CtrlK
BlogDocsLog inGet started
Tessl Logo

knn-imputation

Use when filtering genes with high missingness and then imputing missing values in a bulk expression matrix with group-aware KNN through DMwR2, where donor samples are restricted by one annotation column before imputation. For strata with 10 or fewer samples, the script falls back to row-wise direct filling with mean or median. NOT for: single-cell data, multi-column stratification, non-tabular inputs, network access, or interactive workflows.

67

Quality

81%

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

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, highly actionable skill body with real bundle files and clear navigation. Main weakness is redundancy across the Workflow, Methods, and Input Format sections rather than deferring detail to references.

Suggestions

Consolidate the repeated filter/fallback rules: keep them once (e.g. in Methods or Arguments) and let the Workflow reference those instead of restating thresholds.

Move the verbose input-format requirements into references/cli-guide.md or algorithm.md, keeping only the essential schema inline.

Add an explicit 'verify output' checkpoint at the end of the Workflow step list rather than only in the separate Local Validation section.

DimensionReasoningScore

Conciseness

Largely efficient but contains redundancy — the workflow, Methods, and Examples sections restate the filter/fallback rules already given in Arguments and Input Format, which could be consolidated.

3 / 5

Actionability

Fully executable copy-paste command with all arguments shown, plus runnable short-form examples and concrete validation commands (Rscript --help, wc -l, ls).

5 / 5

Workflow Clarity

Clear five-step sequence with explicit validation in Step 1 (file existence, sample matching, column check) and a stop condition in Step 2, though it lacks an explicit post-output verification checkpoint inside the workflow itself.

4 / 5

Progressive Disclosure

Good one-level-deep structure with a 'When to Read External Files' table pointing to real references (algorithm.md, troubleshooting.md, cli-guide.md) and scripts, all confirmed to exist; minor overlap because some reference material is also restated inline.

4 / 5

Total

16

/

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 strong, specific description that concretely states capabilities, trigger conditions, and exclusions in third person. Trigger-term synonyms could be richer, but it is otherwise highly distinct and complete.

Suggestions

Add a few natural synonyms for trigger terms (e.g. 'missing data', 'NA values', 'fill in gaps') so users phrase it more ways.

Consider naming the input file extensions explicitly (e.g. '.csv') to broaden keyword coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — filtering genes by missingness, group-aware KNN via DMwR2 with single-column donor restriction, and row-wise mean/median fallback for small strata — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers what (filter genes >50% missingness, group-aware KNN imputation, small-strata fallback) and when ('Use when filtering genes...'), plus an explicit 'NOT for' exclusion list.

5 / 5

Trigger Term Quality

Includes natural terms like 'imputing missing values', 'bulk expression matrix', and 'annotation column', but lacks common synonyms/variations a user might say (e.g. 'missing data', 'NA values', 'fill in gaps').

4 / 5

Distinctiveness Conflict Risk

Clear niche — group-aware KNN imputation on bulk matrices restricted by one annotation column — with explicit exclusions (no single-cell, no multi-column, no network), minimizing overlap with other 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.