
{"query": "run the CI checks locally on this branch", "should_trigger": false},
{"query": "fix the bug where checkout throws a 500 error", "should_trigger": false},
{"query": "refactor this module to reduce duplication", "should_trigger": false},
{"query": "write a conventional commit message for these changes", "should_trigger": false},
{"query": "generate a test suite for the payment module", "should_trigger": false},
{"query": "just fix this single typo yourself, it's a one-line change", "should_trigger": false}
]
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |