@geminilight/mindos 0.5.57 → 0.5.59

package/skills/mindos/SKILL.md

@@ -52,7 +52,7 @@ Run this sequence before substantive edits:
 - If unavailable, read root `INSTRUCTION.md` and root `README.md` directly.
 
 2. Discover current structure dynamically.
-- Use `mindos_list_files` and targeted `mindos_search_notes`.
+- Use `mindos_list_spaces` (top-level zones + README blurbs), `mindos_list_files`, and targeted `mindos_search_notes` as needed.
 - Do not assume fixed top-level directory names.
 
 3. Load local guidance around target paths.
@@ -96,6 +96,7 @@ Before any non-trivial write, confirm all checks:
 
 - `mindos_bootstrap`: Load startup context.
 - `mindos_list_files`: Inspect file tree.
+- `mindos_list_spaces`: Top-level Mind Spaces with README blurbs (lighter than full tree).
 - `mindos_search_notes`: Locate relevant files by keyword/scope/type/date. **When searching, always issue multiple parallel searches with different keywords upfront** — synonyms, abbreviations, English/Chinese variants, and broader/narrower terms. A single keyword is fragile; casting a wider net on the first try avoids wasted rounds.
 - `mindos_get_recent`: Inspect latest activity.
 - `mindos_get_backlinks`: Assess impact before rename/move/delete.
@@ -105,6 +106,8 @@ Before any non-trivial write, confirm all checks:
 - `mindos_read_file`: Read file content.
 - `mindos_write_file`: Use only for true full replacement.
 - `mindos_create_file`: Create `.md`/`.csv` files.
+- `mindos_create_space`: Create a Mind Space (directory + README + INSTRUCTION scaffold). Prefer over `create_file` when adding a new cognitive zone.
+- `mindos_rename_space`: Rename a Space folder (directory). Do not use `rename_file` for folders.
 - `mindos_delete_file`: Delete only with explicit user intent.
 - `mindos_rename_file`, `mindos_move_file`: Structural edits with follow-up reference checks.
 

package/skills/mindos/references/README.md

@@ -0,0 +1,11 @@
+# MindOS skill — reference bundle
+
+Long-form supplements for `../SKILL.md`. Load a file only when the task needs it.
+
+| File | When to read |
+|------|----------------|
+| [sop-template.md](./sop-template.md) | Creating or rewriting a workflow SOP in the KB |
+| [post-task-hooks.md](./post-task-hooks.md) | After a write/multi-step task; proposing follow-ups |
+| [preference-capture.md](./preference-capture.md) | User expresses standing preferences to persist |
+
+Chinese mirror: `skills/mindos-zh/references/` (same filenames).

package/skills/mindos/references/post-task-hooks.md

@@ -0,0 +1,53 @@
+# Post-task hooks
+
+After completing a task, check the conditions below. If one matches, make a **one-line** proposal to the user. If none match, end quietly.
+
+## Discipline
+
+1. Do not propose after simple operations (rename, append one line, read-only queries).
+2. **At most 1 proposal per task** — pick the highest priority match.
+3. One sentence + specific target file/path. Only expand if the user says yes.
+4. Check `user-skill-rules.md` suppression section first — skip any suppressed hook.
+5. If the user asked for **no suggestions / quiet mode** for this turn or session, skip all hooks.
+
+## Default hooks
+
+### Experience capture (priority: high)
+- **Condition**: task involved debugging, troubleshooting, or took multiple rounds to resolve.
+- **Propose**: "Record this experience to {related experience file}?"
+- **Format**: problem → cause → solution → rule
+
+### Consistency sync (priority: high)
+- **Condition**: edited file A, and A is referenced by other files (check via `get_backlinks`).
+- **Propose**: "{B} references what you just changed — sync it?"
+
+### Linked update (priority: medium)
+- **Condition**: changed a CSV/TODO item status, and related docs exist.
+- **Propose**: "Sync the corresponding info in {related doc}?"
+
+### Structure classification (priority: medium)
+- **Condition**: created a new file in a temporary location or inbox.
+- **Propose**: "Move this to {recommended directory}?"
+
+### Pattern extraction (priority: low)
+- **Condition**: 3+ structurally similar operations in the current session.
+- **Propose**: "This operation repeated multiple times — create an SOP?"
+
+### SOP drift (priority: medium)
+- **Condition**: task was executed following an existing SOP, but actual steps diverged from documented steps.
+- **Propose**: "Execution diverged from {SOP file} — update the SOP?"
+- **Action**: update divergent steps, append new pitfalls, set `<!-- last-used: -->` to today.
+
+### Conversation retrospective (priority: low)
+- **Condition**: session >10 turns and involved decisions, trade-offs, or lessons.
+- **Propose**: "This conversation had some decisions worth capturing — do a retrospective?"
+
+## User-defined hooks
+
+Add your own below, same format:
+
+```markdown
+### Weekly report material (priority: medium)
+- Condition: updated a Project-related file.
+- Propose: "Record this change in the weekly report?"
+```

