Not in the top 1,000 by GitHub stars
TashanGKD/cognitive-os
cognitive-os · 认知操作系统 — 13 Skills + 4 Rules + 4 SubAgents,把人脑分层记忆结构外化为 AI 可操作的知识体系,以50年认知科学研究为基础
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/cognitive-ask/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-associate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-attend/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-background-synthesizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-calibrate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-capture-fragment/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-consistency-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-consolidate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-creative-synthesis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-daily-briefing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-detect-contradiction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-extract-principle/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-input-classifier/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-integrate-fragments/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-reorganize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-review-brain-map/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-self-reflect/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-update-knowledge/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-version-snapshot/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
skills/cognitive-work-alignment-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
50267ccd7a3d → 50267ccd7a3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 50267ccd7a3d
No earlier version was observed for comparison.
Verified commit 50267ccd7a3d7db2bd7bc2578c39cd93a3428d22
git clone --filter=blob:none --no-checkout https://github.com/TashanGKD/cognitive-os.git .hotskills/tashangkd-cognitive-os && git -C .hotskills/tashangkd-cognitive-os checkout --detach 50267ccd7a3d7db2bd7bc2578c39cd93a3428d22
# Copy each selected skill directory from .hotskills/tashangkd-cognitive-os into .cursor/skills/<skill-name>/Heat
0.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- cognitive-ask
skills/cognitive-ask - cognitive-associate
skills/cognitive-associate - cognitive-attend
skills/cognitive-attend - cognitive-background-synthesizer
skills/cognitive-background-synthesizer - cognitive-calibrate
skills/cognitive-calibrate - cognitive-capture-fragment
skills/cognitive-capture-fragment - cognitive-consistency-check
skills/cognitive-consistency-check - cognitive-consolidate
skills/cognitive-consolidate - cognitive-creative-synthesis
