scvelo

RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.

Quality

73%

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/scvelo/SKILL.md

Quality

Content

71%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 highly actionable, well-sequenced skill body with strong code and reference tables, held back by concept padding and by inlining content that duplicates existing bundle files rather than pointing to them.

Suggestions

Trim the Overview's restatement of RNA-velocity fundamentals and the 'leading Python package' claim to assume Claude's existing knowledge.

Replace the inlined 'Complete Workflow Script' with a pointer to scripts/rna_velocity_workflow.py and the inline velocity-model detail with a reference to references/velocity_models.md, keeping only minimal inline examples.

Add an explicit validation checkpoint (e.g. verify required layers and velocity coherence) between preprocessing and velocity estimation in the body workflow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code/tables, but the Overview paragraph restates known concepts (what RNA velocity is, unspliced/spliced kinetics) and asserts scVelo is 'the leading Python package', which is padding Claude does not need.	3 / 5
Actionability	Provides copy-paste-ready, executable code across an 8-step workflow, a complete reusable function, an output-fields reference table, and a troubleshooting matrix covering the common cases.	5 / 5
Workflow Clarity	The 8 numbered steps and bundled script give a clear, ordered sequence with input asserts, but the inline body steps lack explicit validate-before-proceeding checkpoints between stages.	4 / 5
Progressive Disclosure	Sections are well-organized, but the body inlines a 'Complete Workflow Script' and a velocity-models comparison that duplicate the provided scripts/ and references/ bundle files without linking to them, so the actual references go unsignaled.	3 / 5
	Total	15 / 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.

A specific, well-scoped description with strong capability enumeration and low conflict risk, weakened only by the absence of an explicit 'Use when...' trigger clause.

Suggestions

Add an explicit trigger clause, e.g. 'Use when analyzing RNA velocity, inferring cell-state transitions, or ordering cells along a splicing-derived pseudotime in single-cell RNA-seq data.'

Include a few natural synonyms/users' phrasings (e.g. 'cell fate', 'pseudotime', 'spliced/unspliced') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Estimate cell state transitions', 'infer trajectory directions', 'compute latent time', and 'identify driver genes' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause; 'Complements Scanpy/scVI-tools for trajectory inference' only weakly implies the when, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes strong domain-natural terms like 'RNA velocity', 'single-cell RNA-seq', 'trajectory', and 'unspliced/spliced mRNA', but is missing common synonyms or a file/data trigger phrase.	4 / 5
Distinctiveness Conflict Risk	The scVelo/RNA-velocity/unspliced-spliced niche is distinct with specific triggers and minimal overlap with adjacent Scanpy/scVI 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/scvelo/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.