Cognitive review brain map
Skill TashanGKD/cognitive-os/.cursor/skills/cognitive-review-brain-map
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」。From its SKILL.md
npx -y skills add TashanGKD/cognitive-os --skill cognitive-review-brain-mapAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
4.1 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it
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)
Step 2 统计关键指标
从碎片整合索引统计:
→ 待整合碎片总数(🔲状态)
→ 部分整合数(⚠️状态)
→ 待整合碎片的类型分布
从待完成总清单统计:
→ 🔴 高优先级待处理数量
→ TOP 3 最紧急项(标题+涉及文档)
从L1.5原则库统计:
→ 已确认原则数量
→ 候选原则数量(🟡状态)
从L0文档读取:
→ 各L1文档的最后更新时间(找出最久未更新的)
→ 当前Gap状态(已完成/待处理)
Step 3 生成状态快照,清晰展示
「━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🧠 认知状态快照(今日:YYYY-MM-DD)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📝 待整合碎片:N 个(类型:产品理论M个、自我反思K个...)
📋 高优先级待办:M 项
💡 候选原则待确认:K 个
📅 最久未更新L1文档:[文档名](N天前)
⚠️ 当前已知缺口:X 个(见L0)
TOP 待处理项:
1. [TODO-XXX] [高优先] [描述] → 涉及[文档名]
2. [TODO-XXX] [高优先] [描述] → 涉及[文档名]
3. [TODO-XXX] [中优先] [描述] → 涉及[文档名]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━」
Step 4 建议今日优先处理(根据积压情况自动推断)
基于数量和优先级,给出1-3条建议:
例:
「建议今日优先:
[1] 处理 N 个待整合碎片(运行「整合碎片」)
[2] 确认候选原则 P? 是否成立(运行「提炼原则」)
[3] 完善 [文档名](运行「更新知识」)
[开始处理第1项] [开始处理第2项] [开始处理第3项] [我来决定]」
Step 5 追加 cognitive/L3_logs/system_log.md
[LOG-今日日期-NN] cognitive-review-brain-map | 生成认知快照 | 无文档变更
注意事项
- 快照是只读的,本 Skill 不修改任何 L0/L1/L2/L3 文档内容
- 如果 L0 不存在:「L0 大脑总地图不存在,建议先运行认知结构初始化」
- 快照后直接建议行动,不要只展示数据,要帮用户做决策
- 一次复盘后如果用户选择处理某项,直接过渡到对应 Skill,不要让用户重新说触发词
D5:任务完成后的 Loop 反馈
本次执行产出:S-object 认知快照(对话输出,系统日志追加一行) 产出位置:每次快照输出到对话中,无需写入文件(用户直接消费)
Loop 路由:
- 通路B(Loop 3 → Loop 2): → 若快照中发现"某个 L1 文档内容已大幅落后于实际认知状态":记录到 cognitive/L3_logs/todo.md(待处理洞见) → 若发现"某个 Loop 的某条通路长期未激活(如通路E 30天无记录)":记录到 cognitive/L3_logs/todo.md(待处理缺口)
- 系统日志:
→ 每次快照完成后,追加一行到
cognitive/L3_logs/system_log.md→ 格式:[LOG-YYYYMMDD-NN] cognitive-review-brain-map | 生成认知快照 | 无文档变更
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most review quality skills give in ~1.3k tokens
Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07
- Ask questions one at a timein 81 of 1048, across 64 files
- Provide a recommended answer for each questionin 73 of 1048, across 50 files
- Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
- Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
- Interview the user relentlessly about the planin 38 of 1048, across 13 files
- Order findings by severityin 31 of 1048
- Resolve each branch of the decision treein 27 of 1048, across 5 files
- Run a grilling sessionin 26 of 1048, across 5 files
- Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
- Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
- Create documentation files lazilyin 24 of 1048, across 5 files
- Assign severity to every findingin 24 of 1048
Said here and by no other author read
- Read system state files on activation
- Count pending and partial fragments
- Count high priority tasks and top urgent items
- Count confirmed and candidate principles
- Read update times for each L1 document
- Generate formatted status snapshot
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.