Agent skill

Devdocs Insights

by majiayu000 in majiayu000/claude-skill-registry

Collect improvement insights from UI/UX reviews, document research, or external references, convert confirmed items into development requirements.

MITAuto-check passedFrontend & Design

Install Devdocs Insights

skills CLI
$ npx skills add majiayu000/claude-skill-registry --skill devdocs-insights -a claude-code

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

GitHub CLI
$ gh skill install majiayu000/claude-skill-registry devdocs-insights --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/majiayu000/claude-skill-registry.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/analysis/devdocs-insights .claude/skills/devdocs-insights && 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
devdocs-insights
GitHub stars
666
Used in
1 other repo
Token cost
~1.9k tokens
SKILL.md length
173 words
Files
2
Skills in repo
971
Repo updated
First seen
Licence
MIT

At a glance

Collect improvement insights from UI/UX reviews, document research, or external references, convert confirmed items into development requirements.

  • Users have optimization suggestions
  • SKILL.md covers 语言规则, 触发条件, 核心理念 and 工作流程, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Research findings

What it does

Devdocs Insights is an agent skill from majiayu000/claude-skill-registry. Collect improvement insights from UI/UX reviews, document research, or external references, convert confirmed items into development requirements. Use when users have optimization suggestions, research findings, or want to improve based on external references. Triggers on keywords like "insights", "improvements", "optimize", "review findings", "research", "借鉴", "优化建议", "审查结果", "调研".

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `metadata.json`).

It sits in Frontend & Design, covering UI design and Code review. The repository describes itself as: Searchable Claude Code skills catalog with source-linked guides and generated registry artifacts. The licence is MIT.

When your agent uses it

  • Users have optimization suggestions
  • Research findings
  • Want to improve based on external references
  • Keywords like insights

Example prompts

  • “insights”
  • “improvements”
  • “optimize”
  • “/devdocs-insights”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Glob, Grep, AskUserQuestion, WebFetch

What it can do on your machine

Read from SKILL.md and the folder at commit 000116a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Glob
    • Grep
    • AskUserQuestion
    • WebFetch

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and bash).

    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

Devdocs Insights loads about 1.9k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 173 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 majiayu000/claude-skill-registry at commit 000116a, republished under its MIT licence (© majiayu000). 173 words, ~1,903 tokens.

Download SKILL.mdSave it as .claude/skills/devdocs-insights/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
devdocs-insights
description
Collect improvement insights from UI/UX reviews, document research, or external references, convert confirmed items into development requirements. Use when users have optimization suggestions, research findings, or want to improve based on external references. Triggers on keywords like "insights", "improvements", "optimize", "review findings", "research", "借鉴", "优化建议", "审查结果", "调研".
allowed-tools
Read, Write, Glob, Grep, AskUserQuestion, WebFetch

洞察收集

收集来自 UI/UX 审查、文档调研、外部参考等来源的改进建议,经用户确认后转化为开发需求。

语言规则

  • 支持中英文提问
  • 统一中文回复
  • 使用中文生成文档

触发条件

  • 用户完成 UI/UX 审查,有优化建议
  • 用户调研了文档/方案,发现可借鉴点
  • 用户发现外部参考(竞品、最佳实践)可借鉴
  • 用户有改进想法需要转化为需求

核心理念

洞察来源
┌─────────────────────────────────────────────────────────────┐
│                      洞察来源                                │
├─────────────────────────────────────────────────────────────┤
│  🎨 UI/UX 审查     │ 界面问题、交互优化、视觉改进            │
├─────────────────────────────────────────────────────────────┤
│  📄 文档调研       │ 技术方案、设计模式、架构参考            │
├─────────────────────────────────────────────────────────────┤
│  🔍 外部参考       │ 竞品分析、行业最佳实践、开源项目        │
├─────────────────────────────────────────────────────────────┤
│  💡 内部反馈       │ 用户反馈、团队建议、性能监控            │
└─────────────────────────────────────────────────────────────┘
转化流程
洞察来源                确认阶段                 输出阶段
    │                      │                        │
    ▼                      ▼                        ▼
┌─────────┐          ┌─────────┐            ┌─────────────┐
│ 收集    │    →     │ 用户    │      →     │ 追加到      │
│ 建议    │          │ 确认    │            │ 需求文档    │
└─────────┘          └─────────┘            └─────────────┘
                          │
                          ▼
                    部分确认 / 全部确认 / 拒绝