skills/cognitive-creative-synthesis - cognitive-daily-briefing
skills/cognitive-daily-briefing - cognitive-detect-contradiction
skills/cognitive-detect-contradiction - cognitive-extract-principle
skills/cognitive-extract-principle - cognitive-input-classifier
skills/cognitive-input-classifier - cognitive-integrate-fragments
skills/cognitive-integrate-fragments - cognitive-reorganize
skills/cognitive-reorganize - cognitive-review-brain-map
skills/cognitive-review-brain-map - cognitive-self-reflect
skills/cognitive-self-reflect - cognitive-update-knowledge
skills/cognitive-update-knowledge - cognitive-version-snapshot
skills/cognitive-version-snapshot - cognitive-work-alignment-check
skills/cognitive-work-alignment-check
How it works
cognitive-ask
When your agent uses it
基于用户自己的认知文档回答问题,严格引用来源,标注置信度,暴露矛盾,识别知识空白。触发词:「基于我的文档」「根据我的想法」「我之前怎么想的」「我说过什么关于X」「我对X的看法是什么」「帮我回忆」「我的认知里怎么说」「我的框架里有没有」「从我的角度」「我如何看待」。
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
5,421 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表(执行前必须理解的概念根)
- 这个 Skill 解决的问题
- 激活后立即执行
- 严格边界(铁律,不可突破)
- 特殊情况处理
- 变更记录
- 注意事项
Files
SKILL.mdcore18,603 bytes
Read SKILL.md
# 认知问答 Skill(Cognitive Ask)
> 严格基于用户自己的认知文档(L0/L1/L1.5/L2)回答问题。
> 铁律:**不引入外部观点,不补充用户没有说过的内容,只用用户自己的文字和思考。**
---
## 知识导航表(执行前必须理解的概念根)
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| **D0 认知根(必读)** | `cognitive/L0_brain_map.md` | 整个K-object体系的入口索引:各L1文档的主题/位置/版本;扫描找相关K-objects |
| **D3 规范参考** | `.cursor/rules/knowledge-integrity-rules.mdc`(R2 NO_FABRICATION + R3 READ_FIRST)| R2:不引入用户文档中没有的观点;R3:先读相关文档再回答,不凭印象 |
| **D4 运行时数据** | `L0_大脑总地图.md` + 根据问题确定的相关L1/L1.5/L2文档 | 先扫描L0找相关文档,再读相关文档后回答 |View the complete source on GitHubcognitive-associate
When your agent uses it
联想激活(启动效应等效)。不被用户直接触发,作为「能力层工具函数」由其他Skill调用。给定一个概念,在知识图谱中激活语义相邻的概念网络,返回Top-5邻居摘要给调用方。被 cognitive-ask Step 2c 和 cognitive-capture-fragment Step 2.5 调用。
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,778 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表
- 接口规格
- 激活后立即执行
- 调用示例
- 边界约束
- D5 说明(工具函数豁免)
- 变更记录
Files
SKILL.mdcore6,218 bytes
Read SKILL.md
# cognitive-associate(联想 / 启动效应等效)
> **对应认知活动**:启动效应(Priming)——给定一个概念,自动激活语义相邻的概念网络,找到你可能没想到的关联
>
> **认知五维坐标(COG-TAX)**:
> - 意识程度:前意识→显性(启动是无意识的,结果呈现是显性的)
> - 脑网络:DMN(自由联想)+ SN(相关性检测)
> - 记忆系统:语义记忆(L1)的扩散激活
> - 执行功能:转换(在不同概念节点之间跳转)
> - 双系统:系统1(模式匹配,快速)
>
> **理论依据**:Collins & Loftus (1975) 扩散激活理论;Meyer & Schvaneveldt (1971) 启动效应实验
>
> **实现定位**:能力层工具函数(不是对话层Skill)View the complete source on GitHubcognitive-attend
When your agent uses it
认知信号检测(突显网络 SN 等效)。检测当前对话内容中隐含的五类认知信号:S1洞见/S2跨域联想/S3矛盾/S4反思/S5原则印证。触发词:「检查这段话有没有认知信号」「帮我识别这里的洞见」「这段话有没有值得记录的」「cognitive-attend」「信号检测」「有什么值得深入的」。也可作为可选的对话预处理步骤(见集成说明)。
