tiledbvcf

Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/tiledbvcf/SKILL.md

Quality

Content

50%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 content is a comprehensive, mostly executable reference with concrete code and CLI examples, but it is verbose and monolithic. It over-explains concepts Claude already knows and inlines large sections that would benefit from separate reference files, with no validation checkpoints in its batch workflows.

Suggestions

Trim the enumeration-style 'Common operations' and 'Common workflows' lists and the restated domain explanations to reduce padding and respect token budget.

Add explicit validation/verification checkpoints to ingestion and export workflows (e.g., verify dataset stats after ingest, validate sample counts before export) to lift workflow clarity.

Split the large Cloud-migration and advanced-features material into separate reference files (e.g., CLOUD.md, ADVANCED.md) with clearly signaled one-level-deep links from the body.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose—enumeration-style 'Common operations'/'Common workflows' lists, restated domain concepts, repeated requirements across sections, and marketing-style Cloud sections ('Cost Optimization', 'Security and Compliance') add padding beyond what Claude needs.	2 / 5
Actionability	Provides copy-paste-ready conda/docker install, concrete Python and CLI snippets covering ingestion, query, and export, but the TileDB-Cloud examples carry 'Exact API requires documentation' caveats that introduce minor executability gaps.	4 / 5
Workflow Clarity	Core operations (create → ingest → query → export) are coherent but presented as separate example blocks with no embedded validation checkpoints; batch/destructive operations lack explicit verify-then-proceed feedback loops, capping the score at 3.	3 / 5
Progressive Disclosure	Has clear section headers, but the ~450-line body inlines material that belongs in separate files (Cloud migration, advanced features, full CLI/API reference) and signals no external references at all.	3 / 5
	Total	12 / 20 Passed

Description

75%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 and distinct, listing concrete capabilities in third person without fluff. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the 'when to use' question only weakly implied.

Suggestions

Append an explicit trigger clause, e.g. 'Use when working with VCF/BCF files, building cohort variant databases, or querying variant data across many samples.'

Add common synonyms and file extensions users would say, such as '.vcf', '.bcf', 'variant calls', and 'genomics', to broaden trigger term coverage.

Keep the existing concrete action list but ensure the trigger clause references the same domain terms so 'what' and 'when' are both explicit.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—'VCF/BCF ingestion', 'incremental sample addition', 'compressed storage', 'parallel queries', and 'export capabilities'—giving comprehensive coverage of the tool's surface.	5 / 5
Completeness	Clearly answers 'what' the skill does, but provides no explicit 'Use when...' trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes strong domain keywords users would say ('VCF/BCF', 'genomic variant data', 'population genomics'), but is missing explicit synonyms and file extensions like '.vcf' or '.bcf' that anchor 5 requires.	4 / 5
Distinctiveness Conflict Risk	The combination of 'genomic variant data using TileDB', 'VCF/BCF', and 'population genomics' carves a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/tiledbvcf/SKILL.md
Commit: b2a92ba

Reviewed: 3 days 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.