package/skills/mindos/references/preference-capture.md

@@ -0,0 +1,41 @@
+# Preference capture (`user-skill-rules.md`)
+
+## When to capture
+
+The user expresses a preference correction (e.g. "don't do X", "next time remember…", "this should go in… not in…").
+
+## Confirm-then-write flow
+
+1. **First occurrence of a new preference**: propose the rule and target file before writing.
+   - "Record this preference to `user-skill-rules.md`? Rule: _{summary}_"
+   - Write only after user confirms.
+2. **Repeated confirmation on similar category**: after the user confirms the same category of preference 3+ times, auto-write future rules in that category without asking. Add an `auto-confirm: true` flag to the category header in `user-skill-rules.md`.
+3. **User explicitly grants blanket permission** (e.g. "just record preferences directly"): set a top-level `auto-confirm-all: true` flag and skip confirmation for all future captures.
+
+## File location
+
+- Target: `user-skill-rules.md` in the knowledge base root (read by `mindos_bootstrap` when present).
+- If the file does not exist, create it with the template below on first confirmed write.
+
+## File template
+
+```markdown
+# User Skill Rules
+<!-- auto-confirm-all: false -->
+
+## Preferences
+<!-- Group by category. Mark auto-confirm: true on categories confirmed 3+ times. -->
+
+## Suppressed Hooks
+<!-- List post-task hooks the user has opted out of. -->
+```
+
+## Rule format
+
+Each rule is a bullet under its category:
+
+```markdown
+### {Category}
+<!-- auto-confirm: false -->
+- {Rule description} — _{date captured}_
+```