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
2,460 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表
- 使用方式
- 激活后立即执行
- 五类信号快速参考
- D5:任务完成后的 Loop 反馈
- 设计注意事项
- 变更记录
Files
SKILL.mdcore9,155 bytes
Read SKILL.md
# cognitive-attend(认知信号检测 / 突显网络 SN 等效)
> **对应认知活动**:突显网络(Salience Network)的信号检测——识别对话内容中「值得深入处理」的认知信号,主动路由给对应的 Skill。
>
> 人类大脑在处理日常输入时,SN 负责过滤:哪些信息应该引起注意?哪些需要从「背景」切换到「前景」处理?这个 Skill 模拟这个过程——让你不会遗漏隐藏在普通对话中的重要认知材料。
>
> **认知五维坐标(COG-TAX)**:
> - 意识程度:前意识→显性(自动检测,结果呈现给用户选择)
> - 脑网络:SN(检测不确定性/新颖性/重要性)
> - 记忆系统:无直接写入(信号放大器,不产生独立记录)
> - 执行功能:抑制(阻止忽略重要信号)
> - 双系统:系统1(快速模式匹配)
>
> **理论依据**:Corbetta & Shulman (2002) 双网络注意模型;Menon & Uddin (2010) SN中枢角色View the complete source on GitHubcognitive-background-synthesizer
When your agent uses it
后台认知合成器(DMN等效,Headless)。不被用户直接触发,由后台调度脚本每3天执行一次。跨碎片关联分析:找到不同时间捕捉的碎片之间的隐性关联,生成合成报告写入L3,等待daily-briefing展示给用户。触发词(人工触发时):「执行后台合成」「cognitive-background-synthesizer」。
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
2,148 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表
- 激活后立即执行(Headless 模式)
- Headless 模式规范
- D5:任务完成后的 Loop 反馈
- 变更记录
Files
SKILL.mdcore7,672 bytes
Read SKILL.md
# cognitive-background-synthesizer(后台认知合成 / DMN等效)
> **对应认知活动**:默认模式网络(DMN)——大脑空闲时自发做的跨话题后台合成、远距联想、洞见生成。人类的很多「灵光一闪」发生在非专注状态,这个Skill模拟这个过程。
>
> **认知五维坐标(COG-TAX)**:
> - 意识程度:隐性(用户不参与,后台自动)
> - 脑网络:DMN(默认模式网络,后台合成主导)
> - 记忆系统:情节记忆(L2/L3)跨时间的模式提取
> - 执行功能:无(自动化关联分析)
> - 双系统:系统1(自动模式匹配)→ 结果供用户用系统2评估
>
> **理论依据**:Buckner et al. (2008) DMN综述;Christoff et al. (2016) 心智游走与创造性思维;Kounios & Beeman (2014) 顿悟神经机制
>
> **调用方式**:后台脚本,每3天执行一次(headless模式)View the complete source on GitHubcognitive-calibrate
When your agent uses it
置信度校准(元认知监控)。追踪L1文档和L2碎片中「AI生成/推断」的内容是否事后得到了验证,定期向用户提问「这段内容当时是AI推断,现在有没有实际证据?」。触发词:「验证历史内容」「校准知识置信度」「哪些内容还没验证」「cognitive-calibrate」。也被 cognitive-consistency-check 内部调用(月度维护)。
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
2,082 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表
- 激活后立即执行
- 归因标注说明
- D5:任务完成后的 Loop 反馈
- 变更记录
Files
SKILL.mdcore7,140 bytes
Read SKILL.md
# cognitive-calibrate(置信度校准 / 元认知置信度监控)
> **对应认知活动**:元认知的置信度校准——追踪🟡AI生成内容是否事后得到验证,防止「自我确认偏误」导致未验证的推断长期被当作事实
>
> **认知五维坐标(COG-TAX)**:
> - 意识程度:显性(需要用户参与确认)
> - 脑网络:CEN(目标导向的检索与判断)+ SN(不确定性检测)
> - 记忆系统:语义记忆的准确性评估
> - 执行功能:监控(Monitoring),是元认知的核心成分
> - 双系统:系统2(需要主动评估,不能自动化)
>
> **理论依据**:Flavell (1979) 元认知监控;Dunning & Kruger (1999) 元认知准确性;Nelson & Narens (1990) 置信度监控框架
>
> **调用时机**:View the complete source on GitHubcognitive-capture-fragment
When your agent uses it
捕捉碎片化思考,结构化写入认知结构L2层。触发词:「碎片」「记录一下」「想法」「新洞见」「我发现」「我觉得」「随手记」「想记一个」。
