CtrlK
BlogDocsLog inGet started
Tessl Logo

large-file-kpi-analysis

根据数据量自动选择读取策略(大文件转Parquet),提取关键指标进行单位一致性验证与排序分析,并输出可下载的结果表格。

56

Quality

65%

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-analysis/kpi-metric-analysis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 body is lean, actionable, and well-structured with a clear parent-reference, but the two-step workflow lacks an explicit validation checkpoint and error-recovery loop before writing the batch output file.

Suggestions

Add an explicit validation checkpoint between Step1 and Step2 (e.g., confirm result_df is non-empty and the unit-consistency pass rate is acceptable before saving) plus an error-recovery loop, since this writes a batch output file.

Make the code copy-paste ready by including `import pandas as pd` and showing how `data` is obtained, or state explicitly that these are supplied by the parent workflow.

Replace the placeholder column names with one concrete worked example (real columns and sample values) so the executable path is unambiguous.

DimensionReasoningScore

Conciseness

Mostly lean code with a brief orienting note and no padding about Parquet/pandas; minor redundant labeling comments ('# 确定最终输出的数据框', '# 生成下载链接') could be trimmed.

4 / 5

Actionability

Concrete pandas code with real methods (sort_values, to_excel), but it uses placeholder columns ('numerator_col', 'group_col') and assumes `data`/`pd` already exist, leaving minor gaps for copy-paste use.

4 / 5

Workflow Clarity

A clear Step1→Step2 sequence exists and Step1 has an internal unit-consistency check, but there is no workflow-level validation checkpoint or error-recovery loop before the batch file write, which caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Under ~50 lines and single-purpose, with well-organized Step1/Step2 sections and a clearly signaled one-level reference to 'the parent workflow SKILL.md'; no external bundle files are needed.

5 / 5

Total

16

/

20

Passed

Description

58%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 conveys a specific, multi-action capability but omits any invocation guidance, so it answers 'what' without 'when'. Trigger-term coverage is relevant but misses the natural user phrasings and the input file format.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when analyzing Excel data, verifying engineering quantity units, or ranking business indicators') to provide invocation guidance and raise completeness.

Include natural user-facing keywords and the input file format (Excel/.xlsx, 表格, 数据分析) so users' phrasings match the description.

Name the domain explicitly (e.g., structural/engineering quantity analysis) to sharpen distinctiveness and reduce overlap with generic data-analysis skills.

DimensionReasoningScore

Specificity

Lists several concrete actions ('自动选择读取策略', '大文件转Parquet', '单位一致性验证', '排序分析', '输出可下载的结果表格'), though '提取关键指标' and '排序分析' stay somewhat generic within the niche.

4 / 5

Completeness

The 'what' is clear and detailed, but there is no 'when' — no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guideline.

3 / 5

Trigger Term Quality

Relevant domain keywords appear (Parquet, 关键指标, 单位一致性验证, 排序) but the most natural user terms and the actual input format (Excel/表格/.xlsx) are missing, and the phrasing describes mechanism rather than user need.

3 / 5

Distinctiveness Conflict Risk

The unit-consistency-verification plus downloadable-table combination is a reasonably distinct niche, though '提取关键指标'/'排序分析' could still overlap with general data-analysis skills.

4 / 5

Total

14

/

20

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 missing

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.