Agent skill

Audit User Manual

by devcodex-labs in devcodex-labs/devcodex

用户侧文档专项审查聚合入口 — 用于审查最终用户文档、站点文档、文档站、README、quick start、接入手册、项目文档、菜单导航、sidebar、信息架构、文档设计、用户路径、配置排错、真实工作流、生成站点和维护者内容边界;当用户要求 review/审查/复审/检查用户侧文档或项目文档可用性时使用。

AGPL-3.0Auto-check passedWriting & Content

Install Audit User Manual

skills CLI
$ npx skills add devcodex-labs/devcodex --skill audit-user-manual -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install devcodex-labs/devcodex audit-user-manual --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/content/skills/audit-user-manual .claude/skills/audit-user-manual && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
audit-user-manual
GitHub stars
439
Token cost
~1.2k tokens
SKILL.md length
259 words
Files
2
Skills in repo
70
Repo updated
First seen
Licence
AGPL-3.0

At a glance

用户侧文档专项审查聚合入口 — 用于审查最终用户文档、站点文档、文档站、README、quick start、接入手册、项目文档、菜单导航、sidebar、信息架构、文档设计、用户路径、配置排错、真实工作流、生成站点和维护者内容边界;当用户要求 review/审查/复审/检查用户侧文档或项目文档可用性时使用。

  • Works in 6 steps: 先读… → 若文档包含代码、示例、fixture、mock、demo、quick… → 再读… → …
  • Tasks that involve Technical writing
  • SKILL.md covers 职责, 触发条件, 读取顺序 and 审查输出矩阵, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Audit User Manual is an agent skill from devcodex-labs/devcodex. 用户侧文档专项审查聚合入口 — 用于审查最终用户文档、站点文档、文档站、README、quick start、接入手册、项目文档、菜单导航、sidebar、信息架构、文档设计、用户路径、配置排错、真实工作流、生成站点和维护者内容边界;当用户要求 review/审查/复审/检查用户侧文档或项目文档可用性时使用。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `intent.json`).

It sits in Writing & Content, covering Technical writing and Technical documentation. The repository describes itself as: Intent-driven AI coding workflow runtime for consistent context, skills, approvals, validation, and handoffs across six AI coding hosts. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Technical writing
  • Tasks that involve Technical documentation

Example prompts

  • “/audit-user-manual”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 先读 user-manual-authoring,确认目标文档契约、受众、文档落点和用户主路径。
  2. 若文档包含代码、示例、fixture、mock、demo、quick start、技术方案或报告解读,读取 expert-output-quality,执行专家型产物质量门禁。
  3. 再读 audit-document,执行通用文档结构、准确性、链接、术语、受众和关联一致性审查。
  4. 若目标是 README 或主入口文档,叠加 audit-readme 的 RM-1~RM-6。
  5. 若用户要求正式复审、收敛、外部 finding 或多轮检查,创建或复用 review-checklist。
  6. 涉及导航、sidebar、生成站点、文档站主题或消费者同步时,按 test-router 与 document-sync 选择验证路线。

What it can do on your machine

Read from SKILL.md and the folder at commit 1dd4525. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Audit User Manual loads about 1.2k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 259 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from devcodex-labs/devcodex at commit 1dd4525, republished under its AGPL-3.0 licence (© devcodex-labs). 259 words, ~1,177 tokens.

Download SKILL.mdSave it as .claude/skills/audit-user-manual/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
audit-user-manual
description
用户侧文档专项审查聚合入口 — 用于审查最终用户文档、站点文档、文档站、README、quick start、接入手册、项目文档、菜单导航、sidebar、信息架构、文档设计、用户路径、配置排错、真实工作流、生成站点和维护者内容边界;当用户要求 review/审查/复审/检查用户侧文档或项目文档可用性时使用。

Audit User Manual Skill

职责

本 Skill 是用户侧文档 review 的薄封装入口。它不重新定义已有 Gate 正文,而是把 user-manual-authoring、expert-output-quality、audit-document、audit-readme、review-checklist、document-sync 和 test-router 的文档审查能力按固定顺序聚合,降低“项目文档 / 文档设计 / 菜单导航”审查时的触发心智。

触发条件

场景是否触发
用户要求审查、review、复审、检查最终用户文档、站点文档、文档站、README、quick start、接入手册必须
用户特别提到项目文档、文档设计、信息架构、菜单、导航、sidebar、目录、页面角色、用户路径必须
docs-first 交付后要求确认用户文档是否能看懂、能否第一次成功、是否够详细必须
纯内部技术方案、架构设计、代码审查、发布报告N/A,走对应 audit Skill

