CtrlK
BlogDocsLog inGet started
Tessl Logo

excel-basic-statistics-and-routing

对多Sheet Excel文件进行基础统计与,支持按条件筛选计算均值,以及从指定行区间提取数据去重求和,并生成结果文件与下载链接。

50

Quality

55%

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-statistics/basic-statistics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The body delivers concrete, sequenced pandas code for the three capabilities, but it depends on undefined context variables and placeholders, silently swallows errors in Step2, and lacks explicit validation checkpoints, placing all dimensions at the mid level.

Suggestions

Define or document the expected context variables (df_analysis, total_rows, file_path) and replace hardcoded placeholders with clearly marked parameter inputs so the code is self-contained and copy-paste ready.

Replace bare 'except: pass' in Step2 with explicit error handling/reporting, and add a validate→fix→retry checkpoint before the batch Excel writes in Step3.

Deduplicate the two row-interval extraction blocks into a parameterized loop over (start, end, value_index) tuples to tighten conciseness.

DimensionReasoningScore

Conciseness

Mostly lean code with no concept-explanation fluff, but the two extraction blocks (区间1 '21-28行' and 区间2 '51-58行') are near-duplicate copy-paste that could be a single parameterized loop; not a 3 because of this avoidable repetition.

2 / 3

Actionability

Provides real, executable pandas code rather than pseudocode, but relies on undefined context variables (df_analysis, total_rows, file_path) and placeholder/hardcoded values ('# 占位示例', fixed row ranges, iloc indices), so it is not copy-paste ready; not a 1 because the code is concrete and runnable in form.

2 / 3

Workflow Clarity

Three steps are clearly sequenced and Step1 includes column/type validation, but Step2 uses bare 'except: pass' that silently swallows errors, the 'if total_rows < 10000' guard references an undefined variable, and there are no explicit validate→fix→retry checkpoints for the batch writes; not a 3 per the batch-operation feedback-loop cap.

2 / 3

Progressive Disclosure

Content is organized into three labeled steps with one clearly signaled parent-workflow reference (the blockquote), but there is no overview section and all code is inline in a single ~100-line file with no bundle to offload detail to; not a 1 because steps are organized and the parent reference is signaled.

2 / 3

Total

8

/

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 concretely names several specific Excel capabilities in third person, but it lacks any explicit 'Use when' trigger guidance and contains a grammatical slip ('基础统计与,'), leaving completeness and trigger quality at the mid level.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when computing conditional averages or extracting/deduplicating values from specific row ranges in multi-sheet Excel files') to raise completeness and distinctiveness.

Fix the dangling '基础统计与,' and broaden trigger terms to include common variations users would say (e.g., '平均值', '.xlsx', '汇总', '分组统计').

The name '...routing' does not match the description (no routing is described); align the name with the actual capabilities to reduce conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '按条件筛选计算均值' (filter and average), '从指定行区间提取数据去重求和' (row-range extraction with dedup sum), '生成结果文件与下载链接' (generate file and link) — matching the multiple-specific-actions anchor; not below because it goes beyond naming a single domain/action.

3 / 3

Completeness

Clearly answers 'what' (statistics, conditional averages, row-range dedup sums, output files) but provides no explicit 'Use when...' trigger guidance, so per the guideline completeness is capped at 2; not a 1 because 'what' is solid.

2 / 3

Trigger Term Quality

Contains relevant natural terms ('Excel文件', 'Sheet', '均值', '去重求和') but lacks common variations (e.g., '.xlsx', '平均值', '汇总') and reads as a capability list rather than user speech; not a 3 due to thin coverage, and the dangling '基础统计与,' is a grammar slip.

2 / 3

Distinctiveness Conflict Risk

The row-interval extraction + dedup-sum niche is fairly specific, but 'Excel基础统计/均值' broadly overlaps with other Excel skills and there are no explicit triggers to distinguish it, so it could still conflict; not a 3 because of the missing 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.