univariate-multivariable-cox-regression

Use when running prognostic survival analysis on a clinical cohort with time-to-event data to estimate univariate and multivariable Cox proportional hazards models, export result tables, and generate forest plots. NOT for: nomogram construction, calibration curves, time-dependent ROC analysis, or model training/feature selection beyond the built-in univariate screening rule.

Quality

76%

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 ./awesome-med-research-skills/Data Analysis/univariate-multivariable-cox-regression/SKILL.md

Quality

Content

65%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.

A highly actionable, well-structured skill body with strong reference tables and copy-paste commands, weakened by redundant example repetition, an administrative checklist, missing batch-operation validation checkpoints, and dangling tests/ references.

Suggestions

Add an explicit verification checkpoint between analyze and plotting (e.g. confirm table columns/rows exist and the .xlsx is readable before calling forest-plot) plus a validate→fix→retry loop to lift workflow_clarity above the batch-operation cap of 3.

Bundle the referenced `tests/` artifacts (tests/data/sample_clinical_survival_data.csv, tests/run_smoke_test.R, tests/run_smoke_test.sh, tests/expected_output/) or remove the Testing and tests/data references so no documented path is missing.

De-duplicate the analyze/forest-plot commands that appear in Usage, Examples, and Testing, and remove the build-administrative "Implementation Checklist" to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient dense reference tables, but the same analyze/forest-plot commands recur across Usage, Examples, and Testing, and the "Implementation Checklist" is build-administrative content that does not help Claude use the skill.	3 / 5
Actionability	Copy-paste-ready `Rscript scripts/main.R` commands for all subcommands, complete argument tables with types/defaults, a concrete CSV input example, output-file tables, and an error cause/solution table cover the common cases fully.	5 / 5
Workflow Clarity	Step 1 validates and prepares data and the four steps are sequenced, but this is a batch/destructive operation (the `--overwrite` flag writes into non-empty output dirs) with no inter-step verification checkpoint or validate→fix→retry feedback loop, capping the score at 3.	3 / 5
Progressive Disclosure	The "When to Read External Files" table gives well-signaled one-level-deep navigation and existing references/scripts resolve, but the body repeatedly points to a `tests/` directory (tests/data/, tests/run_smoke_test.R, tests/run_smoke_test.sh, tests/expected_output/) that is absent from the bundle, breaking navigation for those paths.	3 / 5
	Total	14 / 20 Passed

Description

87%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 tight, well-scoped description that pairs concrete capabilities with an explicit use-trigger and a clear "NOT for" boundary. Trigger-term coverage is strong but could add a few synonyms and file extensions to reach full comprehensiveness.

Dimension	Reasoning	Score
Specificity	Names three concrete actions — "estimate univariate and multivariable Cox proportional hazards models, export result tables, and generate forest plots" — with minor coverage gaps rather than the fully comprehensive list required for a 5.	4 / 5
Completeness	Explicitly answers both — WHAT ("estimate... models, export result tables, and generate forest plots") and WHEN ("Use when running prognostic survival analysis on a clinical cohort with time-to-event data") — plus a concrete "NOT for" boundary clause.	5 / 5
Trigger Term Quality	Natural domain phrases ("prognostic survival analysis", "clinical cohort", "time-to-event data", "Cox proportional hazards", "forest plots") give good keyword coverage, but common synonyms (e.g. "hazard ratio") and file extensions are absent.	4 / 5
Distinctiveness Conflict Risk	A narrow statistical niche (Cox PH survival models) with an explicit exclusion list (nomogram, calibration curves, time-dependent ROC, feature selection) yields clear triggers and minimal overlap with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Data Analysis/univariate-multivariable-cox-regression/SKILL.md
Commit: f5ef65b

Reviewed: ~9 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.