读取顺序

  1. 先读 user-manual-authoring,确认目标文档契约、受众、文档落点和用户主路径。
  2. 若文档包含代码、示例、fixture、mock、demo、quick start、技术方案或报告解读,读取 expert-output-quality,执行专家型产物质量门禁。
  3. 再读 audit-document,执行通用文档结构、准确性、链接、术语、受众和关联一致性审查。
  4. 若目标是 README 或主入口文档,叠加 audit-readme 的 RM-1~RM-6。
  5. 若用户要求正式复审、收敛、外部 finding 或多轮检查,创建或复用 review-checklist。
  6. 涉及导航、sidebar、生成站点、文档站主题或消费者同步时,按 test-router 与 document-sync 选择验证路线。

审查输出矩阵

维度必查证据
文档定位targetSurface、documentLocation、primaryAudience、发布/preview 边界
用户路径这是什么、适合谁、第一次成功、常见任务、配置、失败恢复、限制和下一步
文档设计首页首屏、章节顺序、信息层级、reference / operations / maintainer 分区
菜单导航SidebarPageRoleMaterializationProbe / SidebarGroupSemanticModelProbe、pageRoleMatrix、sidebarSemanticModel、route / label 真相源、相邻页面职责、前两组导航是否服务用户主路径
受众与渲染顺序DocsAudienceRoleAndRenderedSequenceProbe:pageRole 分布、首屏前三信息块、前两组 sidebar、current quick start 距离、manual TOC 与 generated outline 重复数
内容可懂功能完整性、配置易懂性、术语首次解释、字段/参数/状态/错误解释、示例真实度
认知高度 / 任务语言模型审查 guide/readme 能否帮助目标读者完成任务;以当前正文摘要绑定的内容审查与实际使用证据为准,函数或短语数量不决定通过
专家型产物质量ExpertOutputQualityGate、ProductionRecommendedPathGate、FrameworkNativeCapabilityFirstGate、FixtureBoundaryDisclosureGate、AntiPatternContrastGate、ExpertEvidenceMatrixGate,区分生产推荐路径、fixture/mock/demo 边界和反模式
真实工作流quick start、队列/异步/批处理、导入导出、失败重试、幂等和观测是否是业务主路径;完整声明必须有 ScenarioCoverageMatrixProbe,持久化批处理追加 DurableBatchOrchestrationProbe
生成与运行态GeneratedSiteGate;命中文档站主题、搜索、代码高亮、移动端、暗色/亮色或交互变化时执行 DocsThemeRuntimeVisualProbeGate
交互语义命中链接、按钮、菜单、对话框、可展开控件或自定义交互时执行 InteractiveSemanticProbe:role、accessible name、focusability、Enter/Space/Escape、focus recovery;截图不能替代
维护者边界release checklist、内部同步清单、台账状态、实现验收是否后置或移出公开用户主路径
消费者同步README、website、Profile、examples、templates、nav/sidebar、validate probes、部署副本和代码消费点

执行步骤

  1. 冻结审查对象:列出文件、页面、路由、sidebar group、README / docs-site / requirement deliverable 落点。
  2. 输出 UserManualReviewScope:targetSurface、primaryAudience、sourceOfTruth、publishedBoundary、reviewMode=light|full。
  3. 建立 DocsNavigationReviewMatrix:每页 role、audience、route、label、sidebar group、sourceOfTruth、是否用户主路径、相邻页面职责。
  4. 对示例、fixture、mock、demo、quick start 或报告解读执行 ExpertOutputQualityGate;无此类内容时写 N/A + skipReason。
  5. 按 audit-document + 条件 audit-readme 做问题分级;同一问题只记录一次,不重复贴多个维度名。
  6. 对菜单、sidebar、站点生成、主题视觉或真实用户路径声明,选择源码反查、生成产物、Browser/截图或人工证据;有交互对象时叠加 InteractiveSemanticProbe,不得用截图证明键盘/辅助技术语义;未触发写 N/A + skipReason。
  7. 命中站点文档时执行 DocsAudienceRoleAndRenderedSequenceProbe:从源码路由/导航生成 pageRole matrix,并从 fresh generated HTML 或 Browser/Playwright 读取渲染后的首屏、outline 与 CTA 顺序;仅证明 route/label/构建存在不得判用户主面通过。
  8. 输出建议时按“用户立即能否看懂并完成第一次成功”排序,技术实现和维护者改动放在次级。
  9. 声称场景完整时核对每个 in-scope 场景的触发、状态、失败、恢复、观测和 executable evidence;队列/批处理不能用一次 API 调用替代 durable run。
  10. 报告必须引用触发的 Skill、关键 Gate、执行证据、未验证项和剩余风险。
DocsAudienceRoleAndRenderedSequenceProbe

