CtrlK
BlogDocsLog inGet started
Tessl Logo

meta-radial-plot

Generate radial plots (Radial Plot/Galbraith Plot) for heterogeneity analysis. Visually assess heterogeneity across studies by displaying the relationship between standardized effect sizes and precision. Input: Meta-analysis data in CSV format; Output: Radial plot PNG and data CSV.

56

Quality

65%

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/meta-radial-plot/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 body delivers concrete, executable R-script guidance and useful data-format/output specifications, but is weakened by generic boilerplate padding and inconsistent guidance about whether the R or Python script is the primary implementation surface. Fixing the script contradiction and trimming boilerplate would meaningfully improve the score.

Suggestions

Resolve the script contradiction: designate the R script (per the Workflow) as the single primary implementation surface and stop presenting `radial_plot_backup.py` as primary in Example Usage, Implementation Details, and Quick Validation; frame the Python file explicitly as a fallback only.

Remove or condense the generic boilerplate sections (When to Use, When Not to Use, Required Inputs, Output Contract, Validation and Safety Rules, Failure Handling) that restate non-skill-specific guidance.

Add an explicit validate→fix→retry feedback loop in the Workflow (e.g., if column validation fails, report the missing column and re-validate) and fix the 'See ## Workflow above' cross-reference to point to the correct, later section.

DimensionReasoningScore

Conciseness

The core operational content (data-format tables, the Rscript command, the output template) is efficient, but generic boilerplate sections ("When to Use", "When Not to Use", "Required Inputs", "Output Contract", "Validation and Safety Rules", "Failure Handling") add padded, non-skill-specific tokens that could be trimmed.

3 / 5

Actionability

The Workflow supplies an executable `Rscript scripts/radial_plot.R "<csv_path>" "<type>" "<outcome_name>" "<output_dir>"` command with concrete parameter descriptions and data-format tables, but the body inconsistently presents `radial_plot_backup.py` as the primary implementation surface in Example Usage, Implementation Details, and Quick Validation.

4 / 5

Workflow Clarity

A clear 3-step sequence with an input-validation checkpoint (columns, integrity, minimum 3 studies) is present, but there is no explicit validate→fix→retry feedback loop for this batch operation, and "See ## Workflow above" references a section that actually appears later in the document.

3 / 5

Progressive Disclosure

Both referenced scripts (`scripts/radial_plot.R` and `scripts/radial_plot_backup.py`) are real, one-level-deep bundle files under a clear section structure, but navigation is slightly muddled by contradictory primary-script references and a misplaced cross-reference.

4 / 5

Total

14

/

20

Passed

Description

70%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-targeted description with strong trigger keywords and a distinct niche, but it lacks an explicit 'Use when' clause, which caps completeness. Adding a trigger phrase would likely raise the completeness and trigger_term_quality scores.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases, e.g. 'Use when the user requests a radial/Galbraith plot or heterogeneity assessment for a meta-analysis.'

Include the .csv file extension alongside 'CSV' to broaden trigger-term coverage toward file-extension matches.

DimensionReasoningScore

Specificity

"Generate radial plots... Visually assess heterogeneity... displaying the relationship between standardized effect sizes and precision" lists several concrete actions (generate, assess, display) plus an explicit Input/Output contract, though coverage stays narrow to a single plot type.

4 / 5

Completeness

There is a clear "what" ("Generate radial plots... for heterogeneity analysis" with stated Input/Output) but no explicit "Use when..." trigger clause, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

"radial plots (Radial Plot/Galbraith Plot)", "heterogeneity analysis", "Meta-analysis data", and "CSV" give good natural keyword coverage including synonyms, but the .csv extension and some common variations are missing.

4 / 5

Distinctiveness Conflict Risk

"Radial Plot/Galbraith Plot for heterogeneity analysis" on "Meta-analysis data in CSV format" is a clear, narrow niche with distinct triggers and minimal overlap risk with sibling meta-analysis skills.

5 / 5

Total

16

/

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.

Validation15 / 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.