CtrlK
BlogDocsLog inGet started
Tessl Logo

line-chart-visualization

提取结构化数据并进行特征清洗与聚类分析,生成包含趋势对比、分布特征与参数敏感性的多维度综合可视化图表,适用于各类趋势预测与多维对比场景。

54

Quality

60%

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-visualization/line-chart-visualization/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 skill provides executable, well-sequenced code with efficient annotation, but it lacks any validation/verification steps for its batch data-processing operations and keeps all code inline with no progressive disclosure to separate files.

Suggestions

Add validation checkpoints between steps (e.g., assert df_clean is non-empty after dropna, verify output_chart.png and output_table.xlsx were written) with a fix-and-retry feedback loop, since this is a batch/destructive workflow.

Move the large per-step code blocks into scripts/ files (e.g., scripts/load_data.py, scripts/visualize.py) and reference them from SKILL.md to improve progressive disclosure and reusability.

Replace the placeholder column names and 占位示例 thresholds with guidance on how to detect/adapt them to the user's actual schema, so the code is closer to copy-paste ready.

DimensionReasoningScore

Conciseness

The body is dominated by executable code with only brief Chinese step headers and short functional inline comments; it does not explain concepts Claude already knows, with just minor over-labeling (e.g., '# 数值特征标准化') that could be trimmed.

4 / 5

Actionability

Real, executable pandas/sklearn/matplotlib code is provided end-to-end; the main gap is placeholder column names ('group_col', 'value_col1') and placeholder thresholds marked 占位示例 that the user must adapt, keeping it just below fully copy-paste-ready.

4 / 5

Workflow Clarity

Steps are clearly sequenced as Step1–Step4, but the pipeline is a batch/destructive operation (large-file conversion, dropna, writing outputs) with no validation checkpoints or error-recovery feedback loops, so per the batch-operations cap workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

Content is organized into four labeled steps, but the entire ~170-line script is inlined in SKILL.md with no external references or bundle files; substantial code that could live in scripts/ is kept inline, matching the 'some structure but content that should be separate is inline' anchor.

3 / 5

Total

14

/

20

Passed

Description

55%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 states concrete capabilities in third person but provides only a weakly-implied 'when' and lacks an explicit 'Use when...' trigger clause, which caps completeness. Trigger terms are present but miss file extensions and synonyms.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when the user asks for trend forecasting, multi-dimensional comparison charts, or clustering-based data visualization').

Include natural file-format keywords users would say (.xlsx, .csv, Excel, 报表) to broaden trigger-term coverage and reduce overlap with generic charting skills.

Tighten the applicability phrase from '各类...场景' to specific, distinctive scenarios to lower conflict risk with general data-analysis skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — "提取结构化数据"、"特征清洗"、"聚类分析"、"生成...可视化图表" with named chart types (趋势对比/分布特征/参数敏感性) — but the actions stay slightly abstract, so it sits just below the comprehensive-coverage anchor.

4 / 5

Completeness

The 'what' is clear, but the 'when' is only weakly implied via "适用于各类趋势预测与多维对比场景" with no explicit 'Use when...' trigger clause, so per the missing-trigger-guidance cap it cannot exceed 3.

3 / 5

Trigger Term Quality

Contains some relevant natural terms ("趋势预测"、"多维对比"、"可视化图表") but misses common variations/synonyms and any file extensions (.xlsx/.csv/.parquet), fitting the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The clustering-plus-multidimensional-viz niche is somewhat specific, but "各类趋势预测与多维对比场景" is broad enough to overlap with generic data-analysis or charting skills, matching the 'somewhat specific but could still overlap' anchor.

3 / 5

Total

13

/

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.