核心原则:

  • 建议必须经过用户确认才能转化为需求
  • 保留建议来源的追溯性
  • 区分优先级,避免需求膨胀

工作流程

1. 识别洞察来源
   │
   ▼
2. 收集/整理建议
   ├── UI/UX 审查结果
   ├── 文档调研发现
   ├── 外部参考借鉴
   └── 内部反馈汇总
   │
   ▼
3. 结构化建议列表
   ├── 分类整理
   ├── 评估影响范围
   └── 建议优先级
   │
   ▼
4. 用户确认(AskUserQuestion)
   ├── 逐条确认
   ├── 批量确认
   └── 调整优先级
   │
   ▼
5. 转化为需求
   ├── 生成功能点 (F-XXX)
   ├── 生成验收标准 (AC-XXX)
   └── 追加到 01-requirements.md
   │
   ▼
6. 建议后续流程
   └── 运行 /devdocs-system-design 或 /devdocs-dev-tasks

输出文件

洞察记录(可选)

文件:docs/devdocs/05-insights.md

用于记录洞察来源和转化历史,便于追溯。

需求追加

确认的建议将追加到:docs/devdocs/01-requirements.md

建议结构

单条建议格式
markdown
### INS-001: <建议标题>

| 属性 | 内容 |
|------|------|
| **来源** | 🎨 UI/UX 审查 / 📄 文档调研 / 🔍 外部参考 / 💡 内部反馈 |
| **参考** | <来源链接或描述> |
| **现状** | <当前问题或不足> |
| **建议** | <改进建议> |
| **影响范围** | <涉及模块/功能> |
| **优先级** | P0 / P1 / P2 |
| **状态** | ⏳ 待确认 / ✅ 已确认 / ❌ 已拒绝 / 🔄 已转化 |

**预期收益**:
- <收益1>
- <收益2>
建议列表格式
markdown
# 洞察收集:<主题>

**收集时间**:YYYY-MM-DD
**来源类型**:UI/UX 审查 / 文档调研 / 外部参考

## 建议汇总

| 编号 | 标题 | 来源 | 优先级 | 状态 |
|------|------|------|--------|------|
| INS-001 | <标题> | 🎨 | P1 | ⏳ |
| INS-002 | <标题> | 📄 | P0 | ⏳ |

## 详细建议

### INS-001: <标题>
...

---

## 确认结果

- [x] INS-001: 已确认 → F-XXX
- [ ] INS-002: 待确认
- [x] INS-003: 已拒绝(原因:...)

来源类型处理

🎨 UI/UX 审查
markdown
**输入**:
- 用户提供截图/原型
- 用户描述交互问题
- 运行 /ui-skills 审查结果

**关注点**:
- 可用性问题
- 视觉一致性
- 无障碍性
- 响应式适配
- 交互流畅度

**示例建议**:
- INS-001: 按钮对比度不足,影响可读性
- INS-002: 表单缺少加载状态反馈
- INS-003: 移动端导航菜单难以点击
📄 文档调研
markdown
**输入**:
- 技术文档链接
- 设计方案文档
- 最佳实践指南

**关注点**:
- 可借鉴的架构模式
- 更优的实现方案
- 性能优化技术
- 安全加固措施

**示例建议**:
- INS-004: 采用 React Query 替代手动状态管理
- INS-005: 引入乐观更新提升用户体验
- INS-006: 使用 Zod 进行运行时类型校验
🔍 外部参考
markdown
**输入**:
- 竞品链接/截图
- 开源项目参考
- 行业报告

**关注点**:
- 竞品优势功能
- 行业通用模式
- 用户期望对齐

**示例建议**:
- INS-007: 参考 Notion 的拖拽排序交互
- INS-008: 借鉴 Linear 的快捷键系统
- INS-009: 采用类似 Figma 的实时协作模式
💡 内部反馈
markdown
**输入**:
- 用户反馈记录
- 团队讨论结果
- 性能监控数据

