在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务,由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流;也用于用户明确要求模型路由、后台 Worker、Agents Team 或持久项目协作。简单问答、状态查询、单文件小改、强顺序任务和发布/付款/删除/账户操作不得自动触发。
npx skills add https://github.com/zjp1997720/codex-model-routing-team --skill codex-model-routing-team
把主 Agent 保持为任务总负责人,通过 Codex App 独立后台任务实现真实的 model 与 thinking 路由。禁止使用原生 spawn_agent 代替本流程。
简单问答、状态查询、单文件小改、强顺序任务,以及发布、付款、删除、账户或生产操作不得自动派遣。
当 Deep Research、PPT、课程生产或其他上游 Skill 已经定义任务拆分、阶段顺序、文件路径和验收标准时,读取 上游 Skill 适配协议。上游 Skill 保持业务流程主权;本 Skill 只负责模型路由、Thread 创建、并发额度、运行读取和归档。
禁止重复执行 Scale、改写上游阶段依赖或创建第二套事实源。安全上限仍然生效;预算不足时收敛 Worker 数量并明确报告。
AGENTS.md 的长期授权有效;没有授权就留在主任务内完成。GPT-5.6-Luna / GPT-5.6-Sol 路由、推理强度、职责,以及为后续阶段和重试预留的累计额度。codex_app__list_projects 定位项目;任何声明工作区输出路径的任务都使用匹配 project local,只有纯聊天交付才能 projectless。用 codex_app__create_thread 显式传入路由策略规定的 model 与 thinking。codex_app__read_thread 验证它已经实体化。只有读到真实 thread、cwd 与 turn 状态后,才记录为已创建并继续派遣。首个创建超时或返回未实体化状态时停止整批派遣,禁止改用 projectless 重试同一故障。codex_app__read_thread 读取结果。信息不足时只在原任务中用 codex_app__send_message_to_thread 追问一次;随后升级推理、切换模型或由主 Agent 接管。每个子任务最多两次执行机会。10. 主 Agent 亲自核对事实、运行验证、处理冲突并整合最终交付。只对已实体化、状态为 completed/idle、输出文件已经验证、且结果已采纳的轻量任务调用 codex_app__set_thread_archived;逐个归档并等待每次确认。失败、争议或待审任务保留。
11. 每次创建成功后立即记录 thread_id / role / model / thinking;验收与归档后补充 status / output / archived。最终汇报任务数、逐 Thread 路由、模型分布、升级/重试、采纳结果、归档情况和未解决风险。
gpt-5.6-luna 与 gpt-5.6-sol。精确模型 ID 和推理强度以 路由策略 为唯一事实源。create_thread / send_message_to_thread 工具描述中的“支持模型”列表只能用于接口说明,不能覆盖本 Skill 的路由策略。gpt-5.5、gpt-5.4、gpt-5.4-mini 或 gpt-5.3-codex-spark。如果 Luna / Sol 创建被运行时拒绝,停止派遣并报告模型目录冲突。create_thread 超时后产生的未实体化 ID 不是可管理任务。禁止恢复、追问或归档该 ID,也禁止直接修改 Codex 数据库;记录故障并停止创建。fork_thread 会复制已完成历史,可能显著增加上下文成本。只有源任务历史很短且继承上下文确有价值时才能作为应急路径;其他情况由主 Agent 接管。交付必须完整、自洽、经过主 Agent 验证,并包含可审计的模型路由摘要。上游 Skill 模式另外报告 reserved slots、阶段门、输出采纳和归档状态。触发、并发、归档和失败边界见 验证案例。
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.
Take zjp1997720/codex-model-routing-team from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.