CtrlK
BlogDocsLog inGet started
Tessl Logo

km-survival-curve

Use when generating Kaplan-Meier survival curves from tabular survival data containing time, event status, and a precomputed risk group. Supports command-line parameter input, parameter validation, automatic time-unit handling, single-file PDF figure export, and session metadata capture.

70

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

83%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 SKILL.md body is highly actionable with executable commands, examples, and validation, organized with clear one-level references. Minor gaps: some duplicated cautionary prose and three bundled test datasets referenced in the body and Quick Examples are not present in the bundle.

Suggestions

Add the missing tests/data/km_sample1.txt, km_sample2.txt, km_sample3.txt (and the tests/data directory) so the Quick Examples and Validation commands are runnable as written.

Collapse the duplicated day-conversion advice from Input Requirements and Time Conversion Caution into a single concise section to reduce token cost.

Add an explicit verify/retry feedback loop in Minimal Workflow (e.g. on a SKILL_* error, consult troubleshooting.md and rerun) to strengthen the validation checkpoint.

DimensionReasoningScore

Conciseness

The body is mostly efficient — tables of arguments, example commands, and terse input requirements — but the large plot-customization table plus repeated cautionary prose (Time Conversion Caution restating Input Requirements) adds some tokens that could be trimmed.

4 / 5

Actionability

Fully executable: a concrete primary command, copy-paste-ready Quick Examples using bundled test data, an argument table with defaults, and a Validation block that checks for the output PDF.

5 / 5

Workflow Clarity

A clear Minimal Workflow sequence and validation step ('verify that tests/validation_output/km-plot.pdf exists') with feedback pointers to troubleshooting.md; however the destructive/batch guidance cautions are advisory rather than an explicit validate-then-recover loop, leaving a minor checkpoint gap.

4 / 5

Progressive Disclosure

Good one-level-deep structure: a 'Read These Files When Needed' table points to real references (algorithm.md, cli-guide.md, troubleshooting.md) and scripts/main.R, but the referenced tests/data/*.txt sample datasets do not exist in the bundle, a minor organization gap.

4 / 5

Total

17

/

20

Passed

Description

88%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, third-person description that concretely enumerates capabilities and gives an explicit 'Use when' trigger with specific data prerequisites. Trigger term coverage is good but could add synonyms like 'KM curve' and '.pdf' for a perfect score.

Suggestions

Add natural synonyms and the output file extension, e.g. 'Use when generating Kaplan-Meier (KM) survival curves ... and exporting a single .pdf figure'.

Optionally name the input formats (CSV/TSV) in the description so users searching for 'tabular' or 'spreadsheet' survival data land on this skill.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'generating Kaplan-Meier survival curves', 'command-line parameter input', 'parameter validation', 'automatic time-unit handling', 'single-file PDF figure export', 'session metadata capture' — providing comprehensive coverage of capabilities.

5 / 5

Completeness

Explicitly states both what it does (generating KM curves with validation, time-unit handling, PDF export, metadata capture) and when to use it ('Use when generating Kaplan-Meier survival curves from tabular survival data containing time, event status, and a precomputed risk group').

5 / 5

Trigger Term Quality

Includes natural terms a user would say ('Kaplan-Meier survival curves', 'survival data', 'risk group', 'PDF figure') but lacks common synonyms/variations and file extensions (e.g. 'KM curve', 'survival analysis', '.pdf'), leaving a few natural terms missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Kaplan-Meier curves from precomputed risk groups) with distinct, specific triggers unlikely to overlap with unrelated skills.

5 / 5

Total

19

/

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.

Validation15 / 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
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.