document-maintenance
Skill220 starsChanged 8 days agoMITView on GitHub
在已确认写集内创建和更新本地 Markdown,核目的、适用对象、原件保全与接续;不负责业务事实判定、外部发布或自动清理。
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- capability-evaluationSkill
- code-implementationSkill
- code-reviewSkill
- conclusion-challengeSkill
- delivery-planningSkill
- docker-build-isolationSkill
- document-reviewSkill
- evidence-collectionSkill
- evidence-diagnosisSkill
- java-build-isolationSkill
- java-spring-checkSkill
- module-planningSkill
- principle-reviewSkill
- requirement-clarificationSkill
- semantic-reviewSkill
- sql-reviewSkill
- task-executionSkill
- technical-design-reviewSkill
- technical-designSkill
- verificationSkill
- workspace-isolationSkill
The file
Files
目的:将确认的文档修改写入正确位置,核目的、适用、原件保全和实际读回。
适用于:已确认项目与精确写集内的本地 Markdown 创建、更新和维护;不代业务事实判定或外发。
文档维护
输入与标准消费
接收责任 Agent 给出的目标、读者、来源/候选、实际工作根、允许写集和验收。先消费目的与适用对象,返回目的相符/拟变化/未知与适用匹配/不匹配/待核及依据。
新建或修改方法原子时同时消费原子属性,导航和模板不伪装成原子。按需要采用按需加载、原件保留;方案或执行文件再消费上下文拆解和执行接续。规则正文保持单源,已有有效判断直接复用。
写入与检查
- 核当前目的、正文和实际差异,将新声明从真实职责归纳;变更职责的必要决定沿当前授权,不用补字段扩大承诺。
- 核精确路径、原候选与已有修改,必要时在授权位置保全原字节和版本;历史原件不注入新头部。
- 完成当前写集,读回实际字节,检查正文、来源、引用、模板语法与目的/范围是否一致。
- 使用文档声明检查工具核字段位置、清单和历史字节;如需修改公开清单与档案旁证,同步到相应入口。结构通过不代语义判断。
- 将候选身份、前后差异、目的和适用判断、实际检查、缺项与恢复条件交回责任 Agent。需要分离审查时由上层安排,本 Skill 不自行启动角色或发布。
异常与停止
并发冲突或结果未知先读回,不盲重写;目的不明、来源不清或关键前置缺失只停相交动作。没有跨设备恢复、强锁或身份认证实现时不作这些保证。
返回:Skills。
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.

