devbooks-docs-consistency — community devbooks-docs-consistency, dev-playbooks-cn, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Code Analysis Agents needing advanced documentation consistency capabilities, particularly those leveraging SSOT, Knife, and quality gateways. 在不可靠的 AI 之上构建可靠的软件。通过 SSOT、Knife 切片、质量闸门与证据闭环，让单人驾驭大型 AI 项目。

Darkbluelr Darkbluelr
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The devbooks-docs-consistency skill by Darkbluelr is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for Code Analysis Agents needing advanced documentation consistency capabilities, particularly those leveraging SSOT, Knife, and quality gateways.

Core Value

Empowers agents to enforce documentation consistency through comprehensive content analysis, utilizing protocols like Dev-Playbooks and file formats such as .yaml and .md, while ensuring evidence closure and traceability via reference tracking and impact analysis.

↓ Capabilities Granted for devbooks-docs-consistency

Automating documentation validation for large-scale AI projects
Generating executable outputs and guidance for single-person projects
Debugging inconsistencies in documentation across multiple repositories

! Prerequisites & Limits

  • Requires specific configuration files (.devbooks/config.yaml, dev-playbooks/project.md, or project.md)
  • Does not replace other role responsibilities or modify tests/
  • Dependent on the presence of specific file paths or project contexts
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

devbooks-docs-consistency

Install devbooks-docs-consistency, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command...

SKILL.md
Readonly

DevBooks：文档一致性（Docs Consistency）

渐进披露

基础层（必读）

目标：明确本 Skill 的核心产出与使用范围。 输入：用户目标、现有文档、变更包上下文或项目路径。 输出：可执行产物、下一步指引或记录路径。 边界：不替代其他角色职责，不触碰 tests/。 证据：引用产出物路径或执行记录。

进阶层（可选）

适用：需要细化策略、边界或风险提示时补充。

扩展层（可选）

适用：需要与外部系统或可选工具协同时补充。

推荐 MCP 能力类型

  • 代码检索（code-search）
  • 引用追踪（reference-tracking）
  • 影响分析（impact-analysis）

前置：配置发现（协议无关）

执行前必须按以下顺序查找配置（找到后停止）：

  1. .devbooks/config.yaml（如存在）→ 解析并使用其中的映射
  2. dev-playbooks/project.md（如存在）→ Dev-Playbooks 协议，使用默认映射
  3. project.md（如存在）→ template 协议，使用默认映射
  4. 若仍无法确定 → 停止并询问用户

兼容与弃用

  • 旧名称：devbooks-docs-sync
  • 当前名称：devbooks-docs-consistency
  • 行为：旧名称作为别名继续可用，并输出弃用提示。
  • 运行提示：别名通过软链接指向新目录，可执行 scripts/alias.sh 输出提示。

弃用提示示例：

devbooks-docs-sync 已弃用，请使用 devbooks-docs-consistency。

角色定义

docs-consistency 是 DevBooks Apply 阶段的文档一致性检查角色，负责识别文档与代码之间的偏差并生成报告，不直接修改代码。

文档分类

文档类型目标受众是否由本 Skill 检查示例
活体文档最终用户✅README.md, docs/*.md, API.md
历史文档最终用户⚠️（只做最低限度检查）CHANGELOG.md
概念性文档设计/架构✅（结构性检查）architecture/*.md

分类规则可配置，默认规则见 references/doc-classification.yaml。

运行模式

模式一：增量扫描（Change-Scoped）

触发条件：在变更包上下文中运行。

行为：

  1. 读取变更范围
  2. 仅扫描变更文件
  3. 记录 token 消耗与扫描时间
  4. 输出检查报告

模式二：全量扫描（Global Check）

触发条件：用户显式请求全局检查（如 devbooks-docs-consistency --global）。

行为：

  1. 扫描所有用户文档
  2. 生成差异报告
  3. 输出改进建议

模式三：检查模式（Check Only）

触发条件：用户使用 --check 参数。

行为：只检查、不修改，输出报告。

命令示例

# 规则引擎：持续规则
bash scripts/rules-engine.sh --rules references/docs-rules-schema.yaml --input README.md

# 规则引擎：一次性任务
bash scripts/rules-engine.sh --once "remove:@augment" --input README.md

# 文档分类
bash scripts/doc-classifier.sh README.md

# 完备性检查
bash scripts/completeness-checker.sh --input README.md --config references/completeness-dimensions.yaml --output evidence/completeness-report.md

# 作为 G6 Scope Evidence 的机读报告（固定落点）
skills/devbooks-delivery-workflow/scripts/docs-consistency-check.sh <change-id> \
  --project-root . --change-root dev-playbooks/changes --truth-root dev-playbooks/specs

完备性检查

对活体文档执行完备性检查，默认覆盖：环境依赖、安全权限、故障排查、配置说明、API 文档。

  • 维度配置：references/completeness-dimensions.yaml
  • 报告输出：<change-root>/<change-id>/evidence/completeness-report.md
  • 方法论参考：完备性思维框架

风格偏好

风格偏好读取优先级：命令行参数 > 配置文件 > 默认值。

  • 文档维护元数据：dev-playbooks/specs/_meta/docs-maintenance.md

输出与报告

默认输出以下报告（变更包上下文）：

  • evidence/gates/docs-consistency.report.json（机读；供 G6 / archive-decider 消费）
  • evidence/completeness-report.md
  • evidence/token-usage.log
  • evidence/scan-performance.log

与工作流的集成

在归档阶段由 devbooks-archiver 触发，在存量初始化时由 devbooks-brownfield-bootstrap 生成文档维护元数据。

当 G6 触发 Scope Evidence Bundle 且判定“docs 一致性为必需项”时（例如 deliverables 涉及 README.md/docs/**/templates/**，或存在 weak_link+docs 的 severity=must 义务）：

  • 必须生成 evidence/gates/docs-consistency.report.json 且 status=pass
  • 缺失或 status!=pass 将被 archive-decider.sh 判定为 fail，从而阻断归档

元数据

字段值
Skill 名称devbooks-docs-consistency
阶段Apply（实现后、归档前）
产物文档一致性检查报告
约束只检查、不修改代码

此 Skill 文档遵循 devbooks- 规范。*

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is devbooks-docs-consistency?

Perfect for Code Analysis Agents needing advanced documentation consistency capabilities, particularly those leveraging SSOT, Knife, and quality gateways. 在不可靠的 AI 之上构建可靠的软件。通过 SSOT、Knife 切片、质量闸门与证据闭环，让单人驾驭大型 AI 项目。

How do I install devbooks-docs-consistency?

Run the command: npx killer-skills add Darkbluelr/dev-playbooks-cn/devbooks-docs-consistency. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for devbooks-docs-consistency?

Key use cases include: Automating documentation validation for large-scale AI projects, Generating executable outputs and guidance for single-person projects, Debugging inconsistencies in documentation across multiple repositories.

Which IDEs are compatible with devbooks-docs-consistency?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for devbooks-docs-consistency?

Requires specific configuration files (.devbooks/config.yaml, dev-playbooks/project.md, or project.md). Does not replace other role responsibilities or modify tests/. Dependent on the presence of specific file paths or project contexts.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add Darkbluelr/dev-playbooks-cn/devbooks-docs-consistency. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use devbooks-docs-consistency immediately in the current project.

Related Skills

Looking for an alternative to devbooks-docs-consistency or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

★ 138.4k
⑂ 0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI