ln-612-semantic-content-auditor

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
Paths: File paths (
shared/
,
references/
,
../ln-*
) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.
Paths: 文件路径(
shared/
,
references/
,
../ln-*
)是相对于技能仓库根目录的。如果在当前工作目录(CWD)中未找到,请定位到本SKILL.md所在目录,然后向上一级找到仓库根目录。

Semantic Content Auditor (L3 Worker)

语义内容审核器(L3 Worker)

Specialized worker auditing semantic accuracy of project documentation.
专注于审核项目文档语义准确性的专用Worker。

Purpose & Scope

目标与范围

  • Worker in ln-610 coordinator pipeline - invoked by ln-610-docs-auditor for each project document
  • Verify document content matches stated SCOPE (document purpose)
  • Check content aligns with project goals (value contribution)
  • Return structured findings to coordinator with severity, location, fix suggestions
  • Does NOT verify facts against codebase
  • ln-610协调器流水线中的Worker - 由ln-610-docs-auditor调用,针对每个项目文档执行审核
  • 验证文档内容与既定SCOPE(文档目标)匹配
  • 检查内容是否符合项目目标(价值贡献)
  • 向协调器返回包含严重程度、位置和修复建议的结构化审核结果
  • 针对代码库验证事实准确性

Target Documents

目标文档

Called ONLY for project documents (not reference/tasks):
DocumentVerification Focus
CLAUDE.md
Instructions serve stated purpose, no off-topic content
docs/README.md
Navigation scope correct, descriptions relevant
docs/documentation_standards.md
Standards applicable to this project type
docs/principles.md
Principles relevant to project architecture
docs/project/requirements.md
Requirements scope complete, no stale items
docs/project/architecture.md
Architecture scope covers all layers
docs/project/tech_stack.md
Stack scope matches project reality
docs/project/api_spec.md
API scope covers all endpoint groups
docs/project/database_schema.md
Schema scope covers all entities
docs/project/design_guidelines.md
Design scope covers active components
docs/project/runbook.md
Runbook scope covers setup + operations
Excluded:
docs/tasks/
,
docs/reference/
,
docs/presentation/
,
tests/
仅针对项目文档调用(不包括参考文档/任务文档):
文档验证重点
CLAUDE.md
指令符合既定目标,无无关内容
docs/README.md
导航范围正确,描述相关
docs/documentation_standards.md
标准适用于当前项目类型
docs/principles.md
原则与项目架构相关
docs/project/requirements.md
需求范围完整,无过时内容
docs/project/architecture.md
架构范围覆盖所有层级
docs/project/tech_stack.md
技术栈范围与项目实际情况匹配
docs/project/api_spec.md
API范围覆盖所有端点组
docs/project/database_schema.md
数据库架构范围覆盖所有实体
docs/project/design_guidelines.md
设计范围覆盖所有活跃组件
docs/project/runbook.md
运行手册范围覆盖搭建与运维操作
排除范围:
docs/tasks/
,
docs/reference/
,
docs/presentation/
,
tests/

Inputs (from Coordinator)

输入参数(来自协调器)

MANDATORY READ: Load
shared/references/audit_worker_core_contract.md
.
Receives from coordinator per invocation:
FieldDescription
doc_path
Path to document to audit (e.g.,
docs/project/architecture.md
)
output_dir
Directory for report output (from contextStore)
project_root
Project root path
tech_stack
Detected technology stack
必读: 加载
shared/references/audit_worker_core_contract.md
每次调用从协调器接收以下参数:
字段描述
doc_path
待审核文档的路径(例如:
docs/project/architecture.md
output_dir
报告输出目录(来自contextStore)
project_root
项目根目录路径
tech_stack
检测到的技术栈

Workflow

工作流程

Phase 1: SCOPE EXTRACTION

阶段1:SCOPE提取

  1. Read document first 20 lines
  2. Parse
    <!-- SCOPE: ... -->
    comment
  3. If no SCOPE tag, infer from document type (see Verification Rules)
  4. Record stated purpose/boundaries
  1. 读取文档前20行
  2. 解析
    <!-- SCOPE: ... -->
    注释
  3. 如果没有SCOPE标签,根据文档类型推断(见验证规则)
  4. 记录既定目标与边界

