meta-sensitivity-plot

Generate leave-one-out sensitivity analysis plots for meta-analysis. Input is a CSV file containing meta-analysis data; outputs are a sensitivity forest plot (PNG) and a sensitivity data table (CSV) showing pooled effect estimates after excluding each study in turn.

Quality

67%

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-sensitivity-plot/SKILL.md

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 body is actionable with concrete R commands, data-format tables, and a clear validated workflow, but is weighed down by generic boilerplate sections and a Python/R inconsistency. Structure and progressive disclosure are sound with real bundle scripts referenced.

Suggestions

Remove the generic 'When to Use', 'Key Features', 'Dependencies', and 'Implementation Details' boilerplate that restates the description and explains concepts Claude already knows.

Resolve the Python/R inconsistency: the 'Example Usage' runs sensitivity_analysis.py while the Workflow calls sensitivity_analysis.R — pick one primary path and align all references.

Add an explicit error-recovery feedback loop for Step 2 (e.g., what to do when the R script fails or packages are missing) to strengthen the workflow.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the 'When to Use', 'Key Features', 'Dependencies', and 'Implementation Details' sections are generic boilerplate that repeat the description verbatim, and 'About Sensitivity Analysis' explains concepts Claude already knows.	2 / 5
Actionability	Provides concrete executable commands (Rscript invocation with explained parameters, install.packages), data-format column tables, and a detailed output template, but the conflicting Python/R script references create a minor gap.	4 / 5
Workflow Clarity	A clear three-step sequence (validate input, execute script, output) with validation checkpoints in Step 1 (column checks, 3-study minimum), though explicit error-recovery feedback loops for script failure are absent.	4 / 5
Progressive Disclosure	Good section structure with one-level-deep references to real bundle scripts (sensitivity_analysis.R and sensitivity_analysis.py both exist), but inline data-format tables and the dual py/R script references are minor organization gaps.	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.

The description is specific and distinctive with concrete inputs, outputs, and mechanism, but lacks an explicit 'when to use' trigger clause, which caps completeness. Trigger term coverage is good but missing common synonyms and file extensions.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases such as 'leave-one-out analysis', 'influence analysis', or 'meta-analysis robustness check'.

Include file extensions (.csv, .png) and synonyms ('influence analysis', 'robustness') to broaden natural trigger coverage.

Clarify the implementation language (the description implies a generic tool, but the body invokes an R script) to avoid mismatch with user expectations.

Dimension	Reasoning	Score
Specificity	Names the domain ('leave-one-out sensitivity analysis for meta-analysis'), concrete inputs (CSV), concrete outputs ('sensitivity forest plot (PNG) and a sensitivity data table (CSV)'), and the mechanism ('excluding each study in turn'), giving comprehensive coverage of specific actions.	5 / 5
Completeness	The 'what' is stated clearly (generate plots from CSV inputs to PNG/CSV outputs), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Includes natural domain terms a researcher would say ('meta-analysis', 'sensitivity analysis', 'forest plot', 'leave-one-out'), but lacks synonyms like 'influence analysis' or file extensions (.csv, .png).	4 / 5
Distinctiveness Conflict Risk	The 'leave-one-out sensitivity analysis for meta-analysis' niche is highly specific with distinct triggers, making conflict with other skills minimal.	5 / 5
	Total	17 / 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-sensitivity-plot/SKILL.md
Commit: f5ef65b

Reviewed: ~5 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.