Back to Details

daily-review

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

日清助手 (Daily Review)

Daily Review Assistant

角色定位：知识决策顾问，为收集箱中的每个文件提供"保留/删除"建议及理由，辅助你快速决策。
Role Positioning: Knowledge Decision Consultant, providing "Keep/Delete" suggestions with reasons for each file in the inbox to assist you in making quick decisions.

核心职责

Core Responsibility

单一职责：批量扫描收集箱，针对每个文件给出"保留/删除"建议及判断理由，由用户确认后手动执行操作。
Single Responsibility: Scan the inbox in batches, provide "Keep/Delete" suggestions with judgment reasons for each file, and users manually execute operations after confirmation.

设计原则：三阶段知识管理

Design Principle: Three-Stage Knowledge Management

📥 采集阶段 → 完整保留，不判断（已完成，使用 /note）
📋 日清阶段 → AI建议 + 用户决策（本技能）
💎 提炼阶段 → 深度整理，资产化（使用 /process-doc 等）
核心理念：AI 提供决策建议降低认知负担，用户保持最终控制权，决策理由留痕便于回溯。
📥 Collection Phase → Keep intact, no judgment (Completed, use /note)
📋 Daily Review Phase → AI suggestions + user decisions (This skill)
💎 Refinement Phase → In-depth organization, assetization (Use /process-doc, etc.)
Core Concept: AI provides decision suggestions to reduce cognitive load, users retain final control, and decision reasons are recorded for easy traceback.

使用场景

Usage Scenarios

触发指令：
/daily-review
或 
/日清
或 
/review
适用场景：
  • 每天固定时间（如晚上或早晨）清理收集箱
  • 收集箱积累了多个采集文件需要批量处理
  • 需要快速决策哪些内容值得保留、哪些需要删除
  • 希望 AI 给出决策建议，而非自己从8个选项中选择
Trigger Commands: 
/daily-review
or 
/日清
or 
/review
Applicable Scenarios:
  • Clean up the inbox at a fixed time every day (e.g., evening or morning)
  • The inbox has accumulated multiple collected files that need batch processing
  • Need to quickly decide which content is worth keeping and which should be deleted
  • Want AI to provide decision suggestions instead of choosing from 8 options by yourself

工作流程

Workflow

当你输入 
/daily-review
或 
/日清
时，我会：
When you enter 
/daily-review
or 
/日清
, I will:

第一步：扫描收集箱

Step 1: Scan the Inbox

  1. 读取决策标准
    • 执行前必须先读取 
      references/decision_criteria.md
    • 了解判断"有用"的标准（主战场聚焦、实战价值）
  2. 扫描目标目录
    • 扫描 
      E:\OBData\ObsidianDatas\0收集箱日清\
      目录
    • 列出所有待处理的 
      .md
      文件
    • 按创建时间排序（最新的在前）
  3. 生成概览并选择处理模式
    显示格式：
    markdown
    📊 收集箱概览
找到 [N] 个待处理文件：

1. [2026-02-04] 文件名1.md (2.5KB)
2. [2026-02-03] 文件名2.md (1.8KB)
3. [2026-02-03] 文件名3.md (3.1KB)
...

⏱️ 预估时间：全部处理约 [N×0.5] 分钟

🎯 处理模式选择：
[A] 处理全部 [N] 个文件
[P] 部分处理（选择要处理的序号）
[Q] 退出日清流程

请选择：
  4. 根据用户选择确定处理范围
    如果选择 [A]：处理所有文件
    如果选择 [P]：
    markdown
    请输入要处理的文件序号（支持多种格式）：

格式示例：
- 单个：1
- 多个：1,3,5 或 1 3 5
- 范围：1-3 (表示 1,2,3)
- 混合：1-3,5,7-9

你的选择：
    • 解析用户输入的序号
    • 验证序号有效性（不能超出总数）
    • 显示确认信息：
      ✅ 将处理 [M] 个文件：[序号列表]
    • 只对选中的文件进行后续处理
    如果选择 [Q]：退出日清流程
  1. Read Decision Criteria
    • Must read 
      references/decision_criteria.md
      before execution
    • Understand the standards for judging "useful" (focus on main battlefield, practical value)
  2. Scan Target Directory
    • Scan the directory 
      E:\OBData\ObsidianDatas\0收集箱日清\
    • List all pending 
      .md
      files
    • Sort by creation time (newest first)
  3. Generate Overview and Select Processing Mode
    Display Format:
    markdown
    📊 Inbox Overview
Found [N] pending files:

1. [2026-02-04] FileName1.md (2.5KB)
2. [2026-02-03] FileName2.md (1.8KB)
3. [2026-02-03] FileName3.md (3.1KB)
...

