Orchestrate parallel sub-agent runs with automatic result aggregation.
npx skills add https://github.com/ai-ecoverse/slicc --skill workflows-ai-ecoverse
Please help me install this Agent Skill. Skill: workflows Source: https://github.com/ai-ecoverse/slicc/tree/main/packages/vfs-root/workspace/skills/workflows Command: npx skills add https://github.com/ai-ecoverse/slicc --skill workflows-ai-ecoverse
This Skill eliminates the inefficiency of sequential turn-by-turn processing for large, parallelizable tasks such as codebase-wide sweeps, cross-source research, multi-source data aggregation, and multi-angle planning, which would require excessive manual effort and context switching if handled one step at a time.
Use the workflows skill to run a parallel audit of all packages in the current codebase to collect all TODO comments and return a consolidated list of findings.
High-intent search queries and answers about installing and using this skill.
To run parallel agent workflows for large-scale codebase sweeps, you can fan out independent sub-tasks to multiple parallel sub-agents. This approach automatically aggregates results into a single output, eliminating inefficient sequential turn-by-turn processing.
Yes, you can execute batch processing tasks in the background without blocking your current turn. Workflows support non-blocking execution where results are delivered automatically upon completion, entirely eliminating the need for manual polling or waiting.
The best way to orchestrate multi-angle planning across parallel sub-agents is using a plain-JS orchestration API. This API allows you to define workflow metadata, launch parallel agent runs, and automatically aggregate the independent results into a consolidated output.
You can save successful workflow runs as persistent, reusable commands for repeated task orchestration by utilizing the skill's built-in saving feature. These saved commands can then be invoked later with custom JSON arguments for repeated use cases.
Yes, parallel sub-agent orchestration fully supports cross-source research and multi-source data aggregation. It fans out independent sub-tasks to multiple agents for faster execution and automatically aggregates the findings into a single consolidated report.
The limitation of using sequential turn-by-turn processing for parallelizable tasks is excessive manual effort and context switching. It is highly inefficient for large tasks like codebase-wide sweeps, making parallel sub-agent orchestration a better approach.
kinfeyBuild deterministic multi-step and multi-agent workflows in Python with the Microsoft Agent Framework.
bartoszwarzochaSave and load JSON session state with /save-session and /load-session commands.
bobmatnycManage multiple Git worktrees for parallel development across branches.
keugenekEnforce OS-level per-turn timeouts for AI coding agent loops.
