agentleFS
dss-timedss-time/repo-doctor-skills/skills/content-consistency-check/SKILL.md

content-consistency-check

Skill1 starsChanged 4 months agoMITView on GitHub

Compare one or more artifacts for conflicting terminology, figures, dates, units, people, versions, links, and conclusions, reporting both locations, severity, conflict type, and a recommended authority. Use when reconciliation across content is primary; use document-review for holistic quality of one document, and do not select a correct value without authoritative evidence or claim unsupported file-format checks. 对一个或多个材料中的术语、数字、日期、单位、人物、版本、链接和结论进行对照,报告冲突两侧位置、严重度、类型和建议权威基准。主要任务是跨内容核对时使用;单份文档整体质量应使用 document-review;没有权威证据时不得擅选正确值,也不得声称完成不受支持的文件格式检查。

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read references/productivity-evidence-and-file-safety.md and references/consistency-dimensions.md.

    line 10
  2. Distinctive:

    Create a normalized comparison layer for terms, figures, dates, units, identities, versions, links, and conclusions while preserving each …

    line 14
  3. Very specific:

    Use document-review when the request is primarily structure, logic, grammar, and completeness within one document.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

English

Content Consistency Check

Read references/productivity-evidence-and-file-safety.md and references/consistency-dimensions.md.

  1. Confirm the artifacts, comparison scope, authoritative sources if any, effective dates, and dimensions to compare.
  2. Inventory actual format capabilities. Extract only what available tools can support from Markdown, text, documents, spreadsheets, PDFs, or presentations; report inaccessible files, sheets, slides, pages, formulas, or visuals.
  3. Create a normalized comparison layer for terms, figures, dates, units, identities, versions, links, and conclusions while preserving each original value and location.
  4. Classify each difference as a true conflict, formatting-only difference, unit conversion, rounding difference, time-basis difference, version/effective-date difference, or unknown.
  5. Report both sides, context, impact, severity, confidence, and proposed authority. Do not silently choose the correct value; select one only when authoritative evidence establishes it.
  6. Summarize systemic patterns and a reconciliation sequence. Keep the source artifacts read-only.

Use document-review when the request is primarily structure, logic, grammar, and completeness within one document.

Output Contract

  1. Scope, artifact inventory, and capability status
  2. Conflict matrix with both locations and original values
  3. Conflict type, severity, impact, and confidence
  4. Recommended authority and evidence status
  5. Systemic patterns, unresolved items, and reconciliation order

简体中文

内容一致性检查

读取 references/productivity-evidence-and-file-safety.md 和 references/consistency-dimensions.md。

  1. 确认材料、比较范围、已有权威来源、生效日期和对比维度。
  2. 盘点真实格式能力;对 Markdown、文本、文档、表格、PDF 或演示材料只提取工具支持的内容,并报告不可访问的文件、工作表、幻灯片、页码、公式或视觉内容。
  3. 为术语、数字、日期、单位、人物、版本、链接和结论建立规范化比较层,同时保留原值和位置。
  4. 把差异分类为真实冲突、纯格式差异、单位换算、舍入差异、时间口径差异、版本/生效日期差异或未知。
  5. 报告冲突两侧、上下文、影响、严重度、置信度和建议权威基准;不得静默选择正确值,只有权威证据明确时才能选定。
  6. 总结系统性模式和协调顺序,保持原材料只读。

主要任务是单份文档的结构、逻辑、语法和完整性时使用 document-review。

输出契约

  1. 范围、材料清单和能力状态
  2. 含两侧位置与原值的冲突矩阵
  3. 冲突类型、严重度、影响和置信度
  4. 建议权威基准与证据状态
  5. 系统性模式、未解决项和协调顺序

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.