通过条件同时满足:所有公开页面有 current-user / target-user / reference / planning / maintainer 角色;首页首屏前三信息块和 sidebar 前两组优先服务 current-user;current quick start 在约定导航距离内;正文手写 TOC 与 generated outline 无重复;证据来自 fresh 生成产物或运行态页面。任一项未观测只能标 unverified,不能用 Markdown 章节存在推断通过。

与其他 Skill 的关系

  • user-manual-authoring:写作入口和文档契约事实源;本 Skill 负责审查聚合。
  • expert-output-quality:代码、文档、示例、fixture 和报告解读的专家型质量门禁,防止测试夹具或低阶写法误导用户主路径。
  • audit-document:通用文档审查维度,必须叠加。
  • audit-readme:README 或主入口文档时叠加。
  • review-checklist:正式复审、收敛、多轮或 finding 批次时管理清单。
  • document-sync:检查 README / website / Profile / examples / templates / nav/sidebar / validate / 部署副本同步。
  • test-router:决定生成站点、链接、Browser/截图、人工复核或 N/A 路线。

禁止

  • 禁止只看 Markdown 源码就宣告菜单、导航、生成站点或主题交互通过;命中运行态风险时必须有生成产物、预览、截图、Browser 或等价证据。
  • 禁止把开发契约、数据模型、实现验收、release checklist 或台账状态当作用户文档主路径。
  • 禁止把 fixture、mock、demo、硬编码单例或每个 route 重复声明当作用户主路径的生产推荐实践。
  • 禁止用“章节很多”代替“用户能第一次成功”;必须检查用户任务、配置、失败恢复和下一步。
  • 禁止把「导出函数/类型清单式 quick start」判为用户文档通过;认知高度失败等同主路径失败。
  • 禁止复制 user-manual-authoring / audit-document / audit-readme 的完整长清单;本 Skill 只做聚合入口和输出矩阵。

© devcodex-labs, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in content/skills/audit-user-manual of devcodex-labs/devcodex.

  • SKILL.md
  • intent.json

Open the folder on GitHubat commit 1dd4525

Compare with similar skills

Audit User Manual next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Audit User Manual compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit User Manual this skilldevcodex-labs/devcodex439—~1.2kAutomated safety check: PassAGPL-3.0
Beads Documentation Style Guidegastownhall/beads28k—~3.2kAutomated safety check: PassMIT
Technical Writing Standardcursor/plugins10k10 repos~2.4kAutomated safety check: PassNone
Heym Documentation Articlesheymrun/heym1.4k—~780Automated safety check: PassCustom licence
Developer Docs Technical Writervercel-labs/github-tools131—~3.9kAutomated safety check: PassMIT
Aholo Viewer Docsmanycoretech/aholo-viewer1.1k—~341Automated safety check: PassMIT

Similar skills

  • Sets the house style for the beads user docs: the canonical concept model, required terminology, prose and diagram conventions, and checks before docs work is done.

    28k GitHub stars~3.2k tokensUpdated today
    Writing & ContentAuto-check passed
  • Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    10k GitHub starsUsed in 10 repos~2.4k tokens
    Writing & ContentAuto-check passed
  • Creates and updates documentation articles for the Heym platform: category choice, manifest entry, markdown file and cross-links from existing pages.

    1.4k GitHub stars~780 tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Developer Docs Technical Writer

    vercel-labs/github-tools

    Official

    Writes, reviews and edits developer documentation for SDKs, libraries and frameworks, from getting-started guides and API references to migration guides.

    131 GitHub stars~3.9k tokensUpdated 8 days ago
    Writing & ContentAuto-check passed
  • Aholo Viewer Docs

    manycoretech/aholo-viewer

    Guides writing and maintaining Aholo Viewer documentation: README, AGENTS.md, architecture notes, bilingual manual pages and AI collaboration guides.

    1.1k GitHub stars~341 tokensUpdated 13 days ago
    Writing & ContentAuto-check passed
  • Diataxis

    WebMCP-org/npm-packages

    Write technical documentation following the Diataxis framework by Daniele Procida.