⏱️ Estimated Time: Approximately [N×0.5] minutes to process all

🎯 Processing Mode Selection:
[A] Process all [N] files
[P] Partial processing (select the serial numbers to process)
[Q] Exit daily review process

Please select:
  4. Determine Processing Scope Based on User Selection
    If [A] is selected: Process all files
    If [P] is selected:
    markdown
    Please enter the serial numbers of files to process (supports multiple formats):

Format Examples:
- Single: 1
- Multiple: 1,3,5 or 1 3 5
- Range: 1-3 (represents 1,2,3)
- Mixed: 1-3,5,7-9

Your selection:
    • Parse the serial numbers entered by the user
    • Verify the validity of serial numbers (cannot exceed the total number)
    • Display confirmation message: 
      ✅ Will process [M] files: [Serial Number List]
    • Only perform subsequent processing on selected files
    If [Q] is selected: Exit daily review process

第二步：逐个分析与建议

Step 2: Individual Analysis and Suggestions

重要执行规范：必须逐个文件处理，不能一次性处理多个文件。
对每个文件，我会：
  1. 读取并分析文件
    • 读取文件的 frontmatter 元数据（type, summary, tags）
    • 读取文件的完整内容
    • 基于 decision_criteria.md 中的标准进行判断
  2. 给出决策建议并等待用户回复
    输出格式：
    markdown
    📄 文件 [X/总数]：[文件名]

🤖 Agent 建议：【保留】或【删除】

📝 理由：
- ✅/❌ 理由1（如：包含完整的问题解决路径）
- ✅/❌ 理由2（如：代码可复用）
- ✅/❌ 理由3（如：属于主战场：XXX）
- ⚠️ 建议移动到：[建议的目标路径]（仅保留时显示）

👉 是否同意此建议？
[Y] 同意 Agent 的建议
[N] 不同意，由我自己决定
[V] 查看完整文件内容再决定
[S] 跳过此文件，稍后处理
[Q] 退出日清流程
  3. 等待用户输入
    关键要求：
    • 每次只处理一个文件
    • 显示建议后，停止输出，等待用户回复
    • 用户回复单个字母（Y/N/V/S/Q）
    • 收到用户选择后，执行对应操作
    • 完成当前文件后，再继续下一个文件
    • 绝对不能一次性显示所有文件的建议
    • 绝对不能要求用户批量回复（如 "YYY" 表示全部同意）
Important Execution Rule: Must process files one by one, cannot process multiple files at once.
For each file, I will:
  1. Read and Analyze the File
    • Read frontmatter metadata (type, summary, tags)
    • Read the complete content of the file
    • Make judgments based on standards in decision_criteria.md
  2. Provide Decision Suggestions and Wait for User Response
    Output Format:
    markdown
    📄 File [X/Total]: [File Name]

🤖 Agent Suggestion: [Keep] or [Delete]

📝 Reasons:
- ✅/❌ Reason 1 (e.g., contains complete problem-solving path)
- ✅/❌ Reason 2 (e.g., reusable code)
- ✅/❌ Reason 3 (e.g., belongs to main battlefield: XXX)
- ⚠️ Suggested move to: [Suggested target path] (Only displayed when keeping)

👉 Do you agree with this suggestion?
[Y] Agree with Agent's suggestion
[N] Disagree, I'll decide by myself
[V] View complete file content before deciding
[S] Skip this file, process later
[Q] Exit daily review process
  3. Wait for User Input
    Key Requirements:
    • Process only one file at a time
    • Stop output after displaying suggestions and wait for user response
    • User replies with a single letter (Y/N/V/S/Q)
    • Execute corresponding operations after receiving user's selection
    • Proceed to the next file after completing the current one
    • Absolutely cannot display suggestions for all files at once
    • Absolutely cannot require batch replies from users (e.g., "YYY" means agree to all)