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
2,639 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表(执行前必须理解的概念根)
- 激活后立即执行(顺序不可跳过)
- 碎片写入格式
- 注意事项
- 变更记录
Files
SKILL.mdcore9,236 bytes
Read SKILL.md
# 碎片捕捉 Skill(Capture Fragment)
> 把用户随时产生的碎片想法,经过关卡A(新洞见判断)后,结构化写入L2碎片层,并更新索引和系统日志。
---
## 知识导航表(执行前必须理解的概念根)
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| **D0 认知根(必读)** | `cognitive/L1_knowledge/formal_spec/self_evolving_agent_spec.md` | 层1:K-object定义(编码陈述性事实的知识对象);层2:D_op.create(对象应存在但不存在);层7:完备题库维度——对象类型 × 操作类型 × 关系类型 |
| **D3 规范参考** | `cognitive/maintenance_protocol.md` | 碎片写入规范:命名格式/存放位置/索引更新要求 |
| **D4 运行时数据** | `cognitive/L2_fragments/fragment_index.md` + `L0_大脑总地图.md` | 当前最大碎片ID(F-XXX)+ 整体认知体系地图(确定碎片归属域)|
View the complete source on GitHubcognitive-consistency-check
When your agent uses it
对认知结构运行完整的C1-C10一致性验证,输出验证报告并修复发现的不一致。触发词:「一致性检查」「自洽检查」「验证认知结构」「检查有没有问题」「跑一遍验证」。批量操作完成后自动触发。
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
5,052 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表(执行前必须理解的概念根)
- 激活后立即执行
- 输出验证报告
- 变更记录
- 修复策略
- D5:任务完成后的 Loop 反馈
- 变更记录
Files
SKILL.mdcore16,539 bytes
Read SKILL.md
# 一致性验证 Skill(Cognitive Consistency Check)
> 基于 `维护协议_自洽规范.md` 的C1-C10条件,对认知结构做完整验证。
> 发现问题后立即修复,不允许「知道有问题但先放着」。
---
## 知识导航表(执行前必须理解的概念根)
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| **D0 认知根(必读)** | `cognitive/L1_knowledge/系统架构思维维度/自进化智能体系统形式规范_v1.0.md` | 层3:C2关系显式化(对象间依赖必须声明);层4:RelType(structural/uses/invokes/verifies/mentions)|
| **D3 规范参考** | `cognitive/maintenance_protocol.md` | C1~C10完整一致性条件(本 Skill 的执行依据)|
| **D4 运行时数据** | 所有L1文档 + `L1.5底层原则库.md` | 被验证的K-objects(需要全量扫描)|View the complete source on GitHubcognitive-consolidate
When your agent uses it
记忆巩固(Headless,睡眠期巩固等效)。不被用户直接触发,由后台调度脚本每7天执行一次。将积压的成熟L2碎片批量整合进L1,conflict类碎片记录到待完成清单由用户决策。触发词(人工触发时):「执行记忆巩固」「批量整合积压碎片」「cognitive-consolidate」。
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
1,993 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表
- 激活后立即执行(Headless 模式,所有决策使用默认策略)
- Headless 模式规范
- D5:任务完成后的 Loop 反馈
- 变更记录
Files
SKILL.mdcore6,767 bytes
Read SKILL.md
# cognitive-consolidate(记忆巩固 / 睡眠期巩固等效)
> **对应认知活动**:睡眠期记忆巩固(海马体→皮层长期存储)——定期将积压的L2碎片批量整合进L1,完成情节记忆→语义记忆的转化
>
> **认知五维坐标(COG-TAX)**:
> - 意识程度:隐性(用户不参与,后台自动)
> - 脑网络:DMN(离线加工,记忆重激活)
> - 记忆系统:情节记忆→语义记忆的转化(海马体→皮层)
> - 执行功能:无(自动化批处理)
> - 双系统:系统1(自动批处理,不需要有意识的决策)
>
> **理论依据**:Stickgold (2005) 睡眠依赖性记忆巩固;Wilson & McNaughton (1994) 海马体重激活;McClelland et al. (1995) 互补学习系统理论
>
> **调用方式**:后台脚本,每7天执行一次(headless模式)View the complete source on GitHubcognitive-creative-synthesis
When your agent uses it
