spec-card-authoring
Skill0 starsChanged 23 days agoMITView on GitHub
给一个系统或一条效果写规格卡时使用:总则铁律 + 逐条规格 + 演出双栏 + 边界与验收,保证策划与程序对同一份文字达成一致
In this repository12 other files it gives its agents.
- ai-output-verifySkill
- asset-import-pipelineSkill
- bug-diagnosis-chainSkill
- codex-rules-verifySkill
- config-table-pipelineSkill
- gameplay-breakdownSkill
- handoff-docSkill
- unity-build-matrixSkill
- unity-commandline-playtestSkill
- unity-editor-verifySkill
- unity-smoke-assertionsSkill
- visual-evidence-reviewSkill
The file
Files
规格卡写法
何时触发
- 一个系统/一批效果要交给程序实现,需要一份「实现唯一依据」的文档
- 需求在群里来回改,需要收敛成一份可对照的规格
结构
- 头部:文档名 + 版本 + 状态(已定稿 / 待拍板)+ 一句话说明它是谁的唯一依据。
- 总则铁律表:编号(C1、C2…)+ 铁律内容。写「不能怎么做」比写「要怎么做」更能防歧义。
- 逐条规格:每条效果一栏,效果 + 演出双写——只写数值会出现「数字对了但玩家看不见」。
- 边界与异常:目标不存在、结算中途死亡、连续触发、叠加规则。
- 验收:每条规格对应一条可执行的验收用例(能自动化就标自动化)。
- 变更记录:日期 + 谁拍板 + 改了什么,方便回溯「为什么是这个数」。
写的时候
- 用「当…则…」句式,避免「尽量」「适当」。
- 一切「看起来/感觉上」的要求都要翻译成可观察行为(颜色、时长、位置、文案)。
- 数值给区间与容差,不给「大概」。
- 演出需求写清时机:触发前 / 结算中 / 结算后。
验收
- 每条规格都能对应一条验收用例
- 没有「见上」「同上」这类指向不明的表述
- 演出与数值分栏写清
- 边界情况至少覆盖 3 种
- 变更记录可追溯到拍板人
坑
- 规格里混着「讨论过程」——决策写进变更记录,正文只留结论。
- 只写效果不写演出,程序按最小实现交差,玩家看不到反馈。
- 数值改动不更新规格卡,两周后没人知道当前值是多少。
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.

