CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

71%

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-sensitivity-plot/SKILL.md
SKILL.md
Quality
Evals
Security

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 core workflow (data format tables, exact R script call, output template, R package dependencies) is genuinely actionable, but it is buried under generic template sections that restate the description and create a confusing Python-vs-R entry point inconsistency. Tightening the boilerplate and reconciling the two script paths would substantially improve the skill.

Suggestions

Delete or collapse the 'When to Use', 'Key Features', 'Dependencies', and 'Implementation Details' boilerplate sections, which restate the description verbatim and add no executable guidance; fold the genuinely useful bits (R package dependencies) into the workflow.

Reconcile the entry point: the front matter and example usage direct readers to 'python scripts/sensitivity_analysis.py --help' while Step 2 executes 'Rscript scripts/sensitivity_analysis.R' with positional arguments. State clearly that the R script is primary and the Python script is a fallback (as its own docstring says), including its matching CLI signature.

Fix the broken cross-reference ('See ## Workflow above' in Implementation Details points to a section that appears later) and add a brief error-recovery note for Step 1 validation failures (missing columns, fewer than 3 studies).

DimensionReasoningScore

Conciseness

The 'When to Use', 'Key Features', 'Dependencies', and 'Implementation Details' sections are template boilerplate that restate the description verbatim twice and add generic filler ('keep results reproducible, identify assumptions explicitly'), padding out roughly a third of the body.

2 / 5

Actionability

Gives an exact Rscript invocation with parameter explanations, per-data-type column tables, a concrete output template, and an install.packages command. Minor gaps: the front sections point to 'python scripts/sensitivity_analysis.py --help' while the workflow actually uses the R script with a different CLI signature, and 'Edit the in-file CONFIG block' matches neither documented path.

4 / 5

Workflow Clarity

Steps 1-3 are clearly sequenced (validate columns and the >=3-study minimum, execute the R script, emit the specified output) and dependency installation is addressed. Not a destructive/batch operation, so the cap of 3 does not apply, but there is no error-recovery guidance if validation fails and the Python-vs-R entry point is ambiguous.

4 / 5

Progressive Disclosure

Both referenced bundle scripts (sensitivity_analysis.R, sensitivity_analysis.py) exist and references are one level deep, but the body contains a broken cross-reference ('See ## Workflow above' appears before the Workflow section), inlines everything with no signal that the Python script is a fallback, and is crowded with boilerplate sections that hurt navigation.

3 / 5

Total

13

/

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, distinctive description that clearly states what the skill produces and in what formats, written in appropriate third-person voice. Its main gap is the complete absence of any 'use when' trigger guidance, which both caps completeness and slightly limits discoverability.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for leave-one-out or influence sensitivity analysis of a meta-analysis, or wants to check how pooled estimates change when individual studies are excluded.'

DimensionReasoningScore

Specificity

Names multiple concrete actions with explicit deliverables and formats: 'sensitivity forest plot (PNG)', 'sensitivity data table (CSV)', 'pooled effect estimates after excluding each study in turn'. Coverage is comprehensive for this niche with no gaps, matching the top anchor rather than the 'minor gaps' anchor at 4.

5 / 5

Completeness

The 'what' is explicit and concrete, but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description. Per the judging guidelines, a missing 'when' clause caps completeness at 3; this matches anchor 3 exactly.

3 / 5

Trigger Term Quality

Contains strong natural researcher phrasing ('leave-one-out sensitivity analysis', 'meta-analysis', 'forest plot', 'pooled effect estimates') but misses common variations users would say such as 'influence analysis' or 'exclude studies one at a time'. Fits 'good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear, highly specialized niche (leave-one-out sensitivity analysis for meta-analysis) with distinct triggers that would not fire for generic plotting or CSV skills. Minimal conflict risk, matching the top anchor.

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

Path

scientific-skills/Data Analysis/meta-sensitivity-plot/SKILL.md

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.