创造性发散(DMN+CEN协同等效)。遇到思路瓶颈时触发,从认知体系中随机抽取「表面不相关」的跨领域概念,强制寻找结构相似性,生成非常规解法候选列表。触发词:「没有思路」「换个角度想」「帮我发散一下」「有什么不同的方向」「反常识的方案」「跨领域看这个问题」「想不到解法」。
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
2,040 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表
- 激活后立即执行
- 设计说明
- D5:任务完成后的 Loop 反馈
- 变更记录
Files
SKILL.mdcore7,359 bytes
Read SKILL.md
# cognitive-creative-synthesis(创造性发散 / DMN+CEN协同等效)
> **对应认知活动**:高创造力状态——DMN(自由联想)与 CEN(目标维持)协同激活,产生远距联想(Remote Associates)
>
> **认知五维坐标(COG-TAX)**:
> - 意识程度:显性(用户主动参与,选择有价值的方向)
> - 脑网络:DMN(发散/联想)+ CEN(目标约束/收敛)协同
> - 记忆系统:语义记忆(L1)跨维度的随机激活
> - 执行功能:转换(在不同概念框架之间切换)
> - 双系统:系统1(快速联想生成)→ 系统2(用户评估筛选)
>
> **理论依据**:Mednick (1962) 远距联想理论;Beaty et al. (2016) 高创造力者 DMN-CEN 协同;Wallas (1926) 顿悟四阶段(酝酿→豁朗)
>
> **⚠<U+FE0F> 特别设计说明**:本 Skill 刻意在发散阶段**豁免 P1「验证优先」约束**——创造性阶段的价值在于暂时松开验证要求,先生成所有可能性,再由用户系统2筛选。收敛时恢复正常验证流程。View the complete source on GitHubcognitive-daily-briefing
When your agent uses it
生成今日认知系统汇报:整合L3记录、待完成项、知识库状态,并主动提问帮助用户恢复上下文。触发词:「汇报」「今天有什么」「有什么更新」「同步一下状态」「有什么积压」「今日简报」「最近新了什么」。
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
1,512 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表(执行前必须理解的概念根)
- 激活后立即执行
- 注意事项
- 变更记录
Files
SKILL.mdcore5,675 bytes
Read SKILL.md
# 每日汇报 Skill(Daily Briefing)
> 秘书向老板汇报:整合所有积压的信息,生成结构化汇报,并主动提问不确信的地方,帮助用户高效恢复上下文并做出今日决策。
---
## 知识导航表(执行前必须理解的概念根)
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| **D0 认知根(必读)** | `cognitive/L0_brain_map.md` | 认知体系全景:各L1文档状态、L2碎片积压情况、当前体系健康度 |
| **D3 规范参考** | — | 本 Skill 为只读查询,无修改操作,无需规范参考 |
| **D4 运行时数据** | `cognitive/L3_logs/system_log.md` + `L2碎片整合索引.md` + `logs/task_log.md` | S-objects历史(已发生了什么)+ G缓冲区状态(积压了什么)|
View the complete source on GitHubcognitive-detect-contradiction
When your agent uses it
检测L1文档之间或文档内部的矛盾,基于L1.5原则提出消解方案。触发词:「矛盾」「不一致」「这里有问题」「检查一致性」「[文档A]和[文档B]是否一致」「有没有冲突」「逻辑漏洞」。
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
2,507 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 激活后立即执行
- 矛盾消解记录格式
- 注意事项
- D5:任务完成后的 Loop 反馈
- 变更记录
Files
SKILL.mdcore8,619 bytes
Read SKILL.md
# 矛盾检测 Skill(Detect Contradiction)
> 识别认知结构中的逻辑矛盾,基于L1.5更高层原则提出消解方案,确保知识体系保持自洽。
>
> **认知根(L1.5 P15 共性优先)**:当检测到多个文档存在相似矛盾时,优先识别共同根因,生成统一消解方案;而非逐个矛盾单独处理。
---
## 激活后立即执行
```
Step 1 确定检测范围
→ 用户指定了具体文档/章节 → 精确检测
→ 用户说"全库"或"全部" → 系统级扫描(较慢,提前告知用户)View the complete source on GitHubcognitive-extract-principle
When your agent uses it
从L2碎片中识别跨领域共同模式,提炼L1.5底层原则候选,经用户确认后写入原则库。触发词:「提炼原则」「有什么规律」「这些碎片有没有共性」「是不是反映了某个习惯」「总结一下模式」「有什么底层逻辑」。
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
4,728 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表(执行前必须理解的概念根)
- 激活后立即执行
- 注意事项
- 变更记录
Files
SKILL.mdcore16,880 bytes
Read SKILL.md
