CtrlK
BlogDocsLog inGet started
Tessl Logo

sample-group-sankey-plot

Use when generating Sankey or alluvial plots from sample annotation tables where rows are samples and selected columns are categorical stages such as risk group, response status, subtype, or cohort labels. NOT for: gene network flow analysis, continuous-value trajectories, or graph-structured pathway visualization.

74

Quality

93%

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

86%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 body is highly actionable with executable R commands, a clear sequenced workflow, and well-signaled one-level-deep references to real bundle files. The main weakness is mild redundancy (repeated readability guidance and reference pointers, and an error-handling table that duplicates troubleshooting.md).

Suggestions

Consolidate the readability guidance so it appears once (either the 'Readability guidance' note or Step 2a advisories, not both) to reduce token redundancy.

Remove repeated reference pointers (e.g. the multiple 'For detailed algorithm, READ: references/algorithm.md' lines) and rely on the 'When to Read External Files' table as the single navigation hub.

Consider trimming or pointing the inline Error Handling table to references/troubleshooting.md to avoid duplicating the same SKILL_* error catalog in two places.

DimensionReasoningScore

Conciseness

Largely efficient tables (Arguments, Input Format, Output Files, Error Handling) with concrete commands, but there is trimmable redundancy: readability guidance appears twice (frontmatter-adjacent and Step 2a), reference pointers are restated multiple times, and the inline Error Handling table overlaps troubleshooting.md. Above the 3 anchor but not fully lean.

4 / 5

Actionability

Fully copy-paste-ready executable guidance: concrete `Rscript scripts/main.R ...` invocations with real flags, a real CSV sample, real output filenames, and runnable test/smoke commands covering the common cases.

5 / 5

Workflow Clarity

Steps 1→2→2a→3→4 are sequenced with explicit validation (file exists/readable, ≥2 columns, requested columns exist) and a non-zero-exit feedback contract; not a 5 because there is no explicit verify-outputs checkpoint inside the workflow itself (it lives separately in Testing), leaving a minor validation gap.

4 / 5

Progressive Disclosure

A 'When to Read External Files' table maps each situation to a real verified file (scripts/main.R, references/algorithm.md, troubleshooting.md, cli-guide.md) one level deep, with clear signaling and a fallback; the body is an overview and bulk detail is split into references/. Minor inline overlap with troubleshooting.md keeps it from being questionable but still anchors at 5.

5 / 5

Total

18

/

20

Passed

Description

100%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.

The description is excellent: it states a concrete capability, opens with an explicit 'Use when' trigger, lists natural synonyms and real annotation-field examples, and sharply excludes adjacent use cases. It uses third-person voice with no fluff or over-claims.

DimensionReasoningScore

Specificity

Names the domain (Sankey/alluvial plots from sample annotation tables) and concrete structural detail: 'rows are samples and selected columns are categorical stages such as risk group, response status, subtype, or cohort labels' — comprehensive coverage with four named stage examples.

5 / 5

Completeness

Explicitly answers both: 'what' (Sankey/alluvial visualization from categorical sample annotation tables) and 'when' via an explicit 'Use when generating...' clause, plus a 'NOT for' exclusion — matching the 5 anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural synonyms users would say ('Sankey or alluvial plots', 'sample annotation tables') plus domain terms (risk group, response status, subtype, cohort labels); not a 4 because both plot-type synonyms and several real annotation-field names are present.

5 / 5

Distinctiveness Conflict Risk

Clear niche (sample-group Sankey from annotation tables) reinforced by an explicit 'NOT for: gene network flow analysis, continuous-value trajectories, or graph-structured pathway visualization', giving minimal conflict risk with adjacent skills.

5 / 5

Total

20

/

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.