    103 GitHub stars~1.7k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed

More from devcodex-labs/devcodex

All 70 skills in this repo
  • Accessibility I18n

    devcodex-labs/devcodex

    无障碍与国际化专家 Owner — 当任务涉及可访问性、键盘操作、焦点、屏幕阅读器、ARIA、语言地区、本地化、RTL、翻译资源、用户可见文案或多语言文档时使用;要求把包容性体验和本地化验证绑定到真实用户路径。

    439 GitHub stars~718 tokensUpdated 20 days ago
    Auto-check passed
  • AI Agent System Architecture

    devcodex-labs/devcodex

    AI Agent 系统架构专家 Owner — 当任务涉及 Agent 路由、工具调用、上下文管理、记忆、状态机、权限、人机协作、可观测性、回放验证或模型辅助治理时使用;要求把 Agent 行为设计成可解释、可恢复、可审计。

    439 GitHub stars~2.4k tokensUpdated 20 days ago
    Auto-check passed
  • API Contract Architecture

    devcodex-labs/devcodex

    API 契约架构专家 Owner — 当任务涉及 public API、HTTP/SDK/CLI 契约、版本兼容、错误模型、分页过滤、幂等、Schema、类型、迁移或消费者影响时使用;要求先冻结消费者契约,再设计实现与验证。

    439 GitHub stars~865 tokensUpdated 20 days ago
    Auto-check passed
  • Architecture Design

    devcodex-labs/devcodex

    架构设计文档编排 Owner — 当用户要求架构设计、系统设计、技术架构或可指导开发、Review 与任务拆分的完整方案时使用;要求从业务流程反推节点、状态、数据、一致性、异常补偿、ADR 与实施任务。

    439 GitHub stars~1.1k tokensUpdated 20 days ago
    Auto-check passed
  • Audit Common

    devcodex-labs/devcodex

    审查公共维度 G0~G5 + Profile Freshness Check — 所有 audit 子类型必先执行的基础维度层

    439 GitHub stars~4.1k tokensUpdated 20 days ago
    Auto-check passed
  • Audit Session

    devcodex-labs/devcodex

    审计工作流的跨会话状态机 — 在 <audit-root/.audit-state/<session-id.json 持久化轮次/发现项/收敛状态,支持 Token 中断后精准恢复

    439 GitHub stars~1.8k tokensUpdated 20 days ago
    Auto-check passed

Questions about Audit User Manual

What does Audit User Manual do?

用户侧文档专项审查聚合入口 — 用于审查最终用户文档、站点文档、文档站、README、quick start、接入手册、项目文档、菜单导航、sidebar、信息架构、文档设计、用户路径、配置排错、真实工作流、生成站点和维护者内容边界;当用户要求 review/审查/复审/检查用户侧文档或项目文档可用性时使用。. Audit User Manual is an agent skill from devcodex-labs/devcodex.

When should I use Audit User Manual?

Audit User Manual fits situations like: tasks that involve Technical writing; tasks that involve Technical documentation.

How do I install Audit User Manual in Claude Code?

Run `npx skills add devcodex-labs/devcodex --skill audit-user-manual -a claude-code`. Or copy the skill folder (content/skills/audit-user-manual in devcodex-labs/devcodex) into .claude/skills/audit-user-manual in your project. Claude Code loads it when a task matches its description.

How do I install Audit User Manual in Codex?

Run `npx skills add devcodex-labs/devcodex --skill audit-user-manual -a codex`. Or copy the skill folder (content/skills/audit-user-manual in devcodex-labs/devcodex) into .agents/skills/audit-user-manual in your project. Codex loads it when a task matches its description.

Can I use Audit User Manual in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add devcodex-labs/devcodex --skill audit-user-manual -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-user-manual, .gemini/skills/audit-user-manual, .github/skills/audit-user-manual and .opencode/skills/audit-user-manual in your project.

What does Audit User Manual need to run?

SKILL.md names no scripts, command-line tools or credentials: Audit User Manual is instructions for the agent only.

Does Audit User Manual access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Audit User Manual safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Audit User Manual use?

Audit User Manual is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audit User Manual use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Audit User Manual?

Skills that share tags, products or a category with Audit User Manual: Beads Documentation Style Guide (gastownhall/beads, 28k stars), Technical Writing Standard (cursor/plugins, 10k stars), Heym Documentation Articles (heymrun/heym, 1.4k stars) and Developer Docs Technical Writer (vercel-labs/github-tools, 131 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit User Manual?

devcodex-labs (a GitHub organization) maintains it in devcodex-labs/devcodex, which has 439 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on September 17, 2026.

Source: devcodex-labs/devcodex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.