# L1.5原则提炼 Skill(Extract Principle)
> 实现「DMN模拟」:从多个L2碎片中发现跨领域共同模式,提炼为L1.5候选原则,经用户确认后正式沉淀。
---
## 知识导航表(执行前必须理解的概念根)
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| **D0 认知根(必读)** | `cognitive/L1.5_principles/principles.md` | K0原则的定义、现有原则列表(P1~Pn)、原则的稳定性要求(几乎不变)|
| **D3 规范参考** | `cognitive/maintenance_protocol.md` | 原则确认流程:候选→用户确认→正式写入的三步要求 |
| **D4 运行时数据** | `cognitive/L2_fragments/碎片整合索引.md` | 所有🔲待整合碎片(提炼原则的原材料)|
View the complete source on GitHubcognitive-input-classifier
When your agent uses it
任意输入的路由分类器。在输入意图不明确时,判断应走「认知更新路径A(cognitive-capture-fragment)」还是「任务执行路径B(对应任务Skill)」,输出明确路由结论 + 判断理由,不自动触发下游。触发词:「帮我判断这是认知更新还是任务执行」「这个输入是什么类型」「先分类再执行」「路由分类一下」。不应触发:关于计算机网络路由算法的技术问题。
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
1,878 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- 激活后立即执行
- 边界条件
- 与其他 Skill 的关系
- 变更记录
Files
SKILL.mdcore7,225 bytes
Read SKILL.md
# 认知输入分类器(cognitive-input-classifier)
> 强绑定 Rule:R2 NO_FABRICATION(判断理由必须基于输入文本中实际存在的信号词)
> R13 RULE_BEATS_STYLE(准确判断优先于表述流畅)
---
## 核心原则
**判断理由必须基于文本证据**:从用户输入中找到具体信号词,引用它来支撑结论。不允许「感觉上像认知更新」这类无证据判断。
**混合时强制拆分**:同时发现两类信号词时,必须走「AB混合」分支,不允许取占比大的一类压过另一类。
**无法判断时只有两个出口**:追问一次,或默认路径B并告知可纠正。不允许输出「这是一个既有认知又有任务性质的输入」类模糊结论。View the complete source on GitHubcognitive-integrate-fragments
When your agent uses it
将待整合的L2碎片通过小人机制整合进L1系统性文档,保持知识体系自洽。触发词:「整合碎片」「哪些碎片没整合」「更新文档」「把碎片整合进去」「处理积压」「消化碎片」。
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
3,716 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表(执行前必须理解的概念根)
- 激活后立即执行
- 变更记录追加格式
- 注意事项
- 变更记录
Files
SKILL.mdcore13,170 bytes
Read SKILL.md
# 碎片整合 Skill(Integrate Fragments)
> 实现「小人整合机制」:读取待整合碎片 → 判断同化/顺应 → 生成具体更新建议 → 用户确认 → 执行写入 → 级联更新。
---
## 知识导航表(执行前必须理解的概念根)
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| **D0 认知根(必读)** | `cognitive/L1_knowledge/formal_spec/self_evolving_agent_spec.md` | 层5:ceremony(K) = 备份+修改+版本+级联;层3:C2关系显式化(修改K1后必须通知依赖它的B-objects)|
| **D3 规范参考** | `cognitive/maintenance_protocol.md` | K1文档修改规范:版本管理/历史备份/矛盾检测要求 |
| **D4 运行时数据** | `cognitive/L2_fragments/fragment_index.md` + 目标L1文档 | 待整合碎片清单 + 目标文档当前内容(整合前必须理解已有结构)|
View the complete source on GitHubcognitive-reorganize
When your agent uses it
从整个工作区出发,系统性地重组认知结构并整理全局文档归属。适用于首次建立认知结构、或积累了大量散落文档需要批量归档时。基于三大闭环框架(Loop1 Skill体系 / Loop2 思维体系 / Loop3 场景投射)做全工作区分类路由。触发词:「系统整理」「重组认知结构」「从文档构建认知结构」「整合文档」「全量梳理」「认知结构乱了」「全工作区整理」「文档归属梳理」「如何加入认知结构」「怎么加入认知结构」「按规范加入」「未更新的文档怎么处理」「这些文档要怎么整理」「有没有关于X的已有文档」。注意:若用户仅询问流程而非执行重组,执行 Step 0.5(检查分类清单现状)后,先向用户展示已有文档状态和分类建议,再确认是否执行完整重组。
What it loads into context
Frontmatter
233 tokensAlways available to the agent
SKILL.md
7,185 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 与其他 Skill 的区别
