CtrlK
BlogDocsLog inGet started
Tessl Logo

excel-smart-analysis-and-cleaning

对多 Sheet Excel 进行智能清洗、跨表核对与可视化分析。。

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-cleaning/missing-value-handling/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 provides actionable, mostly executable code across a clear three-step pipeline, but it lacks validation checkpoints for batch/destructive operations and is a monolithic inline file with no headers or referenced bundles. It is competent but would benefit from structure and error-handling guidance.

Suggestions

Add validation checkpoints (e.g., assert expected columns exist, print row-count deltas before/after filtering, verify reconciliation tolerances) so the batch row-dropping and cross-sheet checks are guarded.

Use real markdown headers (## Step 1 — Cleaning) instead of plain 'Step1' lines, and add the missing `import pandas as pd` so code is copy-paste runnable.

Replace brittle placeholder column names with a short documented schema assumption block, or move the verbose styling/visualization code into a referenced file once bundle assets are added.

DimensionReasoningScore

Conciseness

The body is code-forward with terse Chinese prose and mostly earns its tokens; only minor comments and placeholder assumptions could be trimmed, fitting 'efficient; minor instances of over-explanation'.

4 / 5

Actionability

Each step ships concrete, mostly executable Python, but `pandas` (used as `pd`) is never imported and several placeholder column names ('group_col', 'category_col') require adaptation, matching 'mostly executable guidance; minor gaps'.

4 / 5

Workflow Clarity

Step1→Step2→Step3 are sequenced, but there are no validation/verification checkpoints and Step1 silently drops rows via `df = df[black_mask]`; per the batch/destructive guideline this caps workflow_clarity at 3.

3 / 5

Progressive Disclosure

At ~85 lines with all code inlined and no markdown section headers or references, it has step structure but is not well organized or split; it exceeds the simple-skill (<50 line) exception, fitting anchor 3.

3 / 5

Total

14

/

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 clearly states what the skill does across three concrete capabilities for multi-sheet Excel, but it lacks any 'Use when' trigger guidance and misses file-extension/synonym keywords. It is reasonably specific and distinct but not maximally discoverable.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user provides multi-sheet Excel files (.xlsx) needing cleaning, cross-sheet reconciliation, or visualization.'

Include natural keyword variants and file extensions such as 'Excel', '.xlsx', 'spreadsheet', '工作簿' to improve trigger-term coverage.

Drop the duplicated trailing period ('。。') and replace the vague '智能' with the specific techniques used (ffill, regex, RGB filtering) to sharpen specificity.

DimensionReasoningScore

Specificity

Names the domain ('多 Sheet Excel') and three concrete actions ('智能清洗、跨表核对与可视化分析'), matching the 'several specific actions; minor gaps' anchor; not 5 because '智能' is slightly vague and coverage is not comprehensive.

4 / 5

Completeness

The 'what' is clear (cleaning, reconciliation, visual analysis on multi-sheet Excel) but there is no 'Use when...' or equivalent trigger clause, so per the guideline completeness is capped at 3.

3 / 5

Trigger Term Quality

Contains natural terms a user would say ('Excel', 'Sheet', '清洗', '核对', '可视化') but misses the .xlsx extension and synonyms like 'spreadsheet'/'表格', fitting 'good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

The multi-sheet Excel cleaning/reconciliation/visualization niche is mostly distinct with only minor overlap risk against general data-analysis skills, matching anchor 4; not 5 because overlap with generic Excel/data skills remains.

4 / 5

Total

15

/

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.