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。。

55

Quality

62%

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%

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

The skill provides concrete, mostly executable code across a clear three-step sequence, but it relies on assumed placeholder columns without context and lacks validation checkpoints for its destructive/batch operations.

Suggestions

Replace placeholder column names with guidance on detecting real columns, or show how to inspect df.columns first so the code is executable on actual files.

Add validation/verification steps — e.g. confirm ffill did not corrupt data, check row counts before/after filtering, and verify cross-table differences before reporting — to satisfy the destructive/batch feedback-loop requirement.

Add a short overview line at the top and consider moving the styling/visualization details to a reference file so the SKILL.md body stays a navigable overview.

DimensionReasoningScore

Conciseness

The body is lean and code-forward with brief step labels and inline comments; it does not pad with concepts Claude already knows, so every section earns its place.

3 / 3

Actionability

The code is concrete but not copy-paste ready: it relies on placeholder column names (group_col, category_col, status_col, Red/Green/Blue) and an undefined df_dict/pd context, leaving key details missing.

2 / 3

Workflow Clarity

Steps are sequenced (Step1/Step2/Step3), but the workflow involves destructive and batch operations (ffill overwrites, row filtering, multi-sheet processing) with no validation or verification checkpoints, capping clarity at 2.

2 / 3

Progressive Disclosure

The content is organized into three steps but is a monolithic inline body over 50 lines with no overview and no external references, so structure is present but not well split for navigation.

2 / 3

Total

9

/

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 clearly states several concrete capabilities on a defined domain but omits any explicit "Use when..." trigger guidance and lacks common keyword variations, leaving the "when to use" half unanswered.

Suggestions

Add an explicit trigger clause, e.g. 'Use when cleaning multi-sheet Excel files, reconciling data across worksheets, or generating visual summaries from .xlsx workbooks.'

Include natural keyword variations users would say — Excel, spreadsheet, workbook, .xlsx, worksheet — to improve trigger coverage.

Fix the trailing double period (。。) typo for a cleaner description.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "智能清洗", "跨表核对", "可视化分析" — on a defined domain (multi-sheet Excel), matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

It answers "what" (cleaning, reconciliation, visualization) but provides no "Use when..." trigger clause, so per the judging guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

It includes natural terms users would say ("Excel", "Sheet") but misses common variations like .xlsx, spreadsheet, or workbook, so coverage is partial rather than comprehensive.

2 / 3

Distinctiveness Conflict Risk

The multi-sheet Excel + cross-table reconciliation framing is somewhat specific, but general Excel/data-analysis skills could still overlap with these triggers.

2 / 3

Total

9

/

12

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.