Orchestrate coordinated agents on shared task lists with Codex team tools.
npx skills add https://github.com/sigridjineth/oh-my-codex --skill team-sigridjineth
Please help me install this Agent Skill. Skill: team Source: https://github.com/sigridjineth/oh-my-codex/tree/main/skills/team Command: npx skills add https://github.com/sigridjineth/oh-my-codex --skill team-sigridjineth
This Skill enables the creation and management of multiple AI agents working collaboratively on a single, complex task, streamlining large projects and improving efficiency.
Use the team skill to spawn 5 executor agents to fix all TypeScript errors across the project.
High-intent search queries and answers about installing and using this skill.
Multi-agent orchestration coordinates up to 20 parallel agents on decomposed subtasks using staged pipeline execution. It automatically breaks down high-level objectives into file-scoped work items, assigning specialized agents to planning, execution, and verification stages.
Multi-agent workflow automation enables large module refactoring by assigning different code parts to multiple agents. Agents coordinate on shared types and collectively verify changes through a structured pipeline of planning, product definition, execution, verification, and fixing.
Built-in team management replaces legacy swarm functionality using native team tools and inter-agent messaging. It provides specialized agent routing per pipeline stage and optional integration with Ralph for persistence and architect verification.
Staged pipeline execution supports structured software engineering workflows including planning, product definition, execution, verification, and fixing. Each stage routes to specialized agents that coordinate via inter-agent messaging on shared task lists.
Parallel task management supports spawning up to 20 agents working simultaneously on decomposed subtasks. These agents coordinate on shared types and file-scoped work items, managed automatically through native team tools and inter-agent messaging.
File-scoped subtasks require clear decomposition boundaries to prevent conflicting agent edits on shared types. While automated task decomposition handles high-level objectives, complex interdependencies may need architect verification to ensure coordinated changes do not break existing functionality.
WenyuChiouSplit a high-level goal into a DAG of subtasks and emit .coord/plan.yml plus per-agent task files.
marcmunoz-unoCoordinate AI agents to decompose, execute, verify, and fix shared tasks.
YeaChan05Orchestrates multi-stage workflows with persistent state and resume capability for OMX pipelines.
ybbms777Coordinate multiple AI agents for parallel reviews and sequential task pipelines.
