Decompose engineering tasks into parallel execution plans for multi-agent systems.
npx skills add https://github.com/phintruong/skills --skill orchestrate-phintruong
Please help me install this Agent Skill. Skill: orchestrate Source: https://github.com/phintruong/skills/tree/main/orchestrate Command: npx skills add https://github.com/phintruong/skills --skill orchestrate-phintruong
This skill solves the bottleneck of managing complex engineering tasks by decomposing them into structured, parallelizable subtasks that can be executed by multiple specialized AI agents.
Invoke the orchestrate skill by typing /orchestrate followed by the engineering task you want to decompose into a parallel execution plan.
High-intent search queries and answers about installing and using this skill.
Task decomposition for multi-agent orchestration works by mapping subtask dependencies and assigning each subtask to an agent based on its specific tool capability profile, such as coding, architecture, or UI development.
You coordinate multiple AI agents by using a wave-based execution plan, ensuring foundational work finishes before integration tasks while allowing independent features to be developed in parallel across the distributed development cycle.
Yes, multi-agent orchestration supports agent assignment based on unique tool capability profiles, routing coding, architecture, or UI development subtasks to the most suitable AI agent for the job.
Wave-based workflow coordination is an execution strategy that manages complex engineering workflows through sequential waves, completing foundation work before moving to integration while allowing parallel execution for independent features.
You can track distributed development status by generating instruction files for each subtask, which the orchestration system uses to monitor progress and manage dependency mapping throughout the multi-agent execution cycle.
yebotManage Linear issues, cycles, projects, and milestones via the linearis CLI.
EvanLavender13Execute feature plans by dispatching wave-based parallel agents to implement files.
Kingly-AgencyBuild RAG pipelines that ground LLM responses with retrieved external knowledge.
MeroZemoryParse requirements, delegate to specialists, and verify completion before implementation.
