excel-data-quality-check-basic
Skill1 starsChanged 4 months agoMITView on GitHub
Perform a read-only spreadsheet data-quality audit that reports missing values, duplicates, types, formats, anomalies, and source-traceability issues without cleaning, standardizing, filling, deduplicating, overwriting, or generating a modified copy. Use for requests to check, audit, or list data-quality problems; use spreadsheet-data-cleaning when the user requests transformations, fixes, or a cleaned output. 对表格执行只读数据质量审计,报告缺失、重复、类型、格式、异常和来源可追溯性问题,不清洗、标准化、填补、去重、覆盖或生成修改后的副本。用于检查、审计或列出数据质量问题;用户要求转换、修复或输出清洗结果时使用 spreadsheet-data-cleaning。
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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
- Distinctive: line 14
Do not include finance or investment advice.
- Distinctive: line 15
Do not infer business meaning without source evidence.
- Distinctive: line 16
Do not clean, standardize, fill, deduplicate, overwrite, or generate a modified spreadsheet copy.
- Distinctive: line 21
Use this Skill for requests to check, audit, or list missing values, duplicates, types, formats, and anomalies without changing data.
- Very specific: line 22
Use spreadsheet-data-cleaning when the user asks to clean, normalize, transform, repair, fill, deduplicate, or create a cleaned output.
- Very specific: line 23
If a request starts as an audit but asks for changes, do not apply them.
- Distinctive: line 24
When spreadsheet tools are unavailable, report what cannot be inspected and do not claim that a data-quality check was completed.
- Distinctive: line 29
Check missing values, duplicate rows, inconsistent formats, impossible values, and mixed units.
- Distinctive: line 30
Check whether key fields and source fields are present.
≈ “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.
Files
English
Basic Excel Data Quality Check
Perform a read-only spreadsheet data-quality audit using generic public-safe rules.
Safety Boundary
- Do not include finance or investment advice.
- Do not infer business meaning without source evidence.
- Do not clean, standardize, fill, deduplicate, overwrite, or generate a modified spreadsheet copy.
- Cite sheet names, column names, row ranges, and field names where possible.
Routing Boundary
- Use this Skill for requests to check, audit, or list missing values, duplicates, types, formats, and anomalies without changing data.
- Use
spreadsheet-data-cleaningwhen the user asks to clean, normalize, transform, repair, fill, deduplicate, or create a cleaned output. - If a request starts as an audit but asks for changes, do not apply them; hand the modification task to
spreadsheet-data-cleaning. - When spreadsheet tools are unavailable, report what cannot be inspected and do not claim that a data-quality check was completed.
Workflow
- Identify workbook structure: sheets, tables, headers, dimensions, and data types.
- Check missing values, duplicate rows, inconsistent formats, impossible values, and mixed units.
- Check whether key fields and source fields are present.
- Summarize data quality risks and manual confirmation items.
- Suggest safe next steps without applying changes or generating a modified file.
Output Format
- Workbook overview
- Sheet and field inventory
- Data quality findings
- Evidence references
- Suggested next steps not applied
- Manual confirmation items
简体中文
Excel 数据质量基础检查
使用通用、公开安全的规则执行只读表格数据质量审计。
安全边界
- 不包含财务或投资建议。
- 没有来源证据时不推断业务含义。
- 不清洗、标准化、填补、去重、覆盖或生成修改后的表格副本。
- 尽量引用工作表名称、列名、行范围和字段名。
路由边界
- 用户要求在不改变数据的前提下检查、审计或列出缺失、重复、类型、格式和异常时使用本 Skill。
- 用户要求清洗、规范化、转换、修复、填补、去重或生成清洗结果时使用
spreadsheet-data-cleaning。 - 如果请求先要求审计又要求修改,不在本 Skill 中执行修改;把修改任务转交
spreadsheet-data-cleaning。 - 表格工具不可用时报告无法检查的内容,不得声称已完成数据质量检查。
工作流程
- 识别工作簿结构:工作表、表格、表头、维度和数据类型。
- 检查缺失值、重复行、格式不一致、不可能值和单位混用。
- 检查关键字段和来源字段是否存在。
- 总结数据质量风险和人工确认项。
- 建议安全后续步骤,但不应用修改或生成修改后的文件。
输出格式
- 工作簿概览
- 工作表和字段清单
- 数据质量问题
- 证据来源
- 未执行的建议后续步骤
- 人工确认项
In this repository40 other files it gives its agents.
- api-contract-reviewSkill
- architecture-decision-recordSkill
- architecture-deepening-analysisSkill
- bug-root-cause-analysisSkill
- change-impact-analysisSkill
- ci-failure-diagnosisSkill
- configuration-auditSkill
- content-consistency-checkSkill
- database-migration-reviewSkill
- dead-code-verificationSkill
- decision-prototypeSkill
- dependency-upgrade-analysisSkill
- documentation-syncSkill
- document-reviewSkill
- feature-implementationSkill
- meeting-notes-to-actionsSkill
- pdf-review-basicSkill
- pdf-reviewSkill
- performance-regression-analysisSkill
- presentation-outlineSkill
- project-health-checkSkill
- release-readiness-checkSkill
- repo-doctor-routerSkill
- repo-onboardingSkill
- report-writerSkill
- requirements-clarificationSkill
- requirements-to-specSkill
- research-briefSkill
- safe-change-planSkill
- safe-code-reviewSkill
- safe-fix-implementationSkill
- safe-test-implementationSkill
- security-focused-reviewSkill
- session-handoffSkill
- skill-authoringSkill
- skill-quality-auditSkill
- spec-to-work-itemsSkill
- spreadsheet-data-cleaningSkill
- test-gap-analysisSkill
- word-document-review-basicSkill
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
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.

