decision-curve-analysis

Use when evaluating the clinical utility of a binary prediction model from a single clinical CSV file by fitting a logistic decision-curve model, plotting decision and clinical-impact curves, and exporting summary outputs. NOT for: survival calibration, ROC-only discrimination analysis, nomogram construction, or time-to-event outcomes.

Quality

83%

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

Quality

Content

75%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 well-structured, actionable skill body with executable commands, a complete argument reference, and clear progressive disclosure to real reference/script files. The main weakness is that the Testing section and Implementation Checklist reference a tests/ directory and bundled data that are absent from the bundle.

Suggestions

Either add the tests/ directory (tests/data/dca_data.csv, tests/run_smoke_test.R, tests/run_smoke_test.sh) or remove the Testing section, the 'With Bundled Test Data' example, and the corresponding checked Implementation Checklist item, so no referenced path is broken.

De-duplicate scope guidance: collapse the 'Input Validation' scope paragraph and canned out-of-scope response into the existing 'When Not to Use' section to reduce redundancy.

Make workflow checkpoints explicit (e.g., 'If validation fails, stop and report SKILL_* error to the user; do not proceed to fitting') rather than descriptive sub-bullets.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, information-dense reference material with no over-explanation of basic concepts, but scope is restated across 'When to Use', 'When Not to Use', and the 'Input Validation' paragraph, which could be tightened. Not a 3 because the bulk earns its tokens; not a 5 because of the redundant scope restatement.	4 / 5
Actionability	Provides copy-paste-ready Rscript commands, a complete arguments table with defaults, and an error-cause/solution table; however the documented smoke-test and 'With Bundled Test Data' examples reference tests/data/dca_data.csv and tests/run_smoke_test.R which do not exist in the bundle, leaving a runnable gap. Not a 5 because of the broken test path; not a 3 because the core workflow commands are fully executable.	4 / 5
Workflow Clarity	Four sequenced steps (Validate Input → Prepare Dataset → Fit Model → Save Outputs) with validation as Step 1 and an error-handling table for recovery. Not a 5 because checkpoints are descriptive rather than explicit stop/feedback gates; not a 3 because validation and an error-recovery loop are clearly present.	4 / 5
Progressive Disclosure	Uses a 'When to Read External Files' table with purposes to signal one-level-deep references (algorithm.md, troubleshooting.md, cli-guide.md, scripts/main.R — all real), but references to a non-existent tests/ directory (tests/data/dca_data.csv, run_smoke_test.R/.sh) are broken. Not a 5 because of the broken referenced paths; not a 3 because the real references are well-signaled and one level deep.	4 / 5
	Total	16 / 20 Passed

Description

92%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 strong, specific description that clearly states capabilities, trigger conditions, and exclusions in third person. It is highly distinctive with minimal conflict risk; the only gap is missing common synonyms/abbreviations (DCA, net benefit).

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'fitting a logistic decision-curve model', 'plotting decision and clinical-impact curves', and 'exporting summary outputs' from a 'single clinical CSV file' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (evaluate clinical utility via logistic DCA, plot curves, export summaries) and when ('Use when evaluating the clinical utility of a binary prediction model...'), plus concrete exclusion triggers ('NOT for: survival calibration, ROC-only...').	5 / 5
Trigger Term Quality	Good natural-term coverage ('binary prediction model', 'decision-curve model', 'clinical-impact curves', 'CSV'), but misses common synonyms a clinician would say such as 'DCA', 'net benefit', or the '.csv' extension. Not a 3 because several relevant natural terms are present; not a 5 because synonyms/abbreviations are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (decision-curve / net-benefit analysis) and the explicit NOT-for list (survival, ROC-only, nomogram, time-to-event) minimizes overlap with adjacent biostatistics skills.	5 / 5
	Total	19 / 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: awesome-med-research-skills/Data Analysis/decision-curve-analysis/SKILL.md
Commit: f5ef65b

Reviewed: ~11 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.