CtrlK
BlogDocsLog inGet started
Tessl Logo

excel-multi-sheet-dynamic-analysis

用于分析包含多个Sheet的Excel文件,动态判断数据量级以决定是否转换为Parquet进行大文件处理,并支持跨Sheet的特定字段统计、数据清洗、交叉分析与可视化,最终生成带下载链接的汇总报告。

60

Quality

70%

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-reading/specific-sheet-reading/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-5

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

The content is largely executable and concise, providing real working code for the analysis pipeline, but it lacks validation checkpoints for its batch file operations and has no markdown structure or overview to aid navigation. Adding verification steps and section headers would materially improve the two lowest dimensions.

Suggestions

Add explicit validation/verification checkpoints between steps — e.g., verify the saved Excel file opens correctly and confirm expected sheet names/row counts before declaring success — to satisfy the batch-operation feedback-loop requirement.

Introduce markdown section headers (e.g., '## Step 1: Locate target columns') and a brief one-line overview at the top so the workflow is skimmable and well-structured.

Implement (or explicitly gate) the dynamic Parquet conversion mentioned in the description, since the body currently omits it, to close the gap between promised and provided behavior.

DimensionReasoningScore

Conciseness

The body is almost entirely executable code with brief, useful inline comments (e.g., '占位示例', '合并单元格处理 ffill') and does not pad with explanations of concepts Claude already knows; the placeholder comments add minor noise that could be trimmed, placing it just below the lean/efficient anchor.

4 / 5

Actionability

It provides concrete, copy-paste-ready pandas/openpyxl/matplotlib code across all four steps, but relies on placeholder keywords ('占位示例', target_col_keyword) that the user must fill in and does not implement the dynamic Parquet conversion promised in the description, leaving minor gaps.

4 / 5

Workflow Clarity

The four steps are clearly sequenced (Step1–Step4), but the workflow performs batch Excel processing and file writing with no validation/verification checkpoints or error-recovery feedback loops; per the rubric, missing validation in batch/destructive operations caps workflow clarity at 3.

3 / 5

Progressive Disclosure

There are no bundle files and the content is a single ~154-line code block with no markdown section headers or overview — only inline 'Step1–Step4' labels — so structure exists but is not well organized and lacks an overview that would aid navigation.

3 / 5

Total

14

/

20

Passed

Description

75%Weight 40%Scale 1-5

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 distinct, covering a comprehensive set of concrete analysis actions, but it lacks an explicit 'Use when…' trigger clause, which caps its completeness and slightly limits trigger-term quality. Adding natural trigger phrasing and file extensions would lift both dimensions.

Suggestions

Add an explicit 'Use when…' clause naming concrete trigger scenarios (e.g., 'Use when analyzing multi-sheet Excel files, especially large ones requiring Parquet conversion, or when the user asks for cross-sheet statistics, data cleaning, or cross-analysis with visual reports').

Include natural synonyms and file extensions in the description, such as .xlsx, spreadsheets, and 表格, to broaden trigger-term coverage.

Consider adding a brief English gloss or trigger terms to improve discoverability for users who reference Excel files in English.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "动态判断数据量级以决定是否转换为Parquet", "跨Sheet的特定字段统计、数据清洗、交叉分析与可视化", "生成带下载链接的汇总报告" — providing comprehensive coverage of the skill's capabilities, matching the anchor for listing multiple specific concrete actions.

5 / 5

Completeness

It clearly answers 'what' the skill does but provides no 'Use when…' clause or equivalent explicit trigger guidance for 'when'; per the rubric, a missing use-when clause caps completeness at 3.

3 / 5

Trigger Term Quality

It includes good natural keywords (Sheet, Excel文件, Parquet, 字段统计, 数据清洗, 交叉分析, 可视化) but is missing common synonyms and file extensions such as .xlsx, spreadsheets, or 表格, so it falls between good coverage and comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The combination of multi-sheet Excel analysis, dynamic Parquet conversion, and cross-sheet statistical analysis carves a clear niche with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

17

/

20

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.