**关注点**:
- 高频用户痛点
- 团队共识问题
- 性能瓶颈

**示例建议**:
- INS-010: 列表加载慢,需要分页或虚拟滚动
- INS-011: 搜索功能缺少高级筛选
- INS-012: 导出功能需要支持更多格式

用户确认流程

使用 AskUserQuestion 进行交互式确认:

单条确认
建议 INS-001: 按钮对比度不足,影响可读性

来源:🎨 UI/UX 审查
优先级:P1
影响范围:全局按钮组件

是否确认转化为需求?
- 确认(转化为 F-XXX)
- 调整优先级后确认
- 拒绝(请说明原因)
- 稍后决定
批量确认
以下建议待确认:

| 编号 | 标题 | 优先级 |
|------|------|--------|
| INS-001 | 按钮对比度不足 | P1 |
| INS-002 | 缺少加载状态 | P1 |
| INS-003 | 移动端导航问题 | P2 |

请选择:
- 全部确认
- 选择性确认(输入编号,如:1,2)
- 全部拒绝
- 逐条审查

需求转化规则

转化映射
建议类型转化为说明
新功能建议F-XXX (新功能点)创建新的功能点
优化建议F-XXX (优化标记)标记为优化类型
Bug 修复直接触发 /devdocs-bugfix走 Bug 修复流程
技术改进F-XXX (技术债务)标记为技术改进
功能点格式
markdown
### F-XXX: <功能名称> [优化]

**来源**:INS-XXX (<来源类型>)
**优先级**:P0 / P1 / P2

**描述**:
<从建议转化的功能描述>

**验收标准**:
- AC-XXX: <可验证的标准1>
- AC-XXX: <可验证的标准2>
编号规则
  • 功能点编号:延续 01-requirements.md 中的编号
  • 验收标准编号:延续现有 AC 编号
  • 建议编号:INS-XXX(仅在洞察文档中使用)

约束

收集约束
  • 必须标明建议来源
  • 必须评估影响范围
  • 每条建议必须有明确的现状和改进点
  • 外部参考必须提供来源链接
确认约束
  • 所有建议必须经过用户确认才能转化
  • 拒绝的建议必须记录原因
  • 批量确认前必须展示完整列表
  • 用户可以调整建议优先级
转化约束
  • 转化后的需求必须可追溯到原始建议
  • 必须生成可验证的验收标准
  • 优化类需求必须标记 [优化] 标签
  • 转化后更新建议状态为 🔄 已转化
避免需求膨胀
  • 单次收集建议不超过 10 条
  • 低优先级建议可标记为"待定"
  • 鼓励用户聚焦核心改进
  • 定期清理过期的待确认建议

Skill 协作

场景协作 Skill说明
UI/UX 审查来源/ui-skills审查结果可作为洞察来源
需求转化/devdocs-requirements被调用:洞察转化为需求
设计变更/devdocs-system-design触发:复杂改进需要设计调整
测试补充/devdocs-test-cases触发:改进建议需要测试覆盖
简单改进/devdocs-dev-tasks无架构变更,直接拆分任务
复杂改进/devdocs-feature有架构变更,走完整流程
Bug 类建议/devdocs-bugfix走 Bug 修复流程
需求更新/devdocs-sync同步文档状态

使用示例

示例一:UI/UX 审查后
用户: 我刚审查了登录页面,发现几个问题想优化

Agent: 好的,让我帮你收集这些优化建议。请描述发现的问题:

用户:
1. 密码输入框没有显示/隐藏切换
2. 忘记密码链接不够明显
3. 第三方登录按钮风格不统一

Agent: 已整理以下建议:

| 编号 | 标题 | 优先级 | 状态 |
|------|------|--------|------|
| INS-001 | 添加密码可见性切换 | P1 | ⏳ |
| INS-002 | 突出忘记密码链接 | P2 | ⏳ |
| INS-003 | 统一第三方登录按钮风格 | P2 | ⏳ |

请确认要转化为需求的建议(输入编号,如 1,2,3 或 "全部"):

用户: 1,3

Agent:
✅ 已确认 INS-001, INS-003
已追加到 01-requirements.md:
- F-015: 密码可见性切换 [优化] (来源: INS-001)
- F-016: 统一第三方登录按钮 [优化] (来源: INS-003)

是否继续运行 /devdocs-dev-tasks 拆分开发任务?
示例二:文档调研后
用户: 我看了这篇文章 https://example.com/react-patterns,想借鉴一些模式

Agent: 让我分析这篇文章并提取可借鉴的点...