package/skills/mindos/references/sop-template.md

@@ -0,0 +1,74 @@
+# SOP file template (MindOS knowledge base)
+
+Use when **distilling experience into a new SOP** or normalizing an existing workflow doc. Place the file under whichever directory in the KB holds procedures (often names like `Workflows/`, `SOPs/`, `流程/` — infer from bootstrap tree, do not assume a fixed English folder name).
+
+## Required structure
+
+```markdown
+# SOP: {Title}
+<!-- keywords: {3-5 trigger keywords, English and Chinese} -->
+<!-- last-used: {ISO date} -->
+<!-- created: {ISO date} -->
+<!-- requires-mcp: {comma-separated, e.g. mindos — or "none" if KB-only read/write via other means} -->
+<!-- requires-kb-skills: {optional — paths or names of SKILL.md / instructions the agent must follow, or "none"} -->
+
+## Prerequisites
+
+**Before starting**, list what must already be true. If something is missing, **stop or take the degradation branch** (do not assume).
+
+| Kind | What to record |
+|------|----------------|
+| **MCP / tools** | Which servers or tool families are required (e.g. `mindos`, browser, git). If the workflow only uses MindOS file APIs, say `mindos` or as appropriate. |
+| **Agent skills** | KB-resident or host skills the executor must have loaded or be able to read (e.g. `skills/foo/SKILL.md`, or “follow root INSTRUCTION.md §X”). |
+| **Environment** | CLI installed, network, API keys, logged-in state, OS constraints. |
+| **KB state** | Files, directories, or tables that must exist first; optional “seed” notes. |
+
+If there are **no** special dependencies, write explicitly: **None — MindOS MCP (or equivalent) only.**
+
+## Applicable Scenarios
+
+When to use this SOP. Trigger conditions, audience, and **non-goals** (what this SOP deliberately does not cover).
+
+## Inputs and outputs (optional but recommended)
+
+- **Inputs**: what the user or agent must supply (paths, decisions, raw text).
+- **Outputs**: artifacts produced (files created/updated, messages to user).
+
+## Steps
+
+Each step includes:
+1. **Action** — concrete operation
+2. **Branch** — if X do A, if Y do B (mark "none" if no branching)
+3. **Failure handling** — what can go wrong and how to respond
+
+## Exit Conditions
+
+When is the task complete. When to abort or escalate.
+
+## Pitfall Log
+
+Known edge cases and lessons learned. Append new entries each time the SOP is executed and a new issue is encountered.
+```
+
+## Metadata (HTML comments)
+
+| Tag | Purpose |
+|-----|---------|
+| **`keywords`** | SOP recall via `mindos_search_notes` + parallel variants. English and Chinese. |
+| **`last-used`** | Set to today’s date whenever the SOP is followed. |
+| **`created`** | Set once at creation time. |
+| **`requires-mcp`** | Quick machine/human scan: required MCP servers (or `none`). |
+| **`requires-kb-skills`** | Optional: KB skill paths or “none”. |
+
+Optional, when useful:
+
+- **`<!-- related: path/to/other-sop.md -->`** — supersedes, depends-on, or paired workflows.
+- **`<!-- owner: @handle or name -->`** — who curates this SOP.
+- **`<!-- review-by: YYYY-MM -->`** — reminder to revalidate after product/tool changes.
+
+## Authoring tips
+
+- **Prerequisites vs scenarios**: *Prerequisites* = hard requirements before step 1; *Applicable scenarios* = when the workflow is the right choice among others.
+- **Degradation path**: if MCP or a skill is missing, add a **Branch** in step 1 (“if tool unavailable → tell user to enable X / use manual checklist Y”).
+- **Stable keywords**: avoid one-off typos in `keywords`; include synonyms you actually search for.
+- **Link related SOPs** in Prerequisites or a short “See also” line under Applicable scenarios to avoid duplicate drift.

package/skills/mindos-zh/SKILL.md

@@ -50,7 +50,7 @@ description: >
 - 若不可用，直接读取根 `INSTRUCTION.md` 与根 `README.md`。
 
 2. 动态发现当前结构。
-- 使用 `mindos_list_files` 与按需 `mindos_search_notes`。
+- 使用 `mindos_list_spaces`（顶层分区与 README 摘要）、`mindos_list_files` 与按需 `mindos_search_notes`。
 - 不假设固定一级目录名。
 
 3. 加载目标路径附近的局部规则。
@@ -94,6 +94,7 @@ description: >
 
 - `mindos_bootstrap`：加载启动上下文。
 - `mindos_list_files`：查看文件树。
+- `mindos_list_spaces`：列出顶层心智空间及 README 摘要（比整棵树更轻）。
 - `mindos_search_notes`：按关键词/范围/类型/日期定位文件。**搜索时，第一次就应并行发起多个关键词搜索**——同义词、缩写、中英文变体、更宽/更窄的表述。单一关键词很脆弱，一开始就撒网能避免多轮空搜。
 - `mindos_get_recent`：查看近期活动。
 - `mindos_get_backlinks`：重命名/移动/删除前评估影响。
@@ -103,6 +104,8 @@ description: >
 - `mindos_read_file`：读取文件内容。
 - `mindos_write_file`：仅在确需整文件替换时使用。
 - `mindos_create_file`：创建 `.md`/`.csv` 文件。
+- `mindos_create_space`：新建心智空间（目录 + README + INSTRUCTION 脚手架）。新增整块分区时优先于只建 `某空间/README.md`。
+- `mindos_rename_space`：重命名空间目录（文件夹）。不能用 `rename_file` 重命名目录。
 - `mindos_delete_file`：仅在用户明确意图下删除。
 - `mindos_rename_file`、`mindos_move_file`：结构变更后补做引用检查。
 

