number-orchestrator
Skill4 starsChanged 2 months agoMITView on GitHub
把游戏体验目标转成数值模型、可调参数、实验和配置说明。用于新建或调整数值,不代替领域规则与真实试玩。 Turn game experience goals into numerical models, tunable parameters and balance experiments.
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- build-instant-qte-h5Skill
- build-pseudo-live2d-characterSkill
- day-night-cycleSkill
- day-time-systemSkill
- fps-feelSkill
- free-input-outputSkill
- game-skill-routerSkill
- improve-arpg-hit-feelSkill
- inventory-systemSkill
- number-adventure-likeSkill
- number-card-roguelikeSkill
- number-diablo-arpg-likeSkill
- number-legend-likeSkill
- number-sharedSkill
- number-shmup-likeSkill
- number-sim-management-likeSkill
- number-survivor-likeSkill
- number-tower-defense-likeSkill
- number-turn-card-likeSkill
- scene-transitionSkill
- screen-shake-effectsSkill
- stamina-systemSkill
- survival-ui-guidelinesSkill
The file
Files
游戏数值实验流程
本模块由 Whaocaii 主导设计与维护,使用 AI 辅助编写。当前版本为 0.1.0 工作草稿。按用户的目标与现有项目约束执行;仅使用实际可用的工具。
输入
- 玩家目标、局长或成长周期,以及当前可用数据
- 待调整参数、禁止改变的机制和目标人群
工作过程
- 将主诉拆成观测量、目标方向和可接受区间;不要把“更爽”直接翻译成统一加伤害。
- 列出变量、单位、来源、默认值和依赖。用同级 number-shared 检查量纲及统计口径。
- 按核心循环选择一个最相关的领域模块;混合玩法只有在两个循环分别需要建模时才选择多个领域。
- 先算一个可解释的基准样本,再分别改变少量关键参数。记录体验收益与副作用,不仅优化单一均值。
- 给出配置改动、计算依据、预期表现及失败判据。没有真实数据时用明确标为假设的样本,不伪装成用户行为。
- 完成后区分数学检查、模拟结果与试玩观察。将仍待验证的结论列为下一轮实验。
交付
- 参数表:名称、单位、基准、候选、依据、影响对象
- 实验表:场景、测量方式、目标、结果、结论
检查
- 同一参数只有一个实际配置来源
- 参数变化能追溯到具体目标,未验证结论标明状态
使用案例
一局 8 分钟的游戏前两分钟无聊,后期突然过难。根据提供的击杀记录提出两套可比较的曲线。
验收时按上面的检查项判断结果;只读完本文件不代表完成了任务。
同级依赖
number-shared。通过本仓库安装脚本安装会携带这些模块;缺失时说明限制,不猜测依赖内容。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