[WebFetch 获取内容]

基于文章内容,整理以下借鉴建议:

| 编号 | 标题 | 参考章节 | 优先级 |
|------|------|----------|--------|
| INS-001 | 采用 Compound Components 模式 | 第3节 | P1 |
| INS-002 | 使用 Render Props 替代 HOC | 第5节 | P2 |
| INS-003 | 引入 Custom Hooks 复用逻辑 | 第7节 | P1 |

请确认要采纳的建议:

命令选项

bash
# 标准模式:交互式收集和确认
/devdocs-insights

# 从 URL 提取建议
/devdocs-insights --url <url>

# 从文件提取(如审查报告)
/devdocs-insights --file <path>

# 快速模式:直接输入建议列表
/devdocs-insights --quick

下一步

确认建议并转化为需求后,根据改进复杂度选择路径:

路径选择
确认的改进建议
      │
      ▼
评估是否涉及架构变更
      │
      ├── 无架构变更(简单改进)
      │   ├── UI 微调、配置修改、小功能
      │   └── → /devdocs-dev-tasks 直接拆分任务
      │
      └── 有架构变更(复杂改进)
          ├── 新接口、数据模型变更、新模块
          └── → /devdocs-feature 完整流程
                  └── system-design → test-cases → dev-tasks
架构变更判断
条件是否架构变更推荐路径
仅 UI/样式调整否/devdocs-dev-tasks
仅配置项修改否/devdocs-dev-tasks
新增 API 接口是/devdocs-feature
数据模型变更是/devdocs-feature
新增独立模块是/devdocs-feature
第三方服务集成是/devdocs-feature
使用 AskUserQuestion 确认
已确认 X 条改进建议,转化为需求。

检测到以下情况:
- INS-001: UI 按钮样式调整 → 无架构变更
- INS-003: 新增导出 API → 涉及架构变更

建议路径:
- INS-001 → /devdocs-dev-tasks(直接拆分任务)
- INS-003 → /devdocs-feature(完整流程)

是否按建议执行?[是/调整]

© majiayu000, MIT. 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 skills/analysis/devdocs-insights of majiayu000/claude-skill-registry.

  • SKILL.md
  • metadata.json

Open the folder on GitHubat commit 000116a

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in majiayu000/claude-skill-registry, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Devdocs Insights 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.

Devdocs Insights compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Devdocs Insights this skillmajiayu000/claude-skill-registry6661 repos~1.9kAutomated safety check: PassMIT
Tidymblode/agent-skills142—~4.2kAutomated safety check: PassMIT
Instruction Dashboard Tuningadam-s/intercept189—~4.3kAutomated safety check: PassMIT
Spec App Consistency Auditleo-kuang-ai/spec-first107—~4.6kAutomated safety check: PassMIT
Lofisu Personazclllyybb/lofisu-identity-engine453—~2.8kAutomated safety check: PassUnlicense
Liteyuki Webui FrontendLiteyukiStudio/LiteyukiBot157—~2.5kAutomated safety check: PassCustom licence

Similar skills

  • Tidy

    mblode/agent-skills

    Reviews a local diff, branch diff, or PR with file:line findings in confirmed and plausible tiers, gates any test the diff adds or changes, and in apply mode lands the fixes and diff-scoped…

    142 GitHub stars~4.2k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Use sub-agents to iteratively improve dashboard-building instructions.

    189 GitHub stars~4.3k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed
  • Spec App Consistency Audit

    leo-kuang-ai/spec-first

    Audit mobile App PRD/Figma/local-source consistency across page routes, KMP/Clean Architecture, components, analytics, i18n, engineering quality, and industry lenses before runtime validation; use…

    107 GitHub stars~4.6k tokensUpdated 13 days ago
    DevelopmentAuto-check passed
  • Lofisu Persona

    zclllyybb/lofisu-identity-engine

    LofiSu的行为人格Skill。基于GitHub公开数据(282次commit/150次README迭代/50+fork/100+contribution) 的Codex深度挖掘分析报告+小红书卖课行为报告的系统蒸馏, 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。

    453 GitHub stars~2.8k tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed
  • Liteyuki Webui Frontend

    LiteyukiStudio/LiteyukiBot

    Build, review, or test LiteyukiBot v7's React/Vite WebUI under webui/ and its packaged static delivery in packages/webui/.