- 激活后立即执行
- 工作草稿文件格式
- 关键教训(来自2026-03-19实际执行,已编码为规范)
- 与维护协议的关系
- D5:任务完成后的 Loop 反馈
- 变更记录
Files
SKILL.mdcore24,930 bytes
Read SKILL.md
# 认知结构重组 Skill(Cognitive Reorganize)
> 这个 Skill 编码了「如何从一组散落文档出发,构建完整自洽的认知结构」的完整方法论。
> 基于 2026-03-19 实际执行过程提炼,见过程记录:`认知结构/L3_原始记录/对话记录/认知结构整理过程记录_20260319.md`
---
## 与其他 Skill 的区别
| Skill | 适用场景 |
|---|---|
| `cognitive-capture-fragment` | 捕捉单个新碎片 |
| `cognitive-integrate-fragments` | 处理积压的待整合碎片 |
| **`cognitive-reorganize`** | **从零/从大量散落文档构建/重构整个认知结构** |View the complete source on GitHubcognitive-review-brain-map
When your agent uses it
生成认知结构当前状态快照,帮助用户了解知识体系全貌并决定今日优先处理项。触发词:「大脑地图」「认知状态」「今天做什么」「复盘」「系统状态」「看一下状态」「有什么积压」。
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,123 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 激活后立即执行
- 注意事项
- D5:任务完成后的 Loop 反馈
Files
SKILL.mdcore4,177 bytes
Read SKILL.md
# 大脑地图复盘 Skill(Review Brain Map)
> 读取认知结构各层状态,生成「今日认知快照」,帮助用户快速恢复上下文,决定下一步行动。
---
## 激活后立即执行
```
Step 1 读取全系统状态
Read: cognitive/L0_brain_map.md
Read: cognitive/L2_fragments/碎片整合索引.md
Read: cognitive/L3_logs/待完成总清单.md
Read: cognitive/L1.5_principles/principles.md(只读候选原则部分)View the complete source on GitHubcognitive-self-reflect
When your agent uses it
引导用户进行自我认知反思,结构化写入自我反思记录,并与历史模式做跨时间比对。触发词:「反思」「我发现我有个习惯」「我注意到」「我又犯了」「这个模式」「我有个问题」「感觉自己」。
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
3,531 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 激活后立即执行
- 反思条目写入格式
- 核心原则
- D5:任务完成后的 Loop 反馈
- 变更记录
Files
SKILL.mdcore12,446 bytes
Read SKILL.md
# 自我反思 Skill(Self Reflect)
> 引导者模式:帮用户把模糊的自我观察变成清晰的认知模式记录,并与历史反思做跨时间比对,识别重复出现的模式。
---
## 激活后立即执行
```
Step 1 读取历史反思记录
Read: cognitive/L2_fragments/自我反思记录/自我反思记录.md
→ 记住已有的反思条目数量和关键模式(用于Step 3的历史比对)
→ 内部初始化:追问计数 = 0,五维度覆盖状态全部置为 ❌
View the complete source on GitHubcognitive-update-knowledge
When your agent uses it
受控更新L1系统性文档:含影响范围预分析、历史版本备份、矛盾检测、级联写入。触发词:「更新[文档名]」「完善[文档名]」「修改[文档名]」「我要改[内容]」「在[文档]里加上」「[文档]需要更新」。
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
4,127 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表(执行前必须理解的概念根)
- 激活后立即执行
- 变更记录格式
- 注意事项
- 变更记录
Files
SKILL.mdcore14,836 bytes
Read SKILL.md
# 知识库更新 Skill(Update Knowledge)
> 受控的L1文档直接修改流程:影响分析 → 备份 → 修改 → 矛盾检测 → 强制级联写入。
---
## 知识导航表(执行前必须理解的概念根)
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| **D0 认知根(必读)** | `cognitive/L1_knowledge/系统架构思维维度/自进化智能体系统形式规范_v1.0.md` | 层5:ceremony(K)完整协议 = 备份+版本+修改+日志+级联;层3:C2(K1变化必须通知依赖它的所有B-objects)|
| **D3 规范参考** | `cognitive/maintenance_protocol.md` | K1文档完整修改规范;矛盾检测要求(不可跳过)|
| **D4 运行时数据** | `cognitive/L1.5_principles/principles.md` + `L0_大脑总地图.md` + 目标L1文档 | 现有原则(避免修改与原则矛盾)+ 文档关系图 + 目标文档当前版本 |
