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

80%

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

The body is concise and highly actionable with executable, placeholder-annotated code, but it lacks explicit validation checkpoints in its workflow and keeps all content in a single monolithic file. Adding a verification step and optionally splitting the dashboard panel would raise the two lower dimensions.

Suggestions

Add an explicit validation checkpoint between steps, e.g. after extraction assert that df_clean[numeric_col] is non-empty and within an expected range before plotting.

Consider moving the large 2x2 dashboard panel (Step3) into a referenced script or reference file so SKILL.md stays a lean overview pointing one level deep.

Include a brief error-recovery note (e.g. what to do if value_counts is empty or all conversions fail) to close the feedback loop.

DimensionReasoningScore

Conciseness

The body is lean code with brief step headers and only purposeful comments (font config, placeholder examples); it assumes Claude's competence and does not explain what a histogram or pandas is, matching the 'lean and efficient; every token earns its place' anchor.

3 / 3

Actionability

All three steps provide complete, executable Python with imports, a real extraction function, and clearly-marked '占位示例' placeholders, making it copy-paste ready rather than pseudocode — the score-3 anchor.

3 / 3

Workflow Clarity

The three steps are clearly sequenced and Step1 filters failed conversions, but there are no explicit validation checkpoints or an error-recovery feedback loop, fitting 'steps listed but validation gaps; checkpoints missing or implicit' below the score-3 bar.

2 / 3

Progressive Disclosure

Content is well-organized into three labeled steps with no nested references, but it is a monolithic single file over 50 lines with all code inline and no external references, matching 'some structure but could be better organized; content that should be separate is inline'.

2 / 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 concrete and specific about actions and outputs, but omits an explicit trigger clause, which caps both completeness and distinctiveness. Adding a 'Use when...' sentence with natural user phrasing would lift the weaker dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to analyze the distribution of numeric data extracted from unit-bearing strings, or requests histograms/pie/bar/cumulative-distribution charts.'

Include natural user-facing terms like '数据分布可视化' and '分布分析' alongside the chart-type names to broaden trigger coverage.

Tighten distinctiveness by leading with the niche (unit-string numeric extraction) so it reads as a specialized data-cleaning+viz skill rather than a general plotting tool.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '提取数值并清洗' and generating '直方图、饼图、条形图和累积分布图' — matching the score-3 anchor of multiple specific concrete actions rather than the single-action score-2 example.

3 / 3

Completeness

The 'what' is clearly stated, but 'when' is only implied via the purpose clause '用于展示数据的集中趋势与分布特征'; per the judging guidelines a missing explicit 'Use when...' trigger caps completeness at 2.

2 / 3

Trigger Term Quality

Chart-type names (直方图/饼图/条形图) and '分布' are natural user terms, but there is no 'Use when...' clause and common variations like '数据分布可视化' are missing, so it lands at 'some relevant keywords but missing common variations' rather than full coverage.

2 / 3

Distinctiveness Conflict Risk

The unit-string extraction niche is fairly specific, but the distribution-visualization half overlaps with general charting skills, so it is 'somewhat specific but could still overlap with similar skills' rather than a conflict-free niche.

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.