CtrlK
BlogDocsLog inGet started
Tessl Logo

pivot-table-cross-analysis

利用交叉表与热力图对分类数据进行多维度占比分析,适用于奖项分布、绩效评估或市场占有率等结构化数据的清洗与可视化。

59

Quality

67%

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/pivot-table-analysis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 an efficient, actionable five-step Python pipeline with concrete code, but it lacks validation/verification checkpoints for its batch and file-writing operations, which caps workflow clarity, and offers no orchestration example tying the functions together.

Suggestions

Add validation checkpoints between steps — e.g. assert crosstab row/col sums, verify no unexpected NaNs after dropna, and confirm the Excel file was written — to lift workflow clarity above 3.

Include a short orchestration example showing how to chain preprocess → crosstab → heatmap → insights → export so the functions are immediately runnable end-to-end.

Move the Jupyter-specific FileLink export behind a fallback (or note the environment assumption) so the export step is executable in non-notebook contexts.

DimensionReasoningScore

Conciseness

The body is lean — five short step descriptions each paired with a focused code block, and code comments highlight techniques ('关键技巧:处理合并单元格', '关键技巧:中文字体配置') rather than explaining basic concepts — though a few explanatory comments like 'div(axis=1) 表示按列求和后进行除法' could be trimmed.

4 / 5

Actionability

Five complete, copy-paste-ready Python functions with imports cover the common pipeline (preprocess, crosstab, heatmap, insights, export), but there is no orchestration example chaining them and export relies on IPython FileLink, which are minor gaps.

4 / 5

Workflow Clarity

Steps are clearly sequenced Step1–Step5, but this batch data pipeline (dropna silently dropping rows, overwriting Excel output) has no validation checkpoints or error-recovery feedback loops, so workflow clarity is capped at 3 per the destructive/batch guideline.

3 / 5

Progressive Disclosure

Content is well-organized into five labeled step sections and is appropriately self-contained with no external references needed; it sits just over the simple-skill line, so structure is good but not the ideal clear-overview-with-one-level-references pattern.

4 / 5

Total

15

/

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 third-person, naming concrete techniques and natural trigger scenarios, but it lacks an explicit 'Use when...' trigger clause and omits common synonyms/file extensions, which caps completeness and trigger coverage.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g. 'Use when analyzing award distributions, performance evaluations, or market share from Excel files') to raise completeness above 3.

Include common synonyms and file extensions such as 'Excel', '.xlsx', '交叉分析表', and '占比/比例' to broaden natural trigger-term coverage.

Enumerate the full workflow in the description (clean → crosstab → visualize → rank → export) so capabilities read as comprehensive rather than partial.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — '利用交叉表与热力图...多维度占比分析' and '清洗与可视化' — giving specific techniques rather than vague language, though coverage of the full workflow (e.g. export) is implied rather than enumerated.

4 / 5

Completeness

The 'what' is clear (crosstab/heatmap proportion analysis, cleaning, visualization), but the 'when' is only weakly implied via '适用于...等结构化数据' rather than an explicit 'Use when...' trigger clause, capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Includes natural domain phrases users would say — '交叉表', '热力图', '奖项分布', '绩效评估', '市场占有率' — with good coverage, though common synonyms and file extensions (Excel, .xlsx) are missing.

4 / 5

Distinctiveness Conflict Risk

The crosstab-plus-heatmap proportion-analysis niche with concrete use cases (awards, performance, market share) is mostly distinct from generic data skills, with only minor overlap risk against broad spreadsheet-analysis 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.

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.