meta-funnel-plot

Generate Meta-analysis funnel plots and perform publication bias testing. Takes CSV file with Meta-analysis data as input, outputs funnel plot PNG, Egger test and Begg test results.

Quality

60%

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-funnel-plot/SKILL.md

Quality

Content

62%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 is actionable with executable commands and concrete data-format tables, and has a clear workflow with a validation checkpoint. It is somewhat verbose with generic boilerplate sections and has minor progressive-disclosure gaps from mixed Python/R execution paths.

Suggestions

Remove or condense generic boilerplate sections (When to Use, Key Features, Required Inputs, Output Contract, Validation and Safety Rules) that restate what Claude already knows.

Reconcile the execution path: the body alternates between running python scripts/funnel_plot.py and Rscript scripts/funnel_plot.R; make the intended entry point and the role of each script explicit.

Add an explicit error-recovery feedback loop for the common failure cases (missing R packages, CSV column mismatches) so validation->fix->retry is concrete.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete tables and commands, but includes several generic filler sections (When to Use, Key Features, Required Inputs, Output Contract, Validation and Safety Rules) that restate obvious guidance Claude already knows and could be tightened.	3 / 5
Actionability	Provides an executable Rscript invocation with parameter descriptions, concrete CSV column tables per data type, and a quick-validation command; minor gaps such as the example-run-plan and inline CONFIG editing being only sketched keep it from a 5.	4 / 5
Workflow Clarity	A clear 3-step sequence (validate input -> execute R script -> output results) with an explicit validation checkpoint (at least 3 studies required) and failure-handling guidance; not a 5 because error-recovery feedback loops for script/R-package failures are described generically rather than as explicit validate->fix->retry cycles.	4 / 5
Progressive Disclosure	Content is reasonably sectioned and references real bundle scripts (scripts/funnel_plot.py, scripts/funnel_plot.R), but there is a cross-language inconsistency (Python helper vs R execution path) and a stray 'See ## Workflow above' pointer, and inline details that belong with the scripts are not clearly signaled as one-level-deep references.	3 / 5
	Total	14 / 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 distinctive, clearly naming inputs, outputs, and concrete actions, but it omits an explicit 'Use when' trigger clause, which caps completeness. Trigger term coverage is accurate but lacks natural synonyms and file extensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks for Meta-analysis funnel plots or publication bias testing (Egger/Begg tests) from CSV data.'

Include natural trigger variations and file extensions users might mention, such as 'funnel plot', 'publication bias', 'Egger test', 'Begg test', and '.csv'.

Consider rephrasing in third-person imperative form to match good examples (e.g. 'Generates... Performs...') rather than the slightly mixed voice.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (generate funnel plots, perform publication bias testing, takes CSV input, outputs PNG plus Egger and Begg test results); minor gap is that the test outputs are named but the broader scope is somewhat domain-specific rather than fully comprehensive.	4 / 5
Completeness	Clearly states what the skill does (inputs, outputs, actions) but provides no explicit 'Use when...' clause telling Claude when to invoke it, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Contains relevant terms ('Meta-analysis', 'funnel plots', 'publication bias', 'Egger test', 'Begg test') but misses common natural variations and file extensions a user might say, and lacks synonyms; coverage is domain-accurate but not broad.	3 / 5
Distinctiveness Conflict Risk	The niche (Meta-analysis funnel plots with Egger/Begg tests) is fairly distinct and unlikely to trigger for unrelated skills; only minor overlap risk with other statistical/meta-analysis skills.	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-funnel-plot/SKILL.md
Commit: f5ef65b

Reviewed: ~4 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.