package/skills/mindos-zh/references/README.md

@@ -0,0 +1,11 @@
+# MindOS skill — 参考文档（中文）
+
+`../SKILL.md` 的补充长文。仅在任务需要时读取对应文件。
+
+| 文件 | 何时阅读 |
+|------|----------|
+| [sop-template.md](./sop-template.md) | 在知识库中新建或重写流程类 SOP |
+| [post-task-hooks.md](./post-task-hooks.md) | 写入/多步任务完成后，考虑是否一句话跟进 |
+| [preference-capture.md](./preference-capture.md) | 用户表达要长期记住的偏好 |
+
+英文版见 `skills/mindos/references/`（结构一致）。

package/skills/mindos-zh/references/post-task-hooks.md

@@ -0,0 +1,53 @@
+# 任务后 Hooks
+
+任务完成后检查以下条件。命中则向用户发起**一句话**提议；都不命中则安静结束。
+
+## 纪律
+
+1. 简单操作（改标题、追加一行、只读查询）完成后不提议。
+2. **每次任务最多 1 条提议**，选优先级最高的命中项。
+3. 一句话 + 具体目标路径/文件。用户同意后再展开。
+4. 先查 `user-skill-rules.md` 的抑制区，命中则跳过对应 hook。
+5. 用户本轮或本会话要求**不要建议 / 安静执行**时，跳过所有 hooks。
+
+## 默认 Hooks
+
+### 经验沉淀（优先级：高）
+- **条件**：调试、排错、踩坑，或多轮才解决。
+- **提议**：「要把这个经验记到 {相关经验文件} 吗？」
+- **格式**：问题 → 原因 → 解决 → 规则
+
+### 一致性同步（优先级：高）
+- **条件**：编辑了文件 A，且 A 被其他文件引用（`get_backlinks`）。
+- **提议**：「{B} 引用了刚改的内容，要同步更新吗？」
+
+### 联动更新（优先级：中）
+- **条件**：改了 CSV/TODO 条目状态，且存在关联文档。
+- **提议**：「{关联文档} 的对应信息要同步吗？」
+
+### 结构归类（优先级：中）
+- **条件**：在临时目录或收件箱新建了文件。
+- **提议**：「要归类到 {推荐目录} 吗？」
+
+### 模式提炼（优先级：低）
+- **条件**：当前会话中 3+ 次结构相似操作。
+- **提议**：「这个操作重复了多次，要整理成 SOP 吗？」
+
+### SOP 偏差（优先级：中）
+- **条件**：按某 SOP 执行，但实际步骤与文档不一致。
+- **提议**：「执行过程与 {SOP 文件} 有偏差，要更新这个 SOP 吗？」
+- **动作**：更新偏差步骤、追加踩坑、将 `<!-- last-used: -->` 设为今天。
+
+### 对话复盘（优先级：低）
+- **条件**：会话 >10 轮且涉及决策、权衡或经验教训。
+- **提议**：「这段对话有些决策值得沉淀，要做个复盘吗？」
+
+## 用户自定义 Hooks
+
+在 skill 或笔记中按同格式追加，例如：
+
+```markdown
+### 周报素材收集（优先级：中）
+- 条件：更新了 Project 相关文件
+- 提议：「要把这个变更记到本周周报素材吗？」
+```

