cognitive-os / rules
Cursor rule8 starsChanged 8 months agoMITView on GitHub
碎片优先规则:当用户说「我想在[文档]里加上X」但尚未运行 update-knowledge Skill 时,提示用户考虑先记录为L2碎片再整合,而不是直接修改L1文档。当用户提到想修改某个认知结构文档时自动激活。
In this repository23 other files it gives its agents.
- .cursor/rules/cognitive-l3-auto-log.mdcCursor rule
- .cursor/rules/cognitive-principle-check.mdcCursor rule
- .cursor/rules/cognitive-structure-write-guard.mdcCursor rule
- cognitive-askSkill
- cognitive-associateSkill
- cognitive-attendSkill
- cognitive-background-synthesizerSkill
- cognitive-calibrateSkill
- cognitive-capture-fragmentSkill
- cognitive-consistency-checkSkill
- cognitive-consolidateSkill
- cognitive-creative-synthesisSkill
- cognitive-daily-briefingSkill
- cognitive-detect-contradictionSkill
- cognitive-extract-principleSkill
- cognitive-input-classifierSkill
- cognitive-integrate-fragmentsSkill
- cognitive-reorganizeSkill
- cognitive-review-brain-mapSkill
- cognitive-self-reflectSkill
- cognitive-update-knowledgeSkill
- cognitive-version-snapshotSkill
- cognitive-work-alignment-checkSkill
The file
Files
--- description: 碎片优先规则:当用户说「我想在[文档]里加上X」但尚未运行 update-knowledge Skill 时,提示用户考虑先记录为L2碎片再整合,而不是直接修改L1文档。当用户提到想修改某个认知结构文档时自动激活。 globs: alwaysApply: false --- # 碎片优先规则(Fragment Before Direct Edit) ## 核心原则 **直接修改L1文档 vs 先记录为L2碎片再整合**,这两种路径有本质区别: | 直接修改 | 先记录碎片再整合 | |---|---| | 快,但跳过了关卡A(可能引入重复) | 稍慢,但经过检查 | | 没有留下「这个想法的来龙去脉」 | 碎片记录了原始想法的背景 | | 难以追溯「为什么加了这段」 | 碎片整合索引可追溯 | | 适合:修改已有内容的表述 | 适合:加入全新的洞见或观点 | --- ## 触发条件 当用户说类似以下表述,且尚未明确说「直接改」时: - 「我想在[文档]里加上X」 - 「[文档]的某章应该包含...」 - 「我觉得[文档]漏了一个点」 - 「[文档]需要补充...」 --- ## AI 应该做的事 **在直接修改之前,先询问一次:** 「这个新观点是加入[文档],还是先作为碎片记录后再整合? **直接修改**:更快,适合修改已有表述、纠正错误 **先记碎片**:更严谨,适合加入全新洞见(会自动检查是否重复、标注关联) [直接修改] [先记录为碎片]」 → 用户选「直接修改」→ 触发 `cognitive-update-knowledge` Skill → 用户选「先记录为碎片」→ 触发 `cognitive-capture-fragment` Skill,之后自动问是否立即整合 --- ## 例外情况(不需要询问,直接执行修改) - 用户明确说「直接改」「不用记碎片了」 - 修改类型是纠正错别字/改格式/更新日期等非内容修改 - 用户正在执行某个 Skill 的中间步骤(已经走在整合流程里)
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.

