Audit Document

Organization

devcodex-labs

audit-document

通用文档审查维度 DA-1~DA-6 — README/架构文档/开发指南专属审查层

Overview

Publisher	devcodex-labs
Repository	`devcodex`
Skill name	`audit-document`
Stars	433
Forks	44
Bundled files	1
License	AGPL-3.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by devcodex-labs on GitHub. Read the source before you install it.

Installation

Install the Audit Document AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/devcodex-labs/devcodex/tree/main/content/skills/audit-document
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/devcodex-labs/devcodex.git /tmp/devcodex
mkdir -p .claude/skills
cp -r /tmp/devcodex/content/skills/audit-document .claude/skills/audit-document

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Audit Document in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Audit Document on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Audit Document is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Audit Document Skill

适用范围

审查目标为通用文档（README、架构文档、开发指南，不属于规范/技术方案/需求/报告）时，叠加本 Skill（在 G1~G5 之后）。

用户侧文档、最终用户手册、站点文档、项目文档、菜单导航或文档 IA review 场景应优先使用 audit-user-manual 作为聚合入口；本 Skill 仍负责其中的通用文档审查维度。README / 主入口文档场景在本 Skill 基础上，还应叠加 audit-readme。

维度总览（DA-1~DA-6）

分组	维度	优先级
A — 内容质量	DA-1 结构完整性 · DA-2 内容准确性	🔴
B — 引用与术语	DA-3 引用有效性 · DA-4 术语一致性	🔴/🟡
C — 受众与关联	DA-5 受众适配 · DA-6 关联一致性	💡/🔴

核心检查维度

DA-1 结构完整性 🔴

有目录/大纲且与实际章节一致（无多余/遗漏）
章节间有逻辑连贯性（无突兀断层）
无未完成章节（标题存在但内容为空/"TBD"）
标题层级合理（H1 唯一，逐级递进，无跳级）

DA-2 内容准确性 🔴

版本号/路径/技术栈与实际项目状态一致
代码示例可执行（语法正确，命令可运行）
API/配置说明与代码实现匹配

DA-3 引用有效性 🔴

内部链接（相对路径）目标文件存在
外部链接可访问（不 404）
代码引用的文件/函数/类型存在

DA-4 术语一致性 🟡

同一概念在文档内用统一术语（不混用别名）
术语与项目 profile 定义一致

条件用户文档 / 文档站门禁（差分入口）

共享 Gate 分组与完整探针以 ../spec-governance/gate-registry.json 与 Owner Skill user-manual-authoring / audit-user-manual / expert-output-quality 为准；本 Skill 在 DA-1~DA-6 之外只保留审查触发摘要，不复制用户手册 Gate 百科。

面向使用者的文档：从“这是什么 / 适合谁 / 第一次成功 / 常见任务 / 失败恢复 / 下一步”审查；术语首次解释；示例真实；正式用户文档不得降为内部笔记口吻
用户手册 / 站点文档 / README：优先经 audit-user-manual 聚合；核对主受众、落点、IA、真实工作流与消费者同步；未发布能力不得用开发文档冒充用户手册
多语言 / 正式边界：信息等价与导航顺序；正式面不混台账/复盘；“已验证/可点击”须有实际命令或页面证据
流程图 / 生成站点 / 示例语义 / 专家产物：运行态或生成产物证据，而非仅 Markdown；示例可追溯 public type/runtime；fixture 不得描述成生产推荐路径；不适用写 N/A + skipReason

README 叠加规则

当目标是 README 或主用户使用文档时：

先执行 DA-1~DA-6
若用户要求用户侧文档 review、项目文档、菜单导航或信息架构审查，先通过 audit-user-manual 聚合证据
再叠加 audit-readme 的 RM-1~RM-6
通用结构/准确性问题留在 DA-*
用户路径、快速开始、示例真实度、开发信息后置与消费链一致性问题留在 RM-*

维护者站点维（DA-M · 条件）

当审查目标为维护者/贡献者开发文档站（docsAudience=maintainer-dev 或 CONTRIBUTING/dev/internals 主路径）时，在 DA-1~DA-6 之上追加：

检查	要求
DA-M1 可执行 dev 路径	具备 clone/环境/依赖安装与 test 或 build 命令之一；不得仅产品介绍
DA-M2 受众一致	主叙事服务维护者；不得伪装成用户安装手册却无用户第一次成功路径
DA-M3 命令可信	关键命令与 `package.json`/仓库脚本不矛盾，或标明 N/A 理由
DA-M4 漂移	模型按维护者实际任务审查正文，形成与正文摘要绑定的 review；`classifyDocsAudienceDriftSample('maintainer-dev', body, review)` 只校验绑定并投影结论，unverified 不代表通过

用户站审查仍优先 audit-user-manual；本维不替代用户站聚合入口。

N/A 规则

纯图表/示意图文件无受众概念：DA-5 标 N/A
无关联代码：DA-6 标 N/A
未触发用户手册 / 文档站 / 多语言 / 生成站点 / 示例语义 / 专家产物时：对应条件门禁聚合写 N/A + skipReason（完整 Gate 名见 registry / Owner Skill）
未触发维护者站：DA-M 聚合 N/A + skipReason=not-maintainer-docs
公开主路径若展示旧兼容路径或 DSL/parser 示例：分别检查副作用兼容边界与最小执行探针（Owner：user-manual-authoring / dev-docs）

同步锚点（validate / consumer）

ExpertOutputQualityGate · fixture/mock/demo

额外同步锚点

UserManualProductizationGate · UserManualRenderedFlowAndRealWorkflowProbe · DocsThemeRuntimeVisualProbeGate · BehaviorSemanticDocsParityGate · NegativeTranslationParityProbe · DocsExampleTruthSurfaceGate · CallbackExampleScopeProbe

DocumentationTranslationParityGuard · FormalDocsDevCodexBoundary · LiveVerificationExecutionObligation · FlowchartNodeExplanationGate · DocsSiteVisualAcceptanceGate · UserPerspectiveDocsGate · DocsConsumerSweep · 低心智负担 SideEffectCompatibilityDocsGate · ExecutableExampleTruthProbeGate · UserDocsImmediateComprehensionGate · UserDocsPrimarySurfaceGate · 未发布 runtime · FinalUserManualFirstGate · DocsSiteInformationArchitectureGate · UserManualFlowAndFailureGate · GeneratedSiteGate · ManualTocDuplicationGate · UserPathContractSweep · PublicUserDocsMaintainerBoundaryGate

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

intent.json1 KB

Frequently asked questions

What does the Audit Document AI skill do?

通用文档审查维度 DA-1~DA-6 — README/架构文档/开发指南专属审查层

Why use Audit Document on TypingMind?

Because you install it once and use it with any model. Audit Document is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Audit Document in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/devcodex-labs/devcodex/tree/main/content/skills/audit-document. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Audit Document?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Audit Document?

As many as you like. As long as a model supports skills, you can use Audit Document with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Audit Document AI skill free?

Yes. It is published on GitHub by devcodex-labs under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Skill Host Compat

affaan-m

CommunityPopular

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Brand Voice

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants…

Competitive Platform Analysis

affaan-m

CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

Content Engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Audit Document Skill

适用范围

维度总览（DA-1~DA-6）

核心检查维度

README 叠加规则

维护者站点维（DA-M · 条件）

N/A 规则

同步锚点（validate / consumer）

额外同步锚点

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now