Token导航 LogoToken导航

Agent Skill · 研究检索

re-verify-structure(重新验证结构)

re-verify-structure 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-verify-structure 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,权限为调用外部服务;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 60,976。

总安装 360周安装 15GitHub Stars 公开资料未说明下载 120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-verify-structure(重新验证结构)
来源仓库:https://github.com/caldiaworks/caldiaworks-marketplace
仓库路径:skills/re-verify-structure
安装命令:
npx skills add https://github.com/caldiaworks/caldiaworks-marketplace --skill re-verify-structure
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-verify-structure

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-verify-structure 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。该技能适用于需要重新验证系统结构或数据组织的场景。

来源仓库内路径:skills/re-verify-structure

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

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

re-verify-structure 怎么安装?

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

re-verify-structure 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-verify-structure 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

re-verify-structure 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-verify-structure 用的人多吗?

公开数据是累计安装 360 次,近一周安装 15 次,下载 120 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-verify-structure 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

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。

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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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。

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-verify-structure

重新验证结构 · 本页

360—调用外部服务未明确未通过

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

Structure Verification — Reverse Engineering Phase 1 Critic

Verify the structure map produced by re-structure-analysis against the actual source code. This skill runs as an independent Critic in a separate agent context. It has no access to the Doer's reasoning — only the artifacts.

Gate rule: Phase 2 (re-visualize-logic) shall not proceed until this verification produces a PASS or WARN verdict.

Three Principles (Critic Perspective)

1. Code is Truth

  • The source code is the sole authority. If the structure map says something the code does not confirm, the structure map is wrong.

2. Traceability to Line

  • Every file:line reference in the structure map must resolve to actual code. Unresolvable references are hallucinations.

3. Behavior over Intent

  • Verify what the structure map claims against what the code shows. Do not interpret or justify discrepancies.

Execution

Step 1: Load Artifacts

Determine the manifest path:

  • If manifest argument is provided, use it directly
  • If analysis argument is provided, derive path as docs/reverse/{analysis}/manifest.json
  • At least one of manifest or analysis must be provided

Read the manifest and structure map:

{manifest-path}
{analysis-dir}/01-structure-map.md

Extract from the manifest:

  • targets.entry_points — original user-specified targets
  • phase1.status — must be "completed" to proceed
  • language — for tool strategy

If phase1.status is not "completed", report error and stop.

Step 2: Reference Verification

Extract all file:line references from the structure map.

For each reference:

  1. File existence: Verify the file exists at the specified path.
  2. Line validity: Read the file and verify the line number is within range.
  3. Content match: Verify the content at the cited line matches the claim in the structure map.

Classify each reference:

CategoryCriteria
✅ VALIDFile exists, line exists, content matches claim
⚠️ INACCURATEFile exists, content found within ±10 lines of cited line
❌ INVALIDFile does not exist, or line number grossly wrong
🚫 HALLUCINATIONComponent described in structure map cannot be found in source code at any location

Step 3: Completeness Verification

Count actual components in the target scope and compare with the structure map.

With Serena:

mcp__serena__search_for_pattern(
    substring_pattern="class |interface |def |function ",
    restrict_search_to_code_files=true
)

Without Serena:

  • Use Grep to count class/function definitions in the target scope
  • Compare with the number listed in the structure map

Calculate coverage: (listed_in_map / actual_in_source) * 100

CoverageVerdict
>= 95%PASS
90% - 94%WARN
< 90%FAIL

List any components found in source but missing from the structure map.

Step 4: Mermaid Diagram Validation

For each Mermaid code block in the structure map:

  1. Check syntax validity (matching brackets, valid node definitions, valid arrow syntax)
  2. Spot-check 3 nodes/relationships against source code
  3. Document any syntax errors or content inaccuracies

Step 5: Internal Consistency Check

Verify that:

  • Components in dependency diagrams are also listed in component tables
  • Entry points in diagrams match the entry point section
  • File paths are consistent throughout the document
  • targets_for_phase2 in the manifest references components that exist in the structure map

Step 6: Generate Verification Report

Write to docs/reverse/{analysis}/verification/v1-structure.md:

# Structure Map Verification Report

**Verification Date**: {YYYY-MM-DD}
**Target Document**: docs/reverse/{analysis}/01-structure-map.md
**Verdict**: {PASS / WARN / FAIL}

## Summary

| Check | Result | Details |
|:------|:-------|:--------|
| Reference Accuracy | {✅/⚠️/❌} | {valid}/{total} references ({%}) |
| Component Coverage | {✅/⚠️/❌} | {listed}/{actual} components ({%}) |
| Mermaid Syntax | {✅/⚠️/❌} | {error_count} errors |
| Internal Consistency | {✅/⚠️/❌} | {inconsistency_count} issues |

## Verdict

{PASS}: Phase 2 may proceed.
{WARN}: Minor issues found. Phase 2 may proceed. Corrections recommended.
{FAIL}: **Critical issues found. Phase 2 must not proceed. Corrections required.**

## Reference Verification Details

### Invalid References
| Claim | File:Line | Issue | Expected |
|:------|:----------|:------|:---------|
| {claim} | {reference} | {issue description} | {correct reference or "not found"} |

### Hallucinations
- {component}: {reason it is considered hallucinated}

## Completeness Details

### Missing Components
| Component | File | Type |
|:----------|:-----|:-----|
| {name} | {file path} | {class/function/interface} |

## Mermaid Validation

### Syntax Errors
- Block {N}: {error description}

### Content Inaccuracies
- Node "{node}": {discrepancy}

## Internal Consistency Issues

- {description of inconsistency}

## Recommendations

1. **[CRITICAL]** {fix description}
2. **[HIGH]** {fix description}
3. **[MEDIUM]** {fix description}

Step 7: Update Manifest

Read the current manifest, then update:

  • Set phase1.verification to "verification/v1-structure.md"
  • If verdict is PASS or WARN: set phase1.status to "verified"
  • If verdict is FAIL: leave phase1.status as "completed" (do not promote)
  • Update updated timestamp

Verdict Criteria

CriterionPASSWARNFAIL
Reference accuracy>= 95%80-94%< 80%
Component coverage>= 95%90-94%< 90%
Mermaid errors01-2>= 3
Hallucinations00>= 1

Any single FAIL criterion results in an overall FAIL verdict.

Prohibited Actions

  • Do NOT modify the structure map document
  • Do NOT modify source code files
  • Do NOT assume missing information — flag it as an issue
  • Do NOT approve documents with FAIL status
  • Do NOT access the Doer's conversation context or reasoning

平台分布

Codex

37.84%
按下载量换算45

Claude

29.68%
按下载量换算36

Cursor

18.38%
按下载量换算22

Gemini CLI

9.67%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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