CtrlK
BlogDocsLog inGet started
Tessl Logo

onekgpd

Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals are homozygous-reference at a position, which variants exist in the dataset or carried by specified individuals in a gene or region, the relatedness between two specified individuals. Variants are returned with 1000 Genomes allele frequencies (AF), gnomAD v4.1 exome and genome AF, AlphaMissense score, and HGVSp annotations.

70

Quality

85%

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

78%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 and well-structured with good progressive disclosure and explicit guardrails for risky/batch operations. The main weakness is redundancy between the Quick Start and Typical Workflows sections, which inflates the token budget without adding new information.

Suggestions

Collapse the Quick Start and Typical Workflows sections into a single set of worked examples; the count→select→select-variants-in-samples flow is currently shown twice with near-identical commands.

Consolidate 'When to Use', 'Core Rules', and 'Command Selection Guide' — the command-to-question mapping is repeated across these sections.

Add an explicit error-recovery note for the count-before-select checkpoint (e.g., what 'too large' means and what to do instead) to turn the guardrail into a full feedback loop.

DimensionReasoningScore

Conciseness

Mostly efficient and command-focused, but the Quick Start and Typical Workflows sections duplicate the same count→select→select-variants-in-samples pattern, and the When-to-Use / Core Rules / Command Selection Guide overlap, adding repeatable tokens.

3 / 5

Actionability

Fully executable, copy-paste-ready bash invocations with real example coordinates (BRCA1 chr17:43044292-43170245) and sample IDs, plus complete flag lists covering the common cases.

5 / 5

Workflow Clarity

Clear numbered sequencing with checkpoints (mandatory coordinate provenance, count-before-select guardrail) for batch operations, but lacks an explicit error-recovery feedback loop beyond 'only proceed if count is manageable'.

4 / 5

Progressive Disclosure

Body is a well-organized overview that pushes full per-command argument tables and output schemas to references/onekgpd_commands.md and controlled vocabularies to references/annotation_vocabularies.md — one level deep, clearly signaled links, easy navigation.

5 / 5

Total

17

/

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.

The description is specific, third-person, and clearly states both the capability and a concrete 'Use when' trigger with multiple example question shapes. It is a strong, low-conflict description with only minor missing synonym coverage.

DimensionReasoningScore

Specificity

Enumerates multiple concrete query actions — finding variants/individuals by criteria, homozygous-reference calls, relatedness — giving comprehensive coverage of the skill's capabilities rather than abstract language.

5 / 5

Completeness

Explicitly answers both what ('Query the 1000 Genomes Project dataset... at the level of individual participants') and when ('Use when a question is about individuals or variants in the 1000 Genomes Project cohort:') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural terms ('1000 Genomes Project', 'individuals', 'variants', 'gene or region', 'homozygous-reference', 'relatedness') that a user of this dataset would say, though common shorthand synonyms like '1KG'/'1KGP' are absent.

4 / 5

Distinctiveness Conflict Risk

Scoped to a single named dataset with distinct triggers (1000 Genomes Project cohort, individual-level queries), leaving minimal overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-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.