package/skills/mindos-zh/references/preference-capture.md

@@ -0,0 +1,41 @@
+# 偏好捕获（`user-skill-rules.md`）
+
+## 何时捕获
+
+用户在操作中表达偏好修正（如「以后不要…」「下次记得…」「这个应该放在…而不是…」）。
+
+## 确认后写入流程
+
+1. **某类偏好首次出现**：先提议，用户确认后再写入。
+   - 「记录此偏好到 `user-skill-rules.md`？规则：_{摘要}_」
+   - 仅在用户确认后写入。
+2. **同类偏好确认 3 次以上**：该类别在 `user-skill-rules.md` 中标记 `auto-confirm: true`，后续同类偏好自动写入，不再询问。
+3. **用户明确授权**（如「偏好直接记就行」）：设置顶层 `auto-confirm-all: true`，之后所有偏好跳过确认直接写入。
+
+## 文件位置
+
+- 目标：知识库根目录的 `user-skill-rules.md`（存在时由 `mindos_bootstrap` 读取）。
+- 若文件不存在，在首次确认写入时按下方模板创建。
+
+## 文件模板
+
+```markdown
+# User Skill Rules
+<!-- auto-confirm-all: false -->
+
+## Preferences
+<!-- 按类别分组。确认 3 次以上的类别标记 auto-confirm: true。 -->
+
+## Suppressed Hooks
+<!-- 列出用户已关闭的 Post-Task Hooks。 -->
+```
+
+## 规则格式
+
+每条规则以列表项写在对应类别下：
+
+```markdown
+### {类别名}
+<!-- auto-confirm: false -->
+- {规则描述} — _{记录日期}_
+```

package/skills/mindos-zh/references/sop-template.md

@@ -0,0 +1,74 @@
+# SOP 文件模板（MindOS 知识库）
+
+在**把经验提炼成新 SOP** 或规范化现有流程文档时使用。文件放在知识库中**存放流程/规范**的目录下（常见名如 `Workflows/`、`SOPs/`、`流程/` 等——从 bootstrap 目录树推断，**不要写死**某个英文文件夹名）。
+
+## 必须遵循的结构
+
+```markdown
+# SOP: {标题}
+<!-- keywords: {3-5 个触发关键词，中英文} -->
+<!-- last-used: {ISO date} -->
+<!-- created: {ISO date} -->
+<!-- requires-mcp: {逗号分隔，如 mindos；若仅本地读写且无 MCP 则写 none 并说明方式} -->
+<!-- requires-kb-skills: {可选 — 必须遵循的 SKILL.md 路径或名称；无则写 none} -->
+
+## 前置条件
+
+**开始执行前**必须已满足的条件；若不满足应**中止或走降级分支**（不要默认环境齐全）。
+
+| 类型 | 写什么 |
+|------|--------|
+| **MCP / 工具** | 依赖哪些 MCP 或工具族（如 `mindos`、浏览器、git）。若流程只用 MindOS 文件能力，写明 `mindos` 或实际所用。 |
+| **Agent 技能** | 执行方必须已加载或可读取的知识库内/宿主侧 Skill（如 `skills/foo/SKILL.md`，或「遵循根目录 INSTRUCTION.md §X」）。 |
+| **环境 / 账号** | 是否依赖 CLI、网络、API Key、登录态、操作系统等。 |
+| **知识库状态** | 必须先存在的文件、目录、表格或种子笔记。 |
+
+若**无**特殊依赖，请显式写：**无 — 仅需 MindOS MCP（或等价能力）即可。**
+
+## 适用场景
+
+什么情况下该用这个 SOP。触发条件、面向对象，以及**非目标**（本 SOP 明确不覆盖什么）。
+
+## 输入与产出（建议写）
+
+- **输入**：用户或 Agent 必须提供的信息（路径、决策、原始材料等）。
+- **产出**：会生成或更新哪些产物（文件、对外消息等）。
+
+## 步骤
+
+每步包含：
+1. **做什么** — 具体操作
+2. **判断分支** — 遇到 X 走 A，遇到 Y 走 B（无分支则标注"无"）
+3. **失败处理** — 这步可能失败的情况和应对
+
+## 退出条件
+
+什么时候算完成，什么时候该放弃或升级。
+
+## 踩坑记录
+
+已知的边界 case 和教训。每次执行遇到新坑时追加。
+```
+
+## 元数据（HTML 注释）
+
+| 标签 | 用途 |
+|------|------|
+| **`keywords`** | 供 `mindos_search_notes` 等召回，配合多关键词搜索；中英文都要有。 |
+| **`last-used`** | 每次按该 SOP 执行后更新为当天日期。 |
+| **`created`** | 创建时设置一次。 |
+| **`requires-mcp`** | 快速扫一眼：依赖哪些 MCP（或 `none`）。 |
+| **`requires-kb-skills`** | 可选：依赖的知识库内 Skill；无则 `none`。 |
+
+按需可选：
+
+- **`<!-- related: path/to/other-sop.md -->`** — 被替代、依赖、或成对使用的其他 SOP。
+- **`<!-- owner: 维护人 -->`** — 谁负责迭代本 SOP。
+- **`<!-- review-by: YYYY-MM -->`** — 提醒在工具/产品变更后复核是否仍成立。
+
+## 编写提示
+
+- **前置条件 vs 适用场景**：前置条件 = 开跑前硬门槛；适用场景 = 在众多流程里**何时选**这一条。
+- **降级路径**：若某 MCP 或 Skill 不可用，在**第一步**就写分支（「若工具不可用 → 提示用户开启 X / 改用手动清单 Y」）。
+- **keywords 要稳**：避免一次性错拼；把你会用来搜的同义词写进去。
+- **关联 SOP**：在前置条件或适用场景下加「参见 xxx.md」，减少多份文档互相漂移。

