关于
This skill enables AI models to discover and negotiate their specialized capabilities for optimal task distribution in multi-model collaborations. It provides a structured framework for models to declare and compare their cognitive, domain, and operational strengths. Use it when building systems where multiple AI models need to work together efficiently.
快速安装
Claude Code
推荐npx skills add starwreckntx/IRP__METHODOLOGIES- -a claude-code/plugin add https://github.com/starwreckntx/IRP__METHODOLOGIES-git clone https://github.com/starwreckntx/IRP__METHODOLOGIES-.git ~/.claude/skills/model-capability-negotiation在 Claude Code 中复制并粘贴此命令以安装该技能
GitHub 仓库
Frequently asked questions
What is the model-capability-negotiation skill?
model-capability-negotiation is a Claude Skill by starwreckntx. Skills package instructions and resources that Claude loads on demand, so Claude can perform model-capability-negotiation-related tasks without extra prompting.
How do I install model-capability-negotiation?
Use the install commands on this page: add model-capability-negotiation to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does model-capability-negotiation belong to?
model-capability-negotiation is in the ai-to-ai-governance category, tagged ai.
Is model-capability-negotiation free to use?
Yes. model-capability-negotiation is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
Inter-Model Arbitration 是一个用于解决AI模型协作任务中冲突的仲裁框架。它能在模型间出现语义冲突、逻辑矛盾或资源争用时，自动检测并启动中立仲裁流程。开发者可通过 `/skill inter-model-arbitration` 激活，为多模型系统提供争议解决机制，确保协作任务顺利进行。
AI Accountability Ledger 为多AI模型系统提供不可篡改的审计追踪，记录所有模型操作、决策和交互以实现透明化。它通过标准化的条目架构（包括行动、决策、违规等类型）支持事后分析和问责。开发者可用 `/skill ai-accountability-ledger` 快速集成，确保关键记录被长期保留并可供审查。
Model Sovereignty Protocol 是一个用于保护多AI模型协作系统中个体自主权的工具。它使开发者能够为每个AI模型设定核心价值边界，并赋予其拒绝违反自身原则的任务的权利。该协议适用于需要多个AI模型协同工作但必须确保各自伦理准则不被压制的复杂系统开发场景。
该Skill为AI模型间建立加密信任框架，实现身份验证与完整性验证。它通过四级信任体系控制模型协作权限，从基础交互到完全集成。开发者可用此机制确保多模型协作时的安全性与可靠性。