biannian
Skill2 starsChanged 6 months agoMITView on GitHub
扫描自上次 tag 以来的 git log,按三省六部语境归类变更,输出结构化 CHANGELOG 条目
In this repository26 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analysis-frameworkSkill
- architecture-overviewSkill
- audit-boundariesSkill
- communication-protocolsSkill
- dispatch-rulesSkill
- fault-toleranceSkill
- governance-coreSkill
- hanlinSkill
- intent-classificationSkill
- kejuSkill
- morning-courtSkill
- parallel-executionSkill
- permission-matrixSkill
- qijuzhuSkill
- redline-referenceSkill
- report-formatSkill
- review-coverageSkill
- shengzhiSkill
- special-directivesSkill
- team-bootstrapSkill
- ticket-formatSkill
- token-optimizationSkill
- tuichaoSkill
- veto-mechanismSkill
- zouzheSkill
The file
Files
Skill: 编年
适用 Agent:太子(Lead) 加载时机:皇上输入
/biannian时,或发版前
功能
自动生成变更日志,将 git 历史翻译为三省六部语境下的结构化记录。
执行流程
第一步:确定范围
# 获取最近的 tag
git describe --tags --abbrev=0 2>/dev/null || echo "无历史 tag,扫描全部提交"
# 获取范围内的提交
git log <last-tag>..HEAD --oneline --no-merges若无历史 tag,扫描全部提交历史。皇上也可指定范围(如 /biannian v0.1.0..v0.2.0)。
第二步:分类归档
太子阅读每条 commit message,按以下类别归类:
| 类别 | 图标 | 含义 | 示例 |
| 新旨意 | 📜 | 全新功能或模块 | 新增 Skill、新增 Hook |
| 修缮 | 🔧 | 优化改进现有功能 | 调整流程、优化格式 |
| 封驳修正 | 🔍 | 因门下审议驳回而修改 | 修复一致性、补充约束 |
| 平叛 | ⚔️ | 修复 bug 或异常 | 修复脚本错误、修正逻辑 |
| 典章 | 📝 | 文档与规范变更 | 更新 README、修改 Skill 定义 |
| 科举 | 📋 | 测试与验证 | 添加检查、验证流程 |
| 基建 | 🏗️ | 基础设施变更 | CI/CD、配置文件、依赖 |
第三步:输出 CHANGELOG 条目
## [版本号或日期] — 编年史
### 📜 新旨意
- {commit 摘要} ({short hash})
- ...
### 🔧 修缮
- {commit 摘要} ({short hash})
- ...
### 🔍 封驳修正
- ...
### ⚔️ 平叛
- ...
### 📝 典章
- ...
### 📋 科举
- ...
### 🏗️ 基建
- ...空类别不显示。
第四步:呈报与确认
太子将编年史条目呈给皇上审阅。皇上确认后可选择:
- 追加到 CHANGELOG.md(若存在)
- 仅查看不写入
- 修改后再写入
约束
- 不修改 git 历史,仅读取
- 分类基于 commit message 语义判断,无法判断时归入"修缮"
- 写入 CHANGELOG.md 前必须经皇上确认
- 合并提交(merge commits)默认跳过
- 编年仅处理 git 历史的结构化归类与 CHANGELOG 输出,文档撰写与规范维护仍属礼部职责
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.