    157 GitHub stars~2.5k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Fix PR Design Notes

    different-ai/openwork

    Reads the advisory design review attached to a pull request's screenshots, fixes the flagged UI problems in product code, and proves each note is gone.

    24k GitHub stars~824 tokensUpdated today
    Frontend & DesignAuto-check passed

More from majiayu000/claude-skill-registry

All 971 skills in this repo
  • Deep Research

    majiayu000/claude-skill-registry

    Multi-source deep research using firecrawl and exa MCPs. An agent skill from majiayu000/claude-skill-registry.

    666 GitHub starsUsed in 6 repos~1.1k tokens
    Auto-check passed
  • Exa Search

    majiayu000/claude-skill-registry

    Neural search via Exa MCP for web, code, and company research.

    666 GitHub starsUsed in 5 repos~856 tokens
    Auto-check passed
  • Fal AI Media

    majiayu000/claude-skill-registry

    Unified media generation via fal.ai MCP — image, video, and audio.

    666 GitHub starsUsed in 5 repos~1.7k tokens
    Auto-check passed
  • Bgpt Paper Search

    majiayu000/claude-skill-registry

    Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server.

    666 GitHub starsUsed in 4 repos~619 tokens
    Auto-check: notes
  • Bio Alignment Pairwise

    majiayu000/claude-skill-registry

    Perform pairwise sequence alignment using Biopython Bio.Align.PairwiseAligner.

    666 GitHub starsUsed in 4 repos~1.7k tokens
    Auto-check passed
  • Open Notebook

    majiayu000/claude-skill-registry

    Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis.

    666 GitHub starsUsed in 4 repos~2.4k tokens
    Auto-check passed

Questions about Devdocs Insights

What does Devdocs Insights do?

Collect improvement insights from UI/UX reviews, document research, or external references, convert confirmed items into development requirements. Devdocs Insights is an agent skill from majiayu000/claude-skill-registry. Collect improvement insights from UI/UX reviews, document research, or external references, convert confirmed items into development requirements.

When should I use Devdocs Insights?

Devdocs Insights fits situations like: users have optimization suggestions; research findings; want to improve based on external references; keywords like insights.

How do I install Devdocs Insights in Claude Code?

Run `npx skills add majiayu000/claude-skill-registry --skill devdocs-insights -a claude-code`. Or copy the skill folder (skills/analysis/devdocs-insights in majiayu000/claude-skill-registry) into .claude/skills/devdocs-insights in your project. Claude Code loads it when a task matches its description.

How do I install Devdocs Insights in Codex?

Run `npx skills add majiayu000/claude-skill-registry --skill devdocs-insights -a codex`. Or copy the skill folder (skills/analysis/devdocs-insights in majiayu000/claude-skill-registry) into .agents/skills/devdocs-insights in your project. Codex loads it when a task matches its description.

Can I use Devdocs Insights 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 majiayu000/claude-skill-registry --skill devdocs-insights -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/devdocs-insights, .gemini/skills/devdocs-insights, .github/skills/devdocs-insights and .opencode/skills/devdocs-insights in your project.

What does Devdocs Insights need to run?

SKILL.md names no scripts, command-line tools or credentials: Devdocs Insights is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Glob, Grep, AskUserQuestion, WebFetch.

Does Devdocs Insights 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 Devdocs Insights 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 Devdocs Insights use?

Devdocs Insights is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Devdocs Insights use?

About 1.9k tokens (SKILL.md is roughly 7.6k 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 Devdocs Insights?

Skills that share tags, products or a category with Devdocs Insights: Tidy (mblode/agent-skills, 142 stars), Instruction Dashboard Tuning (adam-s/intercept, 189 stars), Spec App Consistency Audit (leo-kuang-ai/spec-first, 107 stars) and Lofisu Persona (zclllyybb/lofisu-identity-engine, 453 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Devdocs Insights?

majiayu000 (a GitHub user) maintains it in majiayu000/claude-skill-registry, which has 666 GitHub stars. The repository holds 971 skills in this directory. The repository was last updated on October 7, 2026.

Source: majiayu000/claude-skill-registry on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.