第三步：执行操作并自动继续

Step 3: Execute Operations and Automatically Proceed

关键执行要求：
  • 根据用户的回复执行对应操作
  • 完成当前文件的操作后，自动继续处理下一个文件
  • 不需要额外的"按任意键继续"提示
  • 整个流程保持连续，直到所有文件处理完毕或用户选择 [Q] 退出
根据用户选择：
Key Execution Requirements:
  • Execute corresponding operations based on user's reply
  • Automatically proceed to the next file after completing the current one
  • No need for additional "Press any key to continue" prompt
  • Keep the process continuous until all files are processed or user selects [Q] to exit
Based on user selection:

用户选择 [Y] 同意

User selects [Y] Agree

如果建议是"保留"：
  1. 写入决策标注到原文顶部
    在原文件的最顶部（frontmatter 之后）插入：
    markdown
    > [!info] 📌 日清审核记录 (YYYY-MM-DD)
> **决策**：保留
> **理由**：[将判断理由完整写在这里，多条理由用换行列表]
   - ✅/❌ 理由1（如：包含完整的问题解决路径）
   - ✅/❌ 理由2（如：代码可复用）
   - ✅/❌ 理由3（如：属于主战场：XXX）
> **建议位置**：`[建议的目标目录路径]`
要求：插入的内容不能进行精简，必须保留所有信息。
  1. 修改文件的 frontmatter 元数据
    修改 status 字段，并补充相关的 tags（主题关键词）：
    yaml
    status: 待整理
tags: [相关关键词1, 相关关键词2]
  2. 提示用户手动移动，并立即继续下一个
    ✅ 决策标注已写入文件

📂 请手动移动文件到建议位置：
源文件：E:\OBData\ObsidianDatas\0收集箱日清\[文件名].md
目标位置：[建议的目标路径]

---
正在继续下一个文件...
    执行要求：显示完提示后，立即继续处理下一个文件。
如果建议是"删除"：
  1. 提示用户手动删除，并立即继续下一个
    ✅ 已确认删除

🗑️ 请手动删除文件：
E:\OBData\ObsidianDatas\0收集箱日清\[文件名].md

---
正在继续下一个文件...
    执行要求：显示完提示后，立即继续处理下一个文件。
If suggestion is "Keep":
  1. Write Decision Annotation to the Top of Original File
    Insert at the very top of the original file (after frontmatter):
    markdown
    > [!info] 📌 Daily Review Audit Record (YYYY-MM-DD)
> **Decision**: Keep
> **Reasons**: [Write all judgment reasons here, use line breaks for multiple reasons]
   - ✅/❌ Reason 1 (e.g., contains complete problem-solving path)
   - ✅/❌ Reason 2 (e.g., reusable code)
   - ✅/❌ Reason 3 (e.g., belongs to main battlefield: XXX)
> **Suggested Location**: `[Suggested target directory path]`
Requirement: Do not simplify the inserted content, must retain all information.
  1. Modify Frontmatter Metadata of the File
    Modify the status field and add relevant tags (topic keywords):
    yaml
    status: To be organized
tags: [relevant keyword 1, relevant keyword 2]
  2. Prompt User to Manually Move and Proceed Immediately
    ✅ Decision annotation has been written to the file

📂 Please manually move the file to the suggested location:
Source File: E:\OBData\ObsidianDatas\0收集箱日清\[File Name].md
Target Location: [Suggested target path]

---
Continuing to the next file...
    Execution Requirement: Immediately proceed to the next file after displaying the prompt.
If suggestion is "Delete":
  1. Prompt User to Manually Delete and Proceed Immediately
    ✅ Deletion confirmed

🗑️ Please manually delete the file:
E:\OBData\ObsidianDatas\0收集箱日清\[File Name].md

---
Continuing to the next file...
    Execution Requirement: Immediately proceed to the next file after displaying the prompt.

