CtrlK
BlogDocsLog inGet started
Tessl Logo

text-normalization-and-large-file-processing

对Excel文件进行文本标准化清洗(如去除异常前缀、提取纯中文字符等),并,最终输出清洗后的Excel文件并提供下载链接。

57

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/text-normalization/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 body is a concise, mostly actionable two-step workflow with executable Python, but it is weakened by placeholder column names, a missing 'gc' import in Step2, and the absence of a validation checkpoint before saving the output.

Suggestions

Make the code fully executable by importing 'gc' in Step2 and showing how 'pd' and 'df' are obtained, or explicitly noting the assumed prerequisites.

Add a validation checkpoint in Step2 (e.g., verifying non-null counts or a quick head() check) before saving, to form a validate-then-save feedback loop.

Replace or clarify the placeholder column names ('需要转数字的文本列', '需要提取中文的列') with guidance on how to identify the correct columns dynamically.

DimensionReasoningScore

Conciseness

The body is lean and code-driven with brief functional step descriptions and no padding or explanation of concepts Claude already knows, matching the 'lean and efficient' anchor.

3 / 3

Actionability

Concrete executable functions are provided, but column names are placeholders requiring substitution and Step2 uses 'gc' without importing it, so the guidance is incomplete rather than fully copy-paste ready.

2 / 3

Workflow Clarity

A clear two-step sequence (clean then save/download) is present, but Step2 writes a persistent output with no validation checkpoint confirming the cleaned result is correct, which caps workflow clarity at 2.

2 / 3

Progressive Disclosure

No bundle files exist and the skill is short and single-purpose with clearly organized sections, so per the simple-skills note progressive disclosure can score 3 with well-organized sections alone.

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 clearly states concrete cleaning actions and outputs but lacks an explicit 'when to use' trigger clause and has a minor grammatical stutter ('并,最终'). It is reasonably specific yet could conflict with general Excel skills.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., when the user needs to clean or normalize text columns in Excel files).

Add common natural trigger terms users would actually say, such as 'Excel清洗', '中文提取', '数据标准化', '.xlsx'.

Fix the grammatical stutter '并,最终输出' to ',并最终输出' to improve readability and specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('去除异常前缀', '提取纯中文字符', '输出清洗后的Excel文件', '提供下载链接'), matching the anchor for several specific concrete actions.

3 / 3

Completeness

The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Relevant keywords like 'Excel文件', '文本标准化清洗', '中文字符', '下载链接' are present but common natural variations a user might say are missing, so it sits at 'some relevant keywords'.

2 / 3

Distinctiveness Conflict Risk

The text-normalization niche is somewhat specific but still overlaps with broader Excel-processing skills, so it could overlap with similar skills.

2 / 3

Total

9

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

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.