Coordinate two AI agents to plan complex problems with root-cause analysis.
npx skills add https://github.com/getpaseo/paseo --skill paseo-committee
Please help me install this Agent Skill. Skill: paseo-committee Source: https://github.com/getpaseo/paseo/tree/main/skills/paseo-committee Command: npx skills add https://github.com/getpaseo/paseo --skill paseo-committee
The Committee Skill coordinates two high-reasoning agents to step back from a task, perform root-cause analysis, and produce a robust plan before implementation.
Launch the two agents as a committee and begin the planning cycle, awaiting a merged plan for user confirmation.
High-intent search queries and answers about installing and using this skill.
Multi-agent planning coordinates two high-reasoning AI agents to perform root-cause analysis and challenge assumptions before implementation. This dual-agent approach surfaces blind spots and converges on a robust plan, preventing tunnel vision in complex software development tasks.
Root-cause analysis in multi-agent workflow planning involves two agents stepping back from a task to investigate underlying issues before acting. This structured lifecycle process ensures a solid plan is established, preventing premature conclusions and avoiding looping behaviors in research contexts.
Yes, dual-agent planning is ideal for stuck, ambiguous, or high-stakes product development tasks. The committee structure enforces guardrails, discourages premature conclusions, and requires explicit user confirmation before finalizing changes, ensuring alignment with your product goals.
To start a two-agent committee for workflow planning, launch both agents as a committee to begin the planning cycle. The dedicated driver coordinates planning, implementation, and review phases, enforcing wait semantics and awaiting a merged plan for your explicit confirmation.
You should avoid using a multi-agent committee approach for simple tasks that do not require root-cause analysis or complex planning. The structured lifecycle, guardrails, and dual-agent coordination add overhead best suited for high-stakes, ambiguous problems where avoiding tunnel vision is critical.
diegosanchespereira1Diagnose complex problems and convert vague challenges into actionable problem statements.
fascariPlan and implement features phase-by-phase with linting and user authorization before commits.
KQDtianxiaKCoordinate two AI agents to perform root-cause analysis and produce a unified plan.
SteelMorganGenerate a JSON task breakdown with dependencies and self-checks for linear execution.
