CtrlK
BlogDocsLog inGet started
Tessl Logo

table-1-generator-advanced

Generate publication-ready baseline characteristics tables (Table 1) for clinical research papers with automatic variable type detection, appropriate statistics (mean±SD, median[IQR, n(%)), group comparisons (t-test, chi-square), and APA formatting.

58

Quality

73%

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 ./scientific-skills/Data Analysis/table-1-generator-advanced/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 executable core (workflow, usage, parameters, verification commands) is solid and matches the actual bundled script. The body is dragged down by substantial generic template boilerplate, duplicated commands, and a broken requirements.txt reference that inflate token cost without aiding execution.

Suggestions

Delete the boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) — they are template filler that consumes context without helping generate a Table 1.

Merge 'Quick Check' and 'Audit-Ready Commands' (they duplicate the same py_compile command) and remove the 'Features' section that restates the description verbatim.

Ship the referenced requirements.txt (or list the actual dependencies inline) and fix the parameters table so '--output' matches the script's argparse where only '--data' is required.

DimensionReasoningScore

Conciseness

Beyond the useful Workflow/Usage/Parameters sections, roughly half the body is generic template boilerplate that adds no execution value: 'Risk Assessment', 'Security Checklist' (10 unchecked boxes), 'Evaluation Criteria', 'Lifecycle Status', 'Output Requirements', 'Input Validation', and 'Response Template'. The py_compile command is also duplicated in 'Quick Check' and 'Audit-Ready Commands', 'Features' repeats the description verbatim, and 'Output' is three near-empty bullets. This matches anchor 2 ('several unnecessary explanations or padded sections') rather than 3, where padding would be only incidental.

2 / 5

Actionability

Concrete, copy-paste-ready commands are present: 'python scripts/main.py --data patients.csv --group treatment --output table1.csv', the py_compile verification, a full parameters table, and a workflow with explicit inputs/outputs. Minor gaps keep it below 5: 'pip install -r requirements.txt' references a file that does not exist in the bundle, the parameters table marks '--output' as Required while the script's argparse only requires '--data', and the Test Cases are vague ('Standard input → Expected output').

4 / 5

Workflow Clarity

The six-step workflow is clearly sequenced with per-step inputs and outputs, an explicit checkpoint ('⛔ Checkpoint: Confirm statistical method choices with user if normality is borderline'), data validation steps, and a pre-execution compile check — matching anchor 4 ('clear sequence with most checkpoints present'). It falls short of 5 because the workflow itself has no validate-fix-retry feedback loop; recovery guidance lives separately in 'Error Handling'.

4 / 5

Progressive Disclosure

The bundle structure is clean: a single script (scripts/main.py) referenced correctly from multiple sections and confirmed to exist, no nested references, and clearly headed sections that are easy to navigate — matching anchor 4. The missing requirements.txt reference and the inlined boilerplate sections are minor organization gaps that prevent a 5.

4 / 5

Total

14

/

20

Passed

Description

75%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.

A specific, well-scoped description with concrete capabilities and strong domain trigger terms. Its main weakness is the missing 'when to use' guidance, which caps completeness and leaves a few natural trigger phrases (present only in the body) out of the description.

Suggestions

Add an explicit 'when' clause, e.g. 'Use when the user mentions Table 1, baseline characteristics, or demographic/summary tables for a clinical research manuscript.'

Fold the body's trigger phrases ('demographic table', 'clinical trial table', 'summary statistics table') into the description so users' natural phrasings match.

Mention supported input/output formats (CSV/Excel) so the description states what the deliverable looks like.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with specifics: 'Generate publication-ready baseline characteristics tables (Table 1)', 'automatic variable type detection', 'appropriate statistics (mean±SD, median[IQR, n(%))', 'group comparisons (t-test, chi-square)', and 'APA formatting'. This comprehensively matches the script's actual functionality, fitting the score-5 anchor ('multiple specific concrete actions; comprehensive coverage') rather than score 4, which would imply minor coverage gaps.

5 / 5

Completeness

The 'what' is clearly and concretely stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance — the description never says when to invoke the skill. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3 ('clear what but when is missing or only weakly implied').

3 / 5

Trigger Term Quality

Strong natural terms: 'Table 1', 'baseline characteristics', 'clinical research papers', 't-test', 'chi-square' — exactly what a clinical researcher would say. A few natural variations are missing from the description itself ('demographic table', 'summary statistics table', '.csv'), keeping it at the score-4 anchor rather than 5.

4 / 5

Distinctiveness Conflict Risk

'Table 1' and 'baseline characteristics' for clinical research papers is a clear niche with distinct, domain-specific triggers; minimal conflict risk with any general statistics or document skill. Matches the score-5 anchor and is clearly above score 4, which would require overlap with closely related skills.

5 / 5

Total

17

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-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.