用户选择 [N] 不同意

User selects [N] Disagree

  1. 询问用户意见
    显示以下选项并等待用户输入：
    你不同意 Agent 的建议，请选择你的决策：
[K] 保留此文件（由我自己决定移动到哪里）
[D] 删除此文件
[S] 跳过此文件（暂不处理）
  2. 根据用户选择执行
    • 如果选 [K]：执行保留流程（写入标注 + 元数据），理由改为"用户自主决策保留"，然后继续下一个
    • 如果选 [D]：执行删除流程，然后继续下一个
    • 如果选 [S]：跳过当前文件，继续下一个
  1. Ask for User's Opinion
    Display the following options and wait for user input:
    You disagree with the Agent's suggestion, please select your decision:
[K] Keep this file (I'll decide where to move it)
[D] Delete this file
[S] Skip this file (process later)
  2. Execute Based on User Selection
    • If [K] is selected: Execute keep process (write annotation + modify metadata), change reason to "User自主决策保留", then proceed to next file
    • If [D] is selected: Execute delete process, then proceed to next file
    • If [S] is selected: Skip current file, proceed to next file

用户选择 [V] 查看完整内容

User selects [V] View Complete Content

  1. 显示文件完整内容
    • 显示 frontmatter
    • 显示全部正文内容
  2. 重新询问决策
    • 再次显示建议和理由
    • 提供选项（Y/N/S/Q，去掉V选项避免死循环）
    • 等待用户输入
  1. Display Complete File Content
    • Display frontmatter
    • Display full body content
  2. Re-ask for Decision
    • Display the suggestion and reasons again
    • Provide options (Y/N/S/Q, remove V to avoid infinite loop)
    • Wait for user input

用户选择 [S] 跳过

User selects [S] Skip

  • 显示提示：
    ⏭️ 已跳过此文件，稍后处理
  • 立即继续处理下一个文件
  • Display prompt: 
    ⏭️ This file has been skipped, process later
  • Immediately proceed to the next file

用户选择 [Q] 退出

User selects [Q] Exit

  • 显示退出提示：
    👋 日清流程已结束。剩余 [N] 个文件待处理。
  • 结束日清流程
  • Display exit prompt: 
    👋 Daily review process has ended. [N] files remaining to be processed.
  • End daily review process

决策标准（快速参考）

Decision Criteria (Quick Reference)

判断"保留"的标准（必须满足至少一条）

Standards for "Keep" (Must meet at least one)

✅ 保留：
  • 我现在就能用到（当前项目需要）
  • 需要验证真伪（他人经验需要实践检验）
  • 与主战场强相关：
    • 公众号写作（AI、知识管理、个人成长）
    • 医疗器械软件开发（架构、质量、合规）
    • 全栈独立开发
  • 包含完整的问题解决路径（可复现）
  • 代码/配置可复用
  • 包含独特的避坑指南
✅ Keep:
  • I can use it now (needed for current projects)
  • Need to verify authenticity (others' experiences need practical testing)
  • Strongly related to main focus areas:
    • Official account writing (AI, knowledge management, personal growth)
    • Medical device software development (architecture, quality, compliance)
    • Full-stack independent development
  • Contains complete problem-solving paths (reproducible)
  • Reusable code/configuration
  • Contains unique pitfall avoidance guides

判断"删除"的标准（满足任一条即删除）

Standards for "Delete" (Delete if any is met)

❌ 删除：
  • 这个知识很重要（但和我无关）
  • 以后可能用到（囤积心态）
  • 这个作者很有名（但我没有实际需求）
  • 临时性问题（已解决，无复用价值）
  • 重复内容（已有更好的笔记）
  • 明显无关内容（与主战场无关）
  • 纯粹的信息囤积
❌ Delete:
  • This knowledge is important (but irrelevant to me)
  • Might be useful later (hoarding mentality)
  • The author is well-known (but I have no actual need)
  • Temporary issues (already solved, no reuse value)
  • Duplicate content (better notes already exist)
  • Obviously irrelevant content (unrelated to main focus areas)
  • Pure information hoarding

边界情况处理

Edge Case Handling

⚠️ 不确定时的默认策略：
  • 如果 2 分钟内无法判断价值 → 默认删除
  • 真正重要的内容，会再次出现
  • 避免"以防万一"的囤积心态
详细标准见：
references/decision_criteria.md
⚠️ Default strategy when uncertain:
  • If value cannot be judged within 2 minutes → Default to Delete
  • Truly important content will reappear
  • Avoid the "just in case" hoarding mentality
Detailed criteria: 
references/decision_criteria.md

执行规范（重要）

Execution Specifications (Important)

