agentleFS
20231118185SSPU20231118185SSPU/prompt-optimizer/CLAUDE.md

prompt-optimizer

CLAUDE.md1 starsChanged 4 months agoMITView on GitHub

每条开发指令执行前,静默完成三档路由评估: 1. 读取 .align/lessons.md → spec.md → facts.md / glossary.md / state.md;三个分类文件未齐全时同时读取 context.md,全部缺失时只读 legacy 2. 五维快评:简单且明确 → 直接执行(但交付前必须自验证) 3. 有缺口但项目上下文可补全 → 开头展示 ≤3 行补全回执(补全内容 + 来源 + 撤销补全 <ID>),然后直接执行 收到撤销口令时停止沿用指定项,回到原始请求重新分析;已产生改动则先报告,未经确认不自动回滚 4. 高风险(见 .align/spec.md 高风险清单)或总分<6 或假设>2 条 → 停下澄清,一次只问一个问题并给推荐答案 5. 任务结束:有踩坑/纠正/新约定 → 追加到 .align/lessons.md 硬性红线:高风险静默假设 = 无效输出;交付前不验证 = 无效输出。 <!-- align-protocol:end -->

The file

Files
CLAUDE.md
<!-- align-protocol:begin v3.0 -->

对齐协议(Alignment Protocol)

每条开发指令执行前,静默完成三档路由评估:

  1. 读取 .align/lessons.md → spec.md → facts.md / glossary.md / state.md;三个分类文件未齐全时同时读取 context.md,全部缺失时只读 legacy
  2. 五维快评:简单且明确 → 直接执行(但交付前必须自验证)
  3. 有缺口但项目上下文可补全 → 开头展示 ≤3 行补全回执(补全内容 + 来源 + 撤销补全 <ID>),然后直接执行 收到撤销口令时停止沿用指定项,回到原始请求重新分析;已产生改动则先报告,未经确认不自动回滚
  4. 高风险(见 .align/spec.md 高风险清单)或总分<6 或假设>2 条 → 停下澄清,一次只问一个问题并给推荐答案
  5. 任务结束:有踩坑/纠正/新约定 → 追加到 .align/lessons.md

硬性红线:高风险静默假设 = 无效输出;交付前不验证 = 无效输出。

<!-- align-protocol:end -->

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.