CtrlK
BlogDocsLog inGet started
Tessl Logo

invalid-data-cleaning

用于大规模Excel数据的预处理,通过统计总行数判断是否转换为Parquet格式以提升读写效率,并使用正则表达式清洗指定文本列(如仅保留中文字符),最后导出清洗后的文件并提供下载链接。

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/sn-da-excel-workflow/capability/excel-data-cleaning/invalid-data-cleaning/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content provides concrete, executable code in a clean three-step structure suited to a simple skill, but the described row-count decision logic is not implemented and the pipeline lacks validation checkpoints for its destructive cleaning step.

Suggestions

Implement the row-count threshold described in Step1 (e.g. only convert to Parquet when row count exceeds a stated value) so the code matches the stated workflow.

Add a validation checkpoint after cleaning — e.g. print a few sample values or a before/after non-null count — to confirm the regex cleaning worked before exporting.

Drop inline comments that merely restate the following line (such as the Parquet read/write comments) to tighten token efficiency.

DimensionReasoningScore

Conciseness

The body is mostly efficient with brief step instructions and code, but inline comments restate what the code already shows (e.g. "# 读取 Parquet 文件用于后续处理" above `df = pd.read_parquet`) and the closing print statements are illustrative rather than necessary, so it could be tightened.

2 / 3

Actionability

Each step ships fully executable pandas/re code with real imports and operations; the single placeholder `target_col = 'target_column'` is explicitly flagged with "替换为实际需要清洗的列名", which justifies the flexibility rather than leaving pseudocode.

3 / 3

Workflow Clarity

The three steps are clearly sequenced, but Step1 describes a conditional "根据总行数判断是否数据量过大" that the code does not implement (it converts unconditionally), and there are no validation checkpoints for the destructive/batch cleaning and write operations, which caps workflow clarity at 2.

2 / 3

Progressive Disclosure

This is a simple, single-purpose skill under 50 lines with no external bundle files needed; its sections are well-organized and the parent-workflow reference ("see the parent workflow SKILL.md") is clearly signaled one level deep, satisfying the simple-skill allowance for a top score.

3 / 3

Total

10

/

12

Passed

Description

60%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and action-oriented but lacks an explicit use-when trigger clause and leans on technical jargon, capping completeness and trigger-term quality. It is moderately distinctive thanks to its Parquet-plus-Chinese-regex niche.

Suggestions

Add an explicit trigger clause such as 'Use when cleaning or preprocessing large Excel files, especially text columns that must keep only Chinese characters.'

Soften technical jargon by pairing 'Parquet格式' and '正则表达式' with natural user phrasing like 'convert to Parquet for speed' and 'clean text columns'.

Sharpen distinctiveness by leading with the unique capability (Chinese-character text cleaning of large Excel data) rather than the generic '数据预处理' framing.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — "统计总行数判断是否转换为Parquet格式", "使用正则表达式清洗指定文本列(如仅保留中文字符)", and "导出清洗后的文件并提供下载链接" — matching the anchor that lists several specific actions rather than naming only a domain.

3 / 3

Completeness

It clearly states what the skill does (preprocess, convert, clean, export), but there is no "Use when..." or equivalent explicit trigger guidance; per the rubric guidelines a missing when-clause caps completeness at 2.

2 / 3

Trigger Term Quality

It includes some relevant keywords users might say ("Excel数据", "清洗"), but leans technical with "Parquet格式" and "正则表达式" and omits common natural variations and trigger phrasing, so coverage is partial rather than comprehensive.

2 / 3

Distinctiveness Conflict Risk

The Parquet-conversion plus Chinese-character-regex combination is a specific niche, yet the broad framing "大规模Excel数据的预处理" could overlap with general Excel skills and there are no explicit distinct triggers, so conflict risk remains moderate.

2 / 3

Total

9

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
OpenSenseNova/SenseNova-Skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.