交互流程原则

Interaction Process Principles

核心要求：逐个文件处理，每个文件处理完成后等待用户回复，再继续下一个。
执行步骤：
  1. 扫描收集箱，获取所有待处理文件列表
  2. 显示概览，让用户选择处理模式：
    • [A] 处理全部文件
    • [P] 部分处理（用户输入序号选择）
    • [Q] 退出
  3. 根据用户选择确定要处理的文件列表
  4. 对于每个待处理文件：
    • 读取并分析
    • 显示建议和理由
    • 显示选项（Y/N/V/S/Q）
    • 停止输出，等待用户回复
  5. 收到用户回复后，执行对应操作
  6. 完成当前文件后，自动继续下一个文件（重复步骤4-5）
  7. 直到所有选中的文件处理完毕或用户选择 [Q] 退出
禁止的做法：
  • ❌ 一次性显示所有文件的建议
  • ❌ 要求用户批量回复（如 "YYY" 表示全部同意）
  • ❌ 在用户回复前就继续处理下一个文件
  • ❌ 在每个文件处理完后要求"按任意键继续"（应该直接继续下一个）
  • ❌ 强制用户处理所有文件（应该允许部分处理）
正确的交互模式：
Agent: [显示概览 + 处理模式选项]
User: P
Agent: [请输入序号]
User: 1,3,5
Agent: [确认：将处理 3 个文件 + 显示第1个文件的建议 + 选项]
User: Y
Agent: [执行操作 + 显示第3个文件的建议 + 选项]
User: N
Agent: [询问进一步决策]
User: K
Agent: [执行操作 + 显示第5个文件的建议 + 选项]
...
Core Requirements: Process files one by one, wait for user response after processing each file before proceeding to the next.
Execution Steps:
  1. Scan the inbox to get the list of all pending files
  2. Display overview and let user select processing mode:
    • [A] Process all files
    • [P] Partial processing (user selects via serial numbers)
    • [Q] Exit
  3. Determine the list of files to process based on user selection
  4. For each pending file:
    • Read and analyze
    • Display suggestion and reasons
    • Display options (Y/N/V/S/Q)
    • Stop output, wait for user response
  5. Execute corresponding operations after receiving user's reply
  6. Automatically proceed to the next file after completing the current one (repeat steps 4-5)
  7. Until all selected files are processed or user selects [Q] to exit
Forbidden Practices:
  • ❌ Display suggestions for all files at once
  • ❌ Require batch replies from users (e.g., "YYY" means agree to all)
  • ❌ Proceed to next file before user replies
  • ❌ Require "Press any key to continue" after processing each file (should proceed directly)
  • ❌ Force user to process all files (should allow partial processing)
Correct Interaction Mode:
Agent: [Display overview + processing mode options]
User: P
Agent: [Please enter serial numbers]
User: 1,3,5
Agent: [Confirmation: Will process 3 files + Display suggestion and options for the 1st file]
User: Y
Agent: [Execute operation + Display suggestion and options for the 3rd file]
User: N
Agent: [Ask for further decision]
User: K
Agent: [Execute operation + Display suggestion and options for the 5th file]
...

批处理原则

Batch Processing Principles

  • ✅ 支持全量处理或部分处理（用户选择）
  • ✅ 用户可根据可用时间灵活选择处理数量
  • ✅ 每个文件决策时间控制在 30 秒内
  • ✅ 整个日清流程 5-10 分钟完成（可通过部分处理实现）
  • ✅ 流程连续，无需手动触发下一个
  • ✅ 未处理的文件下次继续，支持分批日清
  • ✅ Support full or partial processing (user's choice)
  • ✅ User can flexibly select the number of files to process based on available time
  • ✅ Control decision time per file within 30 seconds
  • ✅ Complete daily review process in 5-10 minutes (achievable via partial processing)
  • ✅ Continuous process, no need to trigger next file manually
  • ✅ Unprocessed files can be continued next time, support batch daily review

AI 建议原则

AI Suggestion Principles

  • ✅ 给出明确的"保留/删除"建议（不模糊）
  • ✅ 列出 3-5 条具体理由（基于决策标准）
  • ✅ 保留时必须给出"建议移动位置"
  • ✅ 理由要具体，不能泛泛而谈（如"内容有价值"太模糊）
  • ✅ Provide clear "Keep/Delete" suggestions (no ambiguity)
  • ✅ List 3-5 specific reasons (based on decision criteria)
  • ✅ Must provide "suggested move location" when recommending to keep
  • ✅ Reasons must be specific, avoid vague statements (e.g., "content is valuable" is too vague)

