Menu
AI深度分析语音记录，揭示行为模式、认知偏见和战略盲点。不只是数据汇总，而是直击本质的战略洞察和否定性指导。提取可沉淀的核心原则和工作偏好，构建个人工作模式知识库。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
仿写/复刻单篇小红书笔记的写作风格：从“单个帖子样本”（标题+正文+标签+可选图片/排版特征）抽取风格指纹，并结合用户给定主题要点与可选知识库链接，生成同风格但不抄袭的新笔记（标题/正文/话题标签/可选配图建议）。当用户说“仿写这篇小红书/按这篇的风格写一篇/复刻口吻排版/基于这条笔记生成同风格内容”，或提供 info.json、detail.txt、链接、截图等作为风格样本时使用。
A generic requirement/problem clarification workflow. Use when a user/client request is ambiguous, underspecified, or hard to execute/verify. The skill reframes the request, defines scope, constraints, inputs, and acceptance criteria, then outputs a concise one-page definition and a minimal question set to close gaps. Suitable for product/feature requests, content requests, ops tasks, research asks, and decision-making prompts.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
统一的推文内容获取技能。支持单条/批量推文提取，输出结构化数据。当用户提供 Twitter/X 链接并希望获取内容时自动触发。
从 Markdown 文件中自动提取并下载 Twitter 图片，生成可直接发布的版本。 当用户说"下载推文图片"、"提取Twitter图片"、"download twitter images"时触发。
通用写作技能：从数据到文章的自动化写作工作流。 支持多种写作模板（专题、教程、分析、总结、文档），可根据数据源或交互式生成文章。 当用户说"写作"、"生成文章"、"写文档"、"universal-writer"时触发。
| name | daily-ai-workflow-analyzer |
| description | AI深度分析语音记录，揭示行为模式、认知偏见和战略盲点。不只是数据汇总，而是直击本质的战略洞察和否定性指导。提取可沉淀的核心原则和工作偏好，构建个人工作模式知识库。 |
从语音记录中提取深度战略洞察，揭示认知偏见和行为盲点
不只是数据汇总，而是：
知识沉淀 > 数据堆积
每次分析后：
python3 /Users/douba/.claude/skills/daily-ai-workflow-analyzer/scripts/analyze_voice_workflow.py --days 1 --all
python3 /Users/douba/.claude/skills/daily-ai-workflow-analyzer/scripts/analyze_voice_workflow.py --days 1 --app Antigravity
步骤1：提取语音记录
步骤2：AI深度分析（核心改进）
步骤3：自动导出到Obsidian
知识体系/个人工作模式/微信聊天记录_YYYY-MM-DD.mdAntigravity开发记录_YYYY-MM-DD.mdAlma使用记录_YYYY-MM-DD.md知识体系/个人工作模式/
├── 微信聊天记录_2026-01-12.md ← 每日分析结果
├── Antigravity开发记录_2026-01-12.md ← 编程App分析
├── Alma使用记录_2026-01-12.md ← 文档工具分析
├── 用户习惯清单.md ← 自动积累
├── 工作模式配置.md ← 自动积累
└── 偏好设置.md ← 自动积累
Launch the interactive dashboard:
/Users/douba/.claude/skills/daily-ai-workflow-analyzer/scripts/start_dashboard.sh
Then visit: http://localhost:8080
Dashboard Features:
Static Framework (One-time creation)
├── analysis_dashboard.html (HTML structure, CSS, JS logic)
│ └── JavaScript: loadData() → fetch from API → renderDashboard()
└── Never regenerated, only data changes
Dynamic Service (Flask API)
├── analysis_server.py (lightweight backend)
│ ├── GET /api/data → Return all apps data
│ ├── POST /api/analyze → Trigger Python analysis
│ ├── GET /api/report/<app> → Return markdown report
│ └── GET /api/status → Real-time analysis status
└── Handles Python script execution and status polling
Data Processing (Python Scripts)
├── extract_voice_records.py (Query Typeless DB)
├── group_by_app.py (Group records by app)
├── generate_analysis_report.py (Generate structured reports)
└── analyze_voice_workflow.py (Master workflow controller)
~/Library/Application Support/Typeless/typeless.db~/Library/Application Support/alma/workspaces/temp-voice-extraction/by_app/*.json~/Library/Application Support/alma/workspaces/temp-voice-extraction/analysis_reports/Located at: templates/analysis_framework.json
Dimensions（根据App类型自动适配）：
extract_voice_records.py: Extract voice records from Typeless SQLite DBgroup_by_app.py: Group records by focused_app_name into separate JSON filesgenerate_analysis_report.py: Generate structured analysis reports (markdown)analyze_voice_workflow.py: Master workflow controller (orchestrates extraction, grouping, reporting)analysis_server.py: Flask API server for dashboardstart_dashboard.sh: One-click startup script for dashboardanalysis_report_template.md: Standardized template for analysis reportsanalysis_framework.json: Configuration for scene/stage/pattern recognitiontypeless_db_schema.md: Complete schema of Typeless.app SQLite databaseobsidian_organization_guidelines.md: Guidelines for structuring Obsidian notes (future integration)When you ask AI to "analyze voice records" or "generate analysis report", it will:
Example commands:
What AI does automatically:
# Check and start Flask server (background)
# Execute full analysis
python3 auto_analyze.py --all
# Read and display report content
You see:
If you want to use the visual dashboard:
start_dashboard.shAnalyze all apps:
python3 /Users/douba/.claude/skills/daily-ai-workflow-analyzer/scripts/auto_analyze.py --all
Analyze specific app:
python3 /Users/douba/.claude/skills/daily-ai-workflow-analyzer/scripts/auto_analyze.py --app Antigravity
Start dashboard only:
/Users/douba/.claude/skills/daily-ai-workflow-analyzer/scripts/start_dashboard.sh
不只是数据汇总，而是深度战略洞察
报告采用"直面本质"的分析框架，旨在：
| 对比维度 | v1.0 (旧版本) | v2.0 (深度洞察版) |
|---|---|---|
| 核心目标 | 数据汇总和行为描述 | 深度洞察和战略指导 |
| 分析深度 | 表面模式识别 | 认知偏见和战略盲点 |
| 行动指导 | 只有正向建议 | 包含否定性指导 |
| 价值产出 | SOP和规则清单 | 原则和偏好固化 |
| 问题导向 | "用户做了什么" | "用户为什么这么做" |
| 反馈机制 | 简单评分 | 多维度评估和反馈闭环 |
生成报告时必须满足：
Each report includes a feedback section:
This feedback is collected to iteratively refine the analysis framework and report structure.
The generated analysis reports can be synced to Obsidian vault:
Currently in MVP phase—focus on report quality and value extraction before automation.