CtrlK
BlogDocsLog inGet started
Tessl Logo

excel-multi-sheet-threshold-analysis

统计多Sheet Excel总行数并根据规模选择处理策略,提取特定维度信息进行去重统计,并生成摘要与明细报表。

58

Quality

66%

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/duplicate-removal/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is a tight, fully executable four-step pandas workflow with good organization and no concept-explanation padding. Its main weakness is the absence of validation/verification checkpoints for a batch file-processing operation.

Suggestions

Add validation checkpoints after risky batch steps — e.g., assert `extracted_data` is non-empty before dedup, and confirm the exported files exist after `to_excel`.

Remove the duplicated `import pandas as pd` in Steps 2 and 4 and trim obvious restating-the-obvious comments to improve token efficiency.

Add minimal error handling around `pd.read_excel` (missing file / wrong sheet name) so the workflow fails fast with a clear message.

DimensionReasoningScore

Conciseness

Mostly efficient with short step labels and executable code, but `import pandas as pd` is repeated in Steps 2 and 4 and a few comments restate the obvious ('# 使用 set 进行高效去重', '# 转换为排序后的列表').

2 / 3

Actionability

All four steps provide fully executable, copy-paste-ready pandas code with concrete column indices, keyword lists, and output paths — no pseudocode or missing details.

3 / 3

Workflow Clarity

Steps are clearly sequenced (Step1–Step4) but this batch read/process/write operation has no validation or verification checkpoints (no check that exports succeeded, no empty-result guard), capping clarity at 2.

2 / 3

Progressive Disclosure

A simple under-50-line single-task skill with no external bundle files; content is cleanly organized into labeled steps with only a one-level pointer to the parent workflow SKILL.md.

3 / 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 specific and action-rich, naming several concrete operations, but it omits any explicit 'Use when...' trigger guidance, which limits its completeness and distinctiveness. Adding natural trigger phrasing would meaningfully raise the score.

Suggestions

Add an explicit 'Use when...' clause naming the user situations that should trigger this skill (e.g., when deduplicating rows across multiple Excel sheets or generating summary/detail reports from multi-sheet workbooks).

Broaden trigger terms with common natural variations users would actually say, such as '去重', '多表统计', 'Excel 汇总报表'.

Tighten distinctiveness by contrasting this sub-skill's scope against the parent workflow (which the body already references) directly in the description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '统计多Sheet Excel总行数', '根据规模选择处理策略', '提取特定维度信息进行去重统计', '生成摘要与明细报表' — going beyond naming a domain and some actions.

3 / 3

Completeness

Clearly answers 'what' with several actions but has no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the guidelines.

2 / 3

Trigger Term Quality

Contains relevant domain keywords ('多Sheet Excel', '去重统计', '摘要与明细报表') but lacks broad natural-term coverage and common variations a user would actually say.

2 / 3

Distinctiveness Conflict Risk

Targets a reasonably specific niche (multi-sheet dedup with threshold-based strategy) but could still overlap with generic Excel analysis skills absent distinct triggers.

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.