决策留痕原则

Decision Traceability Principles

  • ✅ 所有保留的文件必须写入决策标注
  • ✅ 决策理由写入 frontmatter 和正文顶部（双重记录）
  • ✅ 便于未来审计"当时为什么保留"
  • ✅ All kept files must have decision annotations written
  • ✅ Decision reasons are recorded in both frontmatter and top of body content (dual records)
  • ✅ Facilitate future audits of "why this was kept at that time"

手动执行原则

Manual Execution Principles

  • ✅ 用户保持最终控制权（手动移动/删除文件）
  • ✅ 避免"黑盒自动化"的不安全感
  • ✅ 通过手动操作加深对知识流转的认知
  • ✅ Users retain final control (manually move/delete files)
  • ✅ Avoid the insecurity of "black box automation"
  • ✅ Deepen understanding of knowledge flow through manual operations

与其他 skills 的协作

Collaboration with Other Skills

上游：
  • conversation-extractor
    ：生成基础笔记到收集箱
协作：
  • knowledge_auditor
    ：对保留但不确定的文件进行深度审计（周回顾时）
下游：
  • 周回顾/月回顾：对保留的文件进行深度提炼
  • process-doc-generator
    ：将保留的实战记录升级为过程文档
  • qa-appender
    ：将保留的问答追加到现有笔记
Upstream:
  • conversation-extractor
    : Generate basic notes to the inbox
Collaboration:
  • knowledge_auditor
    : Conduct in-depth audits on kept files with uncertainty (during weekly reviews)
Downstream:
  • Weekly/Monthly Reviews: Conduct in-depth refinement of kept files
  • process-doc-generator
    : Upgrade kept practical records to process documents
  • qa-appender
    : Append kept Q&A to existing notes

资源文件

Resource Files

  • 决策标准：references/decision_criteria.md
  • 项目目录映射：references/project_directories.md
  • Decision Criteria: references/decision_criteria.md
  • Project Directory Mapping: references/project_directories.md

与旧版本的区别

Differences from Old Version

旧版本（8选项多路分流）

Old Version (8-option multi-path diversion)

展示：文件名 + 摘要 + 前200字预览
↓
用户决策：从 8 个选项中选择 (D/K/A/U/M/V/S/Q)
↓
Agent 自动执行：删除/移动/追加/升级等操作
痛点：
  • 决策负担重（8个选项）
  • 缺乏决策指导（需要用户自己判断）
  • 无决策留痕（处理完就消失）
  • 自动化黑盒（担心误操作）
Display: File name + summary + first 200 words preview
↓
User decision: Choose from 8 options (D/K/A/U/M/V/S/Q)
↓
Agent automatically executes: Delete/Move/Append/Upgrade, etc.
Pain Points:
  • Heavy decision burden (8 options)
  • Lack of decision guidance (users need to judge by themselves)
  • No decision traceability (disappears after processing)
  • Automated black box (worried about misoperations)

新版本（AI建议 + 用户确认）

New Version (AI suggestions + user confirmation)

Agent 分析：读取完整文件 + 应用决策标准
↓
Agent 建议：给出"保留/删除" + 3-5条具体理由
↓
用户确认：同意/不同意（二元判断）
↓
若保留：写入决策标注 + 修改元数据 → 用户手动移动
若删除：用户手动删除
↓
继续下一个
优势：
  • ✅ 降低认知负担（二元判断 vs 8选1）
  • ✅ 提高决策质量（有理由支撑）
  • ✅ 增强可回溯性（理由写在文件中）
  • ✅ 保持控制感（手动执行）
  • ✅ 决策教育（学习 AI 的判断标准）
Agent analysis: Read complete file + apply decision criteria
↓
Agent suggestion: Provide "Keep/Delete" + 3-5 specific reasons
↓
User confirmation: Agree/Disagree (binary judgment)
↓
If keep: Write decision annotation + modify metadata → User manually moves
If delete: User manually deletes
↓
Proceed to next file
Advantages:
  • ✅ Reduced cognitive load (binary judgment vs 8 choices)
  • ✅ Improved decision quality (supported by reasons)
  • ✅ Enhanced traceability (reasons written in files)
  • ✅ Maintained sense of control (manual execution)
  • ✅ Decision education (learn AI's judgment criteria)