multi-perspective-plan Skill
Multi-perspective planning with rebuttal rounds and adversarial review loop. Use when: planning complex changes, designing architecture, evaluating implementation strategies, drafting implementation plans, or when /plan is invoked. Spawns three planner subagents, runs rebuttals on disagreements, synthesizes their outpu Published by microsoft in bocpy.
What is multi-perspective-plan Skill?
Multi-perspective planning with rebuttal rounds and adversarial review loop. Use when: planning complex changes, designing architecture, evaluating implementation strategies, drafting implementation plans, or when /plan is invoked. Spawns three planner subagents, runs rebuttals on disagreements, synthesizes their outpu Published by microsoft in bocpy. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Design and media
- Design and media use cases
Technical details
- Install or run with Copy skill directory
When to use multi-perspective-plan Skill
- Use it for design and media.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/bocpy
- Skill file: .github/skills/multi-perspective-plan/SKILL.md
What it does
Multi-perspective planning with rebuttal rounds and adversarial review loop. Use when: planning complex changes, designing architecture, evaluating implementation strategies, drafting implementation plans, or when /plan is invoked. Spawns three planner subagents, runs rebuttals on disagreements, synthesizes their outpu
Skill instructions
Multi-Perspective Planning Generate a robust implementation plan by soliciting three competing viewpoints, synthesizing them, and then hardening the result through an adversarial review loop. When to Use - Planning non-trivial code changes that touch multiple subsystems - Evaluating architecture or design trade-offs - Any time you want a plan stress-tested before implementation Persistence and Restart Every intermediate artifact produced by this skill is written to disk under .copilot/plans/<slug/, where <slug is a short kebab-case name derived from the planning task (e.g. work-stealing-scheduler). This makes the process fully resumable: if any step fails, is interrupted, or produces an unsatisfactory result, you can re-run only the affected step using the on-disk artifacts from prior steps as input. Directory layout .copilot/plans/<slug/ ├── 00-context.md Step 1 output ├── 10-plan-speed-lens.md Step 2 outputs (one per lens) ├── 10-plan-usability-lens.md ├── 10-plan-conservative-lens.m
Explore related resources
Frequently asked questions
What is multi-perspective-plan?
multi-perspective-plan is a open-source AI agent skill with Copy skill directory. Multi-perspective planning with rebuttal rounds and adversarial review loop.
Who is multi-perspective-plan best for?
multi-perspective-plan is best for reusing agent instructions, scripts, and references, design and media workflows.
How do I install multi-perspective-plan?
Install or run multi-perspective-plan using Copy skill directory. Check multi-perspective-plan for the latest setup command.
Is multi-perspective-plan actively maintained?
multi-perspective-plan may need a closer maintenance check before production use.
Auto-fetched from GitHub.
