Token导航 LogoToken导航

Agent Skill · 研究检索

re-generate-report(重新生成报告)

re-generate-report 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

re-generate-report 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,674 个 Skill 里排第 59,221。

总安装 392周安装 16GitHub Stars 公开资料未说明下载 127核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:re-generate-report(重新生成报告)
来源仓库:https://github.com/caldiaworks/caldiaworks-marketplace
仓库路径:skills/re-generate-report
安装命令:
npx skills add https://github.com/caldiaworks/caldiaworks-marketplace --skill re-generate-report
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/caldiaworks/caldiaworks-marketplace --skill re-generate-report

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

re-generate-report 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。通过 npx skills add 命令从指定仓库安装,需结合原始 README 确认具体用法。

安装前建议确认权限范围、维护状态及是否触发联网、命令执行或文件读写操作。该技能适用于需要快速生成结构化报告或信息摘要的场景。

来源仓库内路径:skills/re-generate-report

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/caldiaworks/caldiaworks-marketplace --skill re…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

re-generate-report 怎么安装?

在终端执行 npx skills add https://github.com/caldiaworks/caldiaworks-marketplace --skill re-generate-…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

re-generate-report 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

re-generate-report 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

re-generate-report 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

re-generate-report 用的人多吗?

公开数据是累计安装 392 次,近一周安装 16 次,下载 127 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

re-generate-report 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
re-generate-report

重新生成报告 · 本页

392—只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Integrated Report — Reverse Engineering Phase 4

Aggregate ALL reverse engineering artifacts from Phase 1-3 into a consolidated As-Is specification document. This skill reads the manifest to discover all artifacts and produces a single comprehensive report.

Three Principles

1. Code is Truth

  • As-Is spec documents ACTUAL code behavior
  • Suspected bugs remain in Question List, not removed from spec
  • No editorial improvements or "should" statements

2. Traceability to Line

  • Traceability matrix links every requirement to source line
  • All findings traceable to Phase 1-3 artifacts
  • Orphaned findings (no source) flagged for review

3. Behavior over Intent

  • Executive summary focuses on "what" system does, not "why"
  • Architectural patterns described from observed structure
  • No assumptions about business intent

Execution

Step 1: Load Manifest and Collect Artifacts

Read docs/reverse/{analysis}/manifest.json.

Verify:

  • phase3.status is "verified" — if not, report error and stop

Collect all artifacts:

  • Phase 1: phase1.output → structure map
  • Phase 2: phase2.completed[].output → logic diagrams
  • Phase 3: phase3.completed[].output → requirements documents

Read each artifact and extract key sections.

Set phase4.status to "in_progress".

Step 2: Cross-Reference Verification

Requirements → Logic Diagrams: For each requirement, find corresponding nodes in Phase 2 logic diagrams. Confirm line numbers match.

Logic Diagrams → Structure Map: For each logic diagram, confirm the source file is listed in the Phase 1 structure map.

Log inconsistencies:

FindingArtifact AArtifact BIssue

Step 3: Build Traceability Matrix

Combine requirements from all Phase 3 documents:

ModuleREQ-IDEARS TypeRequirementSource File:LineEvidence Strength

Evidence strength:

  • ✅ Strong: Implementation + verified by Critic
  • ⚠️ Medium: Implementation + partial verification
  • ❌ Weak: Implementation only

Step 4: Consolidate Question Lists

Merge from all phases and prioritize:

  • 🔴 Critical: Suspected bugs with high impact (data loss, crashes)
  • 🟡 Important: Architecture/design clarity questions
  • 🟢 Informational: Optimization opportunities, style concerns

Step 5: Generate Executive Summary

Summarize from collected artifacts:

  • System type and technology stack
  • Primary functions (from structure map)
  • Analysis scope and coverage
  • Key findings and technical debt count

Step 6: Generate Report

Write to docs/reverse/{analysis}/04-report.md:

# As-Is Specification: {analysis}

**Document Version**: 1.0
**Analysis Date**: {YYYY-MM-DD}
**Target System**: {system description}
**Language**: {language}
**Framework**: {framework and version}
**Analysis Scope**: {scope description}

---

## Executive Summary

### System Overview

**System Type**: {description}

**Primary Functions**:
- {function 1}
- {function 2}

**Technology Stack**:
- **Language**: {language and version}
- **Framework**: {framework}
- **Database**: {if applicable}
- **Messaging**: {if applicable}

### Analysis Scope

**Files Analyzed**: {count}
**Components Analyzed**: {count}
**Requirements Extracted**: {count} EARS requirements
**Coverage**: {percentage} of target scope

### Key Findings

- **Technical Debt**: {count} suspected issues
  - 🔴 Critical: {count}
  - 🟡 Important: {count}
  - 🟢 Informational: {count}

---

## Technology Stack

{detailed technology stack from structure map}

---

## Module Catalog

{component listing from structure map, organized by category}

---

## Requirements Catalog (EARS)

### By Module

{requirements grouped by component}

### By EARS Type

| EARS Type | Count | Percentage |
|:----------|:------|:-----------|
| Ubiquitous | {n} | {%} |
| Event-driven | {n} | {%} |
| Unwanted | {n} | {%} |
| State-driven | {n} | {%} |
| Optional | {n} | {%} |
| **Total** | **{N}** | **100%** |

---

## Appendix A: Logic Diagrams

{embedded or linked logic diagrams from Phase 2}

---

## Appendix B: Traceability Matrix

{full traceability matrix from Step 3}

---

## Appendix C: Question List (Prioritized)

### 🔴 Critical

{critical questions with source references and recommendations}

### 🟡 Important

{important questions}

### 🟢 Informational

{informational items}

---

## Appendix D: Analysis Constraints

### Confidence Factors
{from structure map}

### Evidence Strength Distribution
| Strength | Count | Percentage |
|:---------|:------|:-----------|
| ✅ Strong | {n} | {%} |
| ⚠️ Medium | {n} | {%} |
| ❌ Weak | {n} | {%} |

---

**Document Control**

| Version | Date | Description |
|:--------|:-----|:------------|
| 1.0 | {YYYY-MM-DD} | Initial As-Is specification |

Step 7: Update Manifest

  • Set phase4.status to "completed"
  • Set phase4.output to "04-report.md"
  • Update updated timestamp

Validation Before Completion

After writing the report, re-read it and verify every number against the source data. Counting errors in the executive summary undermine confidence in the entire report.

  • All Phase 1-3 artifacts collected and referenced
  • Cross-reference verification completed
  • Traceability matrix links all requirements to source
  • Question list prioritized (Critical / Important / Informational)
  • Count verification: Total requirements in executive summary matches actual count in requirements catalog. EARS type distribution sums to the total. Question list count matches actual items in Appendix C. Re-count by enumerating each item — do not rely on numbers from Phase 3 documents or your own earlier statements
  • Executive summary reflects actual findings (no speculation)
  • No requirements added that aren't in Phase 3 documents
  • manifest.json updated

Prohibited Actions

  • Do NOT add requirements not present in Phase 3 artifacts
  • Do NOT editorialize or propose improvements in As-Is spec
  • Do NOT remove suspected bugs — they belong in the Question List
  • Do NOT speculate on business intent
  • Do NOT modify Phase 1-3 artifacts

平台分布

Codex

36.94%
按下载量换算47

Claude

26.09%
按下载量换算33

Cursor

19.14%
按下载量换算24

Gemini CLI

8.51%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills