agentleFS
PeiiiiPeiiii/nextclaw/.agents/skills/autonomous-maintainability-campaign/SKILL.md

autonomous-maintainability-campaign

Skill263 starsChanged 39 days agoMITView on GitHub

仅当用户明确要求跨上下文、整夜或低监督持续执行可维护性治理战役,且治理规则已明确时使用;普通重构、bugfix 和一次性清理不触发。

The file

Files
SKILL.md

自治可维护性治理战役

前提

本 skill 只负责长期治理循环,不重新定义代码、目录或验证规范。启动前必须有明确目标、允许范围、停止条件、当前迭代和可执行的最小验证。

最小状态

在当前有效迭代的 work/ 中维护:

  • working-notes.md:目标、当前事实、已完成批次、剩余候选和下一步;
  • state.json:机器续跑需要的当前批次、状态、验证和更新时间。

只保留当前真相,不写 transcript。没有有效迭代且用户未授权提前留痕时,不为启动战役擅自创建目录。

循环

  1. 读取最小状态和最新工作区事实。
  2. 从候选中只选择一个高置信、范围内、可独立验证的批次。
  3. 按已冻结的标准开发合同完成该批次;结构、死代码等专项只在命中时加载一个 owner,不重新加载上游 lifecycle。
  4. 当前批次实现完成后返回生命周期,由 Validation 与 Review 阶段分别完成风险证明、maintainability 自动检查和条件主观复核。
  5. 写回结果、证据、未解决项和下一批候选。
  6. 只有下一步仍高置信且未命中停止条件时继续。

选择原则

  • 优先删除重复路径、死代码、错误 owner、无语义 wrapper 和明确治理违规。
  • 一个批次只解决一个责任域,不借治理名义扩展产品功能。
  • 显式零增长战役才启用 guard 的 --non-feature;普通清理不靠无关删减抵消行数。
  • 不在 dirty 用户文件上做无法隔离的机械重写,不自动 commit/push/release。

停止

  • 候选需要产品或架构决策;
  • 证据不足、验证环境不可用或将触碰未授权外部状态;
  • 连续候选收益低于调查/回归成本;
  • 用户暂停,或目标已完成。

结束时汇总已完成批次、主要证据、剩余候选、工作区状态和恢复入口。不要把每轮过程输出重新加载为上下文。

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.