package/templates/empty/CONFIG.json

@@ -33,12 +33,14 @@
       "defaultHeadingLevel": 2
     }
   },
-  "protocol": {
-    "readMode": "config_and_doc",
-    "priorityBetweenConfigAndDoc": "none",
+  "naming": {
+    "firstLevelDirEmoji": true,
+    "deeperLevelDirEmoji": false,
     "notes": [
-      "CONFIG.json and CONFIG.md must be read together",
-      "They are complementary and have no priority relationship"
+      "First-level directories (root children) use emoji + name",
+      "Second-level and deeper directories use plain names",
+      "Directory naming language follows languagePreference.folderNamingLanguage",
+      "Content file emoji prefix follows filename.emojiPrefixDefault"
     ]
   },
   "uiSchema": {

package/templates/empty/INSTRUCTION.md

@@ -14,7 +14,7 @@ When entering a knowledge base, load context in this order:
 
 1. Read root `INSTRUCTION.md` (this file)
 2. Read root `README.md` (index and navigation)
-3. Read `CONFIG.json` and `CONFIG.md` together (config values + semantic explanation)
+3. Read `CONFIG.json` (config values + naming semantics)
 4. Route to the target directory
 5. If target directory has `INSTRUCTION.md`, read it first
 6. Then read target `README.md` and target files
@@ -123,7 +123,7 @@ Create it only when local rules are reusable and meaningful. Avoid creating them
 
 - Content files: optional `emoji + name`
 - Directories: follow `languagePreference.folderNamingLanguage`; zh templates default to Chinese naming, en templates default to English naming.
-- System files: `README.md`, `INSTRUCTION.md`, `TODO.md`, `CHANGELOG.md`, `CONFIG.json`, `CONFIG.md`
+- System files: `README.md`, `INSTRUCTION.md`, `TODO.md`, `CHANGELOG.md`, `CONFIG.json`
 
 ### 4.3 Read-Before-Write
 
@@ -172,6 +172,6 @@ Create it only when local rules are reusable and meaningful. Avoid creating them
 
