Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计提醒

ln-610-docs-auditorln 610 文档审核员

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

5,376

周安装

224

GitHub Stars

441

下载量

1,792
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:ln-610-docs-auditor(ln 610 文档审核员)
来源仓库:https://github.com/levnikolaevich/claude-code-skills
仓库路径:skills/ln-610-docs-auditor
安装命令:
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-610-docs-auditor
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/levnikolaevich/claude-code-skills --skill ln-610-docs-auditor

简介

用于文档、README 和内容稿件的整理与改写,适合提炼结构和统一术语。

  • 适用于需要补齐章节、检查链接或把零散材料整理成可读文档的场景。
  • 使用时保留项目已有事实、命令和路径,不把未确认信息写成确定结论。
  • 涉及对外文案时需控制语气,避免过度营销或夸大能力。
  • 安装前建议确认权限范围和维护状态,确保不会触发不必要的网络或文件操作。

SKILL.md

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root.

Type: L2 Coordinator Category: 6XX Audit

Docs Auditor

Mandatory Read

MANDATORY READ: Load shared/references/evaluation_coordinator_runtime_contract.md, shared/references/evaluation_summary_contract.md, shared/references/evaluation_research_contract.md MANDATORY READ: Load shared/references/research_tool_fallback.md

Purpose

  • audit documentation structure, relevance, comments, and factual accuracy
  • coordinate ln-611, ln-612, ln-613, ln-614
  • require research-backed standards before final scoring

Runtime Contract

Runtime family:

  • evaluation-runtime

Identifier:

  • docs-audit

Phase order:

  1. PHASE_0_CONFIG
  2. PHASE_1_DISCOVERY
  3. PHASE_2_RESEARCH
  4. PHASE_3_DELEGATE
  5. PHASE_4_AGGREGATE
  6. PHASE_5_REPORT
  7. PHASE_6_SELF_CHECK

Worker Set

  • ln-611-docs-structure-auditor
  • ln-612-semantic-content-auditor
  • ln-613-code-comments-auditor
  • ln-614-docs-fact-checker

Worker Invocation (MANDATORY)

Use the Skill tool for delegated workers. Do not inline worker logic inside the coordinator.

TodoWrite format (mandatory):

  • Resolve audit scope and build manifest
  • Load project documentation tree
  • Run best-practice research
  • Delegate to domain audit workers
  • Aggregate worker findings
  • Generate audit report
  • Verify cleanup and self-check

Representative invocations:

Skill(skill: "ln-611-docs-structure-auditor", args: "{scope}")
Skill(skill: "ln-612-semantic-content-auditor", args: "{scope}")
Skill(skill: "ln-613-code-comments-auditor", args: "{scope}")
Skill(skill: "ln-614-docs-fact-checker", args: "{scope}")

Workflow

Phase 0: Config

Start evaluation-runtime with required_research=true.

Phase 1: Discovery

Discover documentation surfaces and scope.

Phase 2: Research

Mandatory research sources:

  1. official docs or standards
  2. MCP Ref
  3. Context7 when framework docs matter
  4. current web best-practice research

Phase 3: Delegate

Delegate specialized audit workers.

Child workers must use evaluation-worker-runtime and emit evaluation-compatible summaries recorded through evaluation-runtime.

Phase 4: Aggregate

Merge worker findings into one documentation audit result.

Phase 5: Report

Write final documentation audit output and coordinator summary.

Phase 6: Self-Check

Required checks:

  • mandatory research completed
  • all worker summaries recorded
  • aggregate summary exists
  • cleanup verified
  • coordinator summary recorded

Summary Contract

Write summary_kind=evaluation-coordinator.

Definition of Done

  • Evaluation runtime started
  • Research completed
  • All documentation audit workers completed
  • Aggregation completed
  • Final report written
  • evaluation-coordinator summary written
  • Runtime completed

Meta-Analysis

MANDATORY READ: Load shared/references/meta_analysis_protocol.md

After the coordinator run, analyze the session per protocol section 7 and include the protocol-formatted output with the final documentation audit result.

References

  • Workers: ../ln-611-docs-structure-auditor/SKILL.md, ../ln-612-semantic-content-auditor/SKILL.md, ../ln-613-code-comments-auditor/SKILL.md, ../ln-614-docs-fact-checker/SKILL.md

Version: 5.0.0 Last Updated: 2026-03-01

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude

34.17%
按下载量换算612

Codex

33.56%
按下载量换算601

Cursor

18.42%
按下载量换算330

Gemini CLI

10.56%
按下载量换算189

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

external-service

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 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills