CtrlK
BlogDocsLog inGet started
Tessl Logo

numeric-extraction-and-distribution-analysis

从带单位的字符串列中提取数值并清洗,生成包含直方图、饼图、条形图和累积分布图的多维度综合分布可视化图表,用于展示数据的集中趋势与分布特征。

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-conditional-formatting/data-bar-formatting/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a clean, code-forward, well-sequenced data-analysis skill with concrete executable examples and no unnecessary reference nesting; its main gaps are an assumed (undefined) input DataFrame, no explicit validation feedback loop, and the absence of a brief overview section.

Suggestions

Add a short overview or quick-start section noting the assumed input (a pandas DataFrame `df` with a unit-bearing string column) so the code is fully self-contained.

Add an explicit validation/checkpoint note in Step1 (e.g. report how many rows failed unit conversion before dropping) to strengthen the feedback loop.

Trim obvious inline comments that restate the following line (e.g. '# 绘制直方图') to push conciseness toward 5.

DimensionReasoningScore

Conciseness

The body is code-forward and mostly lean, with one-line Chinese step descriptions; a few inline comments restate the obvious ('# 绘制直方图' before plt.hist, font-config rationale), which is minor over-explanation that could be trimmed but not enough to drop to 3.

4 / 5

Actionability

Each step provides concrete, executable pandas/numpy/matplotlib code with real calls and placeholders for column/unit names; the gap is that `df` is assumed to already exist with no loading step shown, so it is mostly rather than fully copy-paste ready.

4 / 5

Workflow Clarity

Three steps are clearly sequenced (extract/clean → basic histogram → comprehensive dashboard) and Step1 includes light validation via dropna/try-except on failed conversions; not a destructive or batch operation so the cap does not apply, but there is no explicit validate-then-recover checkpoint, keeping it at 4 rather than 5.

4 / 5

Progressive Disclosure

No bundle files exist and the content is self-contained, well-organized into three labeled steps with headers and no nested references; at ~100 lines with no overview/quick-start section it slightly exceeds the under-50-line simple-skill exception, so minor organization gaps hold it at 4.

4 / 5

Total

16

/

20

Passed

Description

66%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 concrete with good natural trigger terms and a distinct niche, but it lacks an explicit 'Use when...' trigger clause, stating purpose rather than when-to-use guidance, which caps completeness at 3.

Suggestions

Add an explicit trigger clause such as 'Use when the user wants to analyze the distribution of numeric values extracted from unit-bearing strings, or asks for distribution/histogram/pie/bar/cumulative charts.'

Include a few natural synonyms and variations (e.g. 频数分布, 统计图, 数据分布分析) to broaden trigger coverage toward a 5.

Consider stating the input expectation (a pandas DataFrame with a unit-bearing string column) to sharpen distinctiveness from generic plotting skills.

DimensionReasoningScore

Specificity

Lists several concrete actions ('提取数值并清洗', '生成...直方图、饼图、条形图和累积分布图'), naming four distinct chart types; falls just short of the comprehensive 5-anchor since the actions group into extract-and-clean plus a single generate-visualization action.

4 / 5

Completeness

The 'what' is explicit and concrete, but there is no 'Use when...' trigger clause; the trailing '用于展示数据的集中趋势与分布特征' states purpose/intent rather than explicit when-to-use guidance, so completeness is capped at 3 per the missing-trigger guideline.

3 / 5

Trigger Term Quality

Good coverage of natural Chinese terms a user would say ('分布', '可视化图表', '直方图', '饼图', '条形图', '累积分布图', '集中趋势'); a few synonyms/extensions (e.g. 频数分布, 统计图, file extensions) are missing, keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

The combination of unit-string extraction plus a specific multi-chart distribution dashboard is a clear niche with low conflict risk, but the broad 'distribution visualization' framing has minor overlap potential with general data-viz/plotting skills.

4 / 5

Total

15

/

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.

Validation — 16 / 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.