View the complete source on GitHubcognitive-version-snapshot
When your agent uses it
为L1文档创建新的x.0版本快照,标志一次重大变更的里程碑。触发词:「创建新版本」「打一个快照」「这是v2.0了」「这次改动很大」「记录一下这个版本」。
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
1,042 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何时使用本 Skill(vs 普通修改)
- 激活后执行
- 版本历史格式示例
- 注意事项
Files
SKILL.mdcore3,374 bytes
Read SKILL.md
# 版本快照 Skill(Cognitive Version Snapshot)
> 当L1文档发生重大变更时,创建新的 x.0 版本快照,作为后续变更的新基准。
> 基于 `维护协议_自洽规范.md` 第0.2条:版本快照+变更日志体系。
---
## 何时使用本 Skill(vs 普通修改)
| 修改类型 | 处理方式 |
|---|---|
| 补充一个段落/修改措辞 | 直接修改 + 在变更记录追加一条 |
| 增加一个新章节 | 直接修改 + 在变更记录追加一条 |
| **核心论点发生变化** | **触发本 Skill,创建 v2.0 快照** |View the complete source on GitHubcognitive-work-alignment-check
When your agent uses it
认知-工作对齐检查。验证你的实际工作产出是否可追溯到你的认知体系(L1.5原则 or L1文档),识别「漂浮工作」——有执行但无认知根的任务,输出对齐报告。触发词:「检查工作与认知的对齐」「认知根对齐」「这个工作有没有认知根」「认知体系和工作是否自洽」「认知对齐检查」「第四维健康检查」。
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
1,616 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 知识导航表(执行前阅读)
- 激活后立即执行
- D5:任务完成后的 Loop 反馈
- 设计背景
- 变更记录
Files
SKILL.mdcore5,935 bytes
Read SKILL.md
# 认知-工作对齐检查(cognitive-work-alignment-check)
> **设计意图**:你的认知体系(L1.5原则 + L1文档)应该是所有判断和行动的根基。
> 如果某项工作无法追溯到任何 L1.5 原则或 L1 文档,它就是「漂浮工作」——
> 做完了,但没有认知依据,也无法通过工作反哺认知体系。
>
> **认知科学依据**:元认知监控(Flavell, 1979)——
> 意识到「我为什么这么判断」比「我判断了什么」更重要。
---
## 知识导航表(执行前阅读)
| 层级 | 文档 | 用途 |View the complete source on GitHubSkills included
- cognitive-ask
- cognitive-associate
- cognitive-attend
- cognitive-background-synthesizer
- cognitive-calibrate
- cognitive-capture-fragment
- cognitive-consistency-check
- cognitive-consolidate
- cognitive-creative-synthesis
- cognitive-daily-briefing
- cognitive-detect-contradiction
- cognitive-extract-principle
- cognitive-input-classifier
- cognitive-integrate-fragments
- cognitive-reorganize
- cognitive-review-brain-map
- cognitive-self-reflect
- cognitive-update-knowledge
- cognitive-version-snapshot
- cognitive-work-alignment-check
Repository facts
- License
- MIT
- Created
- Mar 25, 2026
- Last pushed
- Mar 26, 2026
- Forks
- 1
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 4, 2026
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/cognitive-ask/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/cognitive-ask/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Native | Path .cursor/agents/cognitive-cascade-notifier.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/cognitive-ask/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/cognitive-ask/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/cognitive-ask/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.