 ## 9. CONFIG Read Protocol
 
-- `CONFIG.json` and `CONFIG.md` must be read together.
-- They are complementary and have no priority relationship.
-- `CONFIG.json` provides structured config values; `CONFIG.md` provides semantic explanation and intent.
+- `CONFIG.json` is the single source of truth for all configuration.
+- Field semantics are embedded in `keySpecs`; directory naming rules in `naming`.
+- No separate `CONFIG.md` is needed.

package/templates/empty/README.md

@@ -9,7 +9,6 @@ my-mind/
 ├── INSTRUCTION.md
 ├── README.md
 ├── CONFIG.json
-├── CONFIG.md
 ├── TODO.md
 ├── CHANGELOG.md
 ├── 👤 Profile/
@@ -22,6 +21,6 @@ my-mind/
 
 ## 💡 Usage
 
-- Bootstrap read order: `INSTRUCTION.md` -> `README.md` -> `CONFIG.json` + `CONFIG.md`
+- Bootstrap read order: `INSTRUCTION.md` -> `README.md` -> `CONFIG.json`
 - Capture first in `📝 Notes/`, then move stable content to domain folders
 - Directories that need regular updates: `👤 Profile/`, `🔗 Connections/`, `🚀 Projects/`

package/templates/en/CONFIG.json

@@ -33,12 +33,14 @@
       "defaultHeadingLevel": 2
     }
   },
-  "protocol": {
-    "readMode": "config_and_doc",
-    "priorityBetweenConfigAndDoc": "none",
+  "naming": {
+    "firstLevelDirEmoji": true,
+    "deeperLevelDirEmoji": false,
     "notes": [
-      "CONFIG.json and CONFIG.md must be read together",
-      "They are complementary and have no priority relationship"
+      "First-level directories (root children) use emoji + name, e.g. 👤 Profile/",
+      "Second-level and deeper directories use plain names, e.g. Family/",
+      "Directory naming language follows languagePreference.folderNamingLanguage",
+      "Content file emoji prefix follows filename.emojiPrefixDefault"
     ]
   },
   "uiSchema": {

package/templates/en/INSTRUCTION.md

@@ -14,7 +14,7 @@ When entering a knowledge base, load context in this order:
 
 1. Read root `INSTRUCTION.md` (this file)
 2. Read root `README.md` (index and navigation)
-3. Read `CONFIG.json` and `CONFIG.md` together (config values + semantic explanation)
+3. Read `CONFIG.json` (config values + naming semantics)
 4. Route to the target directory
 5. If target directory has `INSTRUCTION.md`, read it first
 6. Then read target `README.md` and target files
@@ -123,7 +123,7 @@ Create it only when local rules are reusable and meaningful. Avoid creating them
 
 - Content files: optional `emoji + name`
 - Directories: follow `languagePreference.folderNamingLanguage`; zh templates default to Chinese naming, en templates default to English naming.
-- System files: `README.md`, `INSTRUCTION.md`, `TODO.md`, `CHANGELOG.md`, `CONFIG.json`, `CONFIG.md`
+- System files: `README.md`, `INSTRUCTION.md`, `TODO.md`, `CHANGELOG.md`, `CONFIG.json`
 
 ### 4.3 Read-Before-Write
 
@@ -172,6 +172,6 @@ Create it only when local rules are reusable and meaningful. Avoid creating them
 
 ## 9. CONFIG Read Protocol
 
-- `CONFIG.json` and `CONFIG.md` must be read together.
-- They are complementary and have no priority relationship.
-- `CONFIG.json` provides structured config values; `CONFIG.md` provides semantic explanation and intent.
+- `CONFIG.json` is the single source of truth for all configuration.
+- Field semantics are embedded in `keySpecs`; directory naming rules in `naming`.
+- No separate `CONFIG.md` is needed.

