CtrlK
BlogDocsLog inGet started
Tessl Logo

data-analyst

Data analysis expert for statistics, visualization, pandas, and exploration

49

Quality

53%

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 ./crates/openfang-skills/bundled/data-analyst/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

The content is well-organized and reasonably actionable with specific pandas methods, but it is held back by restating concepts Claude already knows, lacking complete executable code, and presenting only an implicit workflow without validation checkpoints.

Suggestions

Trim or remove the 'Pitfalls to Avoid' and obvious 'Key Principles' items that restate knowledge Claude already has, keeping only non-obvious project-specific guidance.

Add at least one complete executable code block (imports + a runnable EDA snippet) and show the scipy calls for the named hypothesis tests.

Make the workflow explicit with numbered steps and a validation checkpoint, e.g. 'After cleaning, re-run df.isnull().sum() and df.duplicated() to confirm before analyzing.'

DimensionReasoningScore

Conciseness

Bullets are lean and use specific pandas methods, but the 'Pitfalls to Avoid' and 'Key Principles' sections restate concepts Claude already knows (correlation vs. causation, Simpson's paradox, sample size, which chart suits which data), fitting the 'mostly efficient but includes some unnecessary explanation' anchor.

2 / 3

Actionability

Concrete method references (df.isnull().sum(), pd.to_datetime, df.corr()) and named tests are given, but there are no complete executable code blocks and the statistical tests lack an implementation (e.g. scipy.stats.*), so it is not copy-paste ready.

2 / 3

Workflow Clarity

The section order implies an EDA -> clean -> visualize -> analyze flow and mentions validating data quality, but there is no explicit numbered sequence, checkpoints, or validate-and-retry feedback loop for the multi-step process.

2 / 3

Progressive Disclosure

The body is under 50 lines, needs no external references, and is organized into clear labeled sections, so per the simple-skill scoring note it earns a 3 on organization.

3 / 3

Total

9

/

12

Passed

Description

50%

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 names a clear domain and relevant tools but relies on topic nouns rather than concrete actions and omits any explicit use-trigger, leaving both completeness and trigger guidance implied rather than stated.

Suggestions

Add concrete actions: e.g. 'Explore datasets, compute descriptive statistics, and build visualizations using pandas and matplotlib.'

Append an explicit trigger clause: 'Use when analyzing datasets, computing statistics, or creating charts and visualizations.'

Include common user phrasings like 'EDA', 'exploratory data analysis', 'charts', and 'dataframes' to improve trigger coverage.

DimensionReasoningScore

Specificity

Names the domain and tooling ('data analysis', 'statistics', 'visualization', 'pandas') but lists topic nouns rather than concrete actions, so it stops short of the multi-action anchor 3 and is more specific than the vague anchor 1.

2 / 3

Completeness

It states what the skill covers but has no 'Use when...' or equivalent trigger clause; per the judging guidelines a missing explicit trigger caps completeness at 2.

2 / 3

Trigger Term Quality

Terms like 'data analysis', 'statistics', 'visualization', and 'pandas' are natural, but common variations users would say (EDA, charts, plots, datasets, dataframes) are missing, matching the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The pandas/statistics niche is somewhat specific, but without explicit triggers it could overlap with a general Python skill or a dedicated plotting/statistics skill, fitting the 'somewhat specific but could still overlap' anchor.

2 / 3

Total

8

/

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
RightNow-AI/openfang
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.