meta-baujat-plot

Generate Baujat plots for heterogeneity analysis. Identify studies that contribute most to the overall meta-analysis results and heterogeneity, helping discover potential outlier studies. Input meta-analysis data CSV, output Baujat plot PNG and contribution data CSV.

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/meta-baujat-plot/SKILL.md

Quality

Content

56%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 content is actionable and has a clear validate-execute-output workflow with real bundle scripts, but it carries substantial generic boilerplate that inflates token cost without adding Claude-specific knowledge. Moving CSV schemas, install steps, and the output template into reference files would improve both conciseness and progressive disclosure.

Suggestions

Cut or collapse the generic policy sections ('When to Use', 'Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling') into a few terse lines; they restate behavior Claude already follows.

Reconcile the two entrypoints (baujat_plot.R via Rscript vs baujat_plot_fallback.py) into one primary path with the other as a documented fallback, so Example Usage, Workflow, and Quick Validation stop duplicating commands.

Move the per-type CSV column tables, R-package install snippet, and the full output template into a references/ file (e.g. DATA_FORMAT.md) and link to it, keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: large generic sections ('When to Use', 'Key Features', 'Dependencies', 'Implementation Details', 'Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling', 'Quick Validation') restate boilerplate Claude already knows, and the Example Usage / Quick Validation / Workflow command surfaces partly duplicate each other, padding the token budget beyond what earns a 3.	2 / 5
Actionability	It provides concrete, runnable commands ('Rscript scripts/baujat_plot.R "<csv_path>" "<type>" ...', 'python scripts/baujat_plot_fallback.py --help'), a parameter list, exact required CSV columns per data type, and an output template; only minor gaps (e.g. the two script entrypoints are not reconciled) keep it from 5.	4 / 5
Workflow Clarity	The Workflow is sequenced as Validate -> Execute R Script -> Output Results with an explicit validation checkpoint ('at least 3 studies are required') and a structured output template; not a full 5 because error-recovery feedback loops (validate -> fix -> retry) are described only generically in 'Failure Handling' rather than inline at the checkpoint.	4 / 5
Progressive Disclosure	The bundle exists (scripts/baujat_plot.R, scripts/baujat_plot_fallback.py) and is referenced by path, but the SKILL.md inlines substantial content that could live in references (e.g. full CSV column tables, R-package install snippets, the output template), and references to scripts are not uniformly signaled as one-level-deep navigation links, leaving it between anchors 3 and 4.	3 / 5
	Total	13 / 20 Passed

Description

58%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 is specific and well-scoped to a distinct niche, but it omits an explicit 'Use when...' trigger clause and natural user phrasings, which together cap completeness and trigger-term quality. Adding a concrete trigger sentence would lift both.

Suggestions

Append a 'Use when...' clause naming natural user phrases (e.g. 'Use when the user asks for Baujat plots, heterogeneity diagnostics, or outlier study detection in a meta-analysis').

Include synonyms and the relevant file extension (e.g. mention .csv input and heterogeneity/I-squared diagnostics) to broaden natural trigger coverage.

Keep third-person voice but explicitly state when NOT to use it (e.g. general forest plots) to sharpen distinctiveness from sibling meta-analysis skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Generate Baujat plots', 'Identify studies that contribute most', 'discover potential outlier studies') and concrete I/O ('Input meta-analysis data CSV, output Baujat plot PNG and contribution data CSV'), with only minor coverage gaps.	4 / 5
Completeness	Clearly answers 'what' the skill does but provides no explicit 'when'/'Use when...' clause; per the rubric a missing trigger clause caps completeness at 3, so it does not reach 4.	3 / 5
Trigger Term Quality	Contains relevant domain keywords ('Baujat plots', 'heterogeneity analysis', 'meta-analysis') but lacks the natural user-facing trigger phrases, synonyms, or file extensions (e.g. 'Use when the user mentions heterogeneity or outliers') that anchor 4 requires.	3 / 5
Distinctiveness Conflict Risk	Baujat plots are a specialized niche with a clear, narrow trigger surface, leaving only minor overlap risk with other meta-analysis skills rather than the broad collision risk of anchor 3.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/meta-baujat-plot/SKILL.md
Commit: f5ef65b

Reviewed: ~3 hours ago

Table of Contents

Discovery Implementation Validation

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.