deep-review

Name: deep-review
Availability: InStock
Author: zephyrwang6

Analyze weekly or monthly work JSON to produce roadmap, trends, and research insights.

14|4|Updated Mar 31, 2026

Search Tags:#research #productivity #roadmap #trend-analysis #work-analysis #longitudinal-data

Ready to run

npx skills add https://github.com/zephyrwang6/allSkills --skill deep-review-zephyrwang6

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deep-review
Source: https://github.com/zephyrwang6/allSkills/tree/main/deep-review
Command: npx skills add https://github.com/zephyrwang6/allSkills --skill deep-review-zephyrwang6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

这个 Skill 用于分析较长时间跨度的结构化工作数据，帮助你从周报或月报中看清项目进展、工作节奏和技术关注点，避免只看到零散记录却看不到整体趋势。

Core Features & Use Cases

项目 Roadmap 分析：评估每个活跃项目的完成情况、方向偏差、潜在风险和下一步行动建议。
工作趋势分析：对比不同周期的时间分配、工作模式、效率指标、Token 消耗和高低效时段分布。
技术调研总结：提炼周期内反复出现的技术主题，梳理知识关联，并给出学习与实践建议。
Use Case：适合把一周或一个月的工作记录整理成可执行的管理视图，用于复盘项目、优化投入结构、发现技术盲点。

Quick Start

Use the deep-review skill to analyze the attached weekly work JSON and return roadmap, trends, and research insights.

Frequently Asked Questions about deep-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I analyze long-term work logs to identify project progress and work trends?▼

Long-term work logs are analyzed by processing structured weekly or monthly review datasets to identify project progress, shifting time allocation, and recurring technical themes. This approach extracts quantitative evidence and conversation citations to reveal overall work trends.

What is the best way to turn structured weekly work data into actionable roadmap insights?▼

The best way to generate roadmap insights from weekly work data is to evaluate each active project's completion status, direction deviations, and potential risks. This process yields actionable recommendations for the next steps in your project roadmap.

Can I extract recurring technical discussion themes from monthly review datasets?▼

Yes, you can extract recurring technical discussion themes from monthly review datasets by distilling repeated technical topics and mapping knowledge associations. This analysis provides targeted learning and practice recommendations for technical research.

Does work trend analysis require specific structured JSON formats for multiple active projects?▼

Work trend analysis requires structured work data, such as weekly work JSON, containing multiple active projects and shifting time allocations. Processing this structured input allows for accurate comparison of efficiency metrics and Token consumption across periods.

How do I compare time allocation and efficiency metrics across different review periods?▼

Comparing time allocation and efficiency metrics across review periods involves analyzing longitudinal work data to contrast work patterns, Token consumption, and high or low efficiency time distributions. This comparison highlights shifting work trends and structural optimizations.

When should I not use longitudinal data analysis for work reviews?▼

Longitudinal data analysis for work reviews is not suitable for unstructured or single-day records lacking multiple active projects. It requires module-based output selection and quantitative evidence, making it less effective for isolated, brief tasks without recurring themes.