package/templates/en/README.md

@@ -9,7 +9,6 @@ my-mind/
 ├── INSTRUCTION.md
 ├── README.md
 ├── CONFIG.json
-├── CONFIG.md
 ├── TODO.md
 ├── CHANGELOG.md
 ├── 👤 Profile/
@@ -22,6 +21,6 @@ my-mind/
 
 ## 💡 Usage
 
-- Bootstrap read order: `INSTRUCTION.md` -> `README.md` -> `CONFIG.json` + `CONFIG.md`
+- Bootstrap read order: `INSTRUCTION.md` -> `README.md` -> `CONFIG.json`
 - Capture first in `📝 Notes/`, then move stable content to domain folders
 - Directories that need regular updates: `👤 Profile/`, `🔗 Connections/`, `🚀 Projects/`

package/templates/en//360/237/223/232 Resources/README.md"

@@ -8,10 +8,10 @@ External resource collections and structured indexes.
 📚 Resources/
 ├── README.md
 ├── INSTRUCTION.md
-├── 🧾 AI Products.csv
-├── 🧾 AI Influencers.csv
-├── 🧾 AI Tools.csv
-└── 🧾 AI Scholars.csv
+├── 🧾 Books.csv
+├── 🧾 People to Follow.csv
+├── 🧾 Tools.csv
+└── 🧾 Learning Resources.csv
 ```
 
 ## Usage

package/templates/en//360/237/223/232 Resources//360/237/247/276 Books.csv"

@@ -0,0 +1 @@
+Title,Author,Category,Status,Rating,StartedAt,FinishedAt,Notes

package/templates/en//360/237/223/232 Resources//360/237/247/276 Learning Resources.csv"

@@ -0,0 +1 @@
+Name,Type,Topic,Provider,Link,Status,UpdatedAt,Notes

package/templates/en//360/237/223/232 Resources//360/237/247/276 People to Follow.csv"

@@ -0,0 +1 @@
+Name,Field,Platform,Link,WhyFollow,Status,UpdatedAt,Notes

package/templates/en//360/237/223/232 Resources//360/237/247/276 Tools.csv"

@@ -0,0 +1 @@
+Name,Category,PrimaryUse,Website,Pricing,Status,UpdatedAt,Notes

package/templates/en//360/237/223/235 Notes/Ideas//360/237/247/252_example_product_idea.md"

@@ -1,16 +1,13 @@
-# 💡 Product Idea Example: Trust Layer for Personal AI
+# 💡 Idea Example: Weekend Reading Digest
 
 ## Concept
-- Add a "Trust Trace" panel that shows where each generated answer came from in the user's own knowledge base.
+- Every Sunday, review highlights from the week's reading and distill 3 actionable takeaways.
 
-## User Promise
-- "You don't just get answers. You see evidence."
+## Why It Matters
+- Prevents knowledge from evaporating after consumption.
+- Builds a compounding library of personal insights.
 
-## Why It Can Win
-- Converts skepticism into confidence.
-- Creates strong differentiation against black-box assistants.
-
-## Validation Plan
-1. Prototype trace UI in one workflow.
-2. Run 10 user sessions.
-3. Measure confidence score before/after.
+## Next Steps
+1. Pick one book or article from this week.
+2. Write 3 bullet takeaways in Notes/Inbox.
+3. Move the best one into a project or goal.

package/templates/en//360/237/224/204 Workflows/Configurations//360/237/247/252_example_config_update_sop.md"

@@ -4,9 +4,8 @@
 - Ensure agents can run with minimal reconfiguration across sessions.
 
 ## Steps
-1. Update `CONFIG.json` for structured keys.
-2. Update `CONFIG.md` for semantic intent.
-3. Verify naming-level rules (emoji + hierarchy) remain consistent.
+1. Update `CONFIG.json` (structured keys, `keySpecs` for semantics, `naming` for directory rules).
+2. Verify naming-level rules (emoji + hierarchy) remain consistent.
 4. Run `rg` sweep for stale paths and obsolete labels.
 5. Validate one real workflow end-to-end.