Phase 2: CONTENT-SCOPE ALIGNMENT

阶段2:内容-范围一致性校验

Analyze document sections against stated scope:
CheckFinding Type
Section not serving scopeOFF_TOPIC
Scope aspect not coveredMISSING_COVERAGE
Excessive detail beyond scopeSCOPE_CREEP
Content duplicated elsewhereSSOT_VIOLATION
Scoring:
  • 10/10: All content serves scope, scope fully covered
  • 8-9/10: Minor off-topic content or small gaps
  • 6-7/10: Some sections not aligned, partial coverage
  • 4-5/10: Significant misalignment, major gaps
  • 1-3/10: Document does not serve its stated purpose
对照既定范围分析文档各章节:
检查项问题类型
章节不符合范围OFF_TOPIC
范围要求未覆盖MISSING_COVERAGE
超出范围的冗余细节SCOPE_CREEP
内容在其他位置重复SSOT_VIOLATION
评分标准:
  • 10/10:所有内容符合范围,范围完全覆盖
  • 8-9/10:少量无关内容或小范围缺失
  • 6-7/10:部分章节不符合,覆盖不完整
  • 4-5/10:严重不符合,大范围缺失
  • 1-3/10:文档未实现其既定目标

Phase 3: SCORING & REPORT

阶段3:评分与报告

Calculate final score based on scope alignment:
overall_score = weighted_average(coverage, relevance, focus)
Coverage: how completely the scope is addressed. Relevance: how much content serves the scope. Focus: absence of off-topic content.
根据范围一致性计算最终分数:
overall_score = weighted_average(coverage, relevance, focus)
覆盖度:范围要求的完成程度。相关性:内容对范围的服务程度。聚焦度:无关内容的缺失程度。

Scoring Algorithm

评分算法

MANDATORY READ: Load
shared/references/audit_worker_core_contract.md
and
shared/references/audit_scoring.md
.
必读: 加载
shared/references/audit_worker_core_contract.md
shared/references/audit_scoring.md

Output Format

输出格式

MANDATORY READ: Load
shared/references/audit_worker_core_contract.md
and
shared/templates/audit_worker_report_template.md
.
Write report to
{output_dir}/612-semantic-{doc-slug}.md
where
doc-slug
is derived from document filename (e.g.,
architecture
,
tech_stack
,
claude_md
).
With
category: "Semantic Content"
and checks: scope_alignment.
Return summary to coordinator:
Report written: docs/project/.audit/ln-610/{YYYY-MM-DD}/612-semantic-architecture.md
Score: X.X/10 | Issues: N (C:N H:N M:N L:N)
必读: 加载
shared/references/audit_worker_core_contract.md
shared/templates/audit_worker_report_template.md
将报告写入
{output_dir}/612-semantic-{doc-slug}.md
,其中
doc-slug
由文档文件名派生(例如:
architecture
,
tech_stack
,
claude_md
)。
报告需包含
category: "Semantic Content"
和检查项:scope_alignment。
向协调器返回摘要:
Report written: docs/project/.audit/ln-610/{YYYY-MM-DD}/612-semantic-architecture.md
Score: X.X/10 | Issues: N (C:N H:N M:N L:N)

Critical Rules

核心规则

MANDATORY READ: Load
shared/references/audit_worker_core_contract.md
.
  • Read before judge: Always read full document before reporting issues
  • Scope inference: If no SCOPE tag, use document filename to infer expected scope
  • No false positives: Better to miss an issue than report incorrectly
  • Location precision: Always include line number for findings
  • Actionable fixes: Every finding must have concrete fix suggestion
  • No fact-checking: Do NOT verify paths, versions, endpoints against code
必读: 加载
shared/references/audit_worker_core_contract.md
  • 先阅读再判断: 报告问题前务必通读完整文档
  • 范围推断: 如果没有SCOPE标签,使用文档文件名推断预期范围
  • 避免误报: 宁可遗漏问题也不要错误报告
  • 位置精准: 所有问题必须包含行号
  • 可执行修复建议: 每个问题都要有具体的修复建议
  • 不做事实校验: 请勿针对代码验证路径、版本、端点等信息

Definition of Done

完成标准

MANDATORY READ: Load
shared/references/audit_worker_core_contract.md
.
  • Document read completely
  • SCOPE extracted or inferred
  • Content-scope alignment analyzed (OFF_TOPIC, MISSING_COVERAGE, SCOPE_CREEP, SSOT_VIOLATION)
  • Score calculated using penalty algorithm
  • Report written to
    {output_dir}/612-semantic-{doc-slug}.md
    (atomic single Write call)
  • Summary returned to coordinator
必读: 加载
shared/references/audit_worker_core_contract.md
  • 已完整阅读文档
  • 已提取或推断SCOPE
  • 已分析内容-范围一致性(OFF_TOPIC、MISSING_COVERAGE、SCOPE_CREEP、SSOT_VIOLATION)
  • 已使用惩罚算法计算分数
  • 已将报告写入
    {output_dir}/612-semantic-{doc-slug}.md
    (原子单次写入操作)
  • 已向协调器返回摘要

Reference Files

参考文件

  • Audit output schema:
    shared/references/audit_output_schema.md

Version: 2.0.0 Last Updated: 2026-03-01
  • 审核输出 schema:
    shared/references/audit_output_schema.md

版本: 2.0.0 最后更新: 2026-03-01