Conciseness

The body is dominated by dense, executable code and reference tables with little filler, matching the efficient-with-minor-trim-instances anchor. The Overview paragraph explaining mRNA splicing biology and the duplication between the 8-step walkthrough and the 'Complete Workflow Script' (plus the Velocity Models table duplicating references/velocity_models.md) are the over-explanation instances that keep it below the every-token-earns-its-place anchor at 5.

Actionability

Every section provides copy-paste-ready, fully executable code with real parameters (scv.pp.filter_and_normalize(adata, min_shared_counts=20), scv.tl.recover_dynamics(adata, n_jobs=4), concrete plotting calls) plus a complete runnable pipeline function, matching the fully-executable/covers-common-cases anchor. It is not score 4 because there are no gaps — installation, loading, preprocessing, both model modes, and all downstream visualizations are concrete.

Workflow Clarity

The workflow is clearly sequenced as numbered steps 1-8 with layer verification at setup (print(adata) with expected-structure comments), sanity checks in Best Practices, and a Troubleshooting table providing problem-to-solution feedback; this matches the clear-sequence/most-checkpoints anchor. It is not 5 because validation between intermediate steps is implicit rather than explicit (e.g., no checkpoint that velocity genes or fit_likelihood look sane before downstream analysis), and not 3 because checkpoints and error-recovery guidance are present, just unevenly distributed.

Progressive Disclosure

The body is well-sectioned internally, but neither bundle file is referenced anywhere — references/velocity_models.md (168 lines of model math) and scripts/rna_velocity_workflow.py (240-line validated pipeline with asserts) are orphaned from navigation, and the inline Velocity Models Comparison table duplicates the reference file. This matches the some-structure/references-not-clearly-signaled/content-that-should-be-separate-is-inline anchor; it is not 2 because the body itself has clear headers and is not a monolithic wall of text, and not 4 because a key structural duty (linking the existing deeper material) is entirely missing.

Specificity

The description lists four concrete, comprehensive actions: "Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes" — each names a specific capability with the underlying mechanism, matching the multiple-specific-actions/comprehensive-coverage anchor. It is not score 4 because coverage has no meaningful gaps for this tool's capability set; not below because every action is concrete rather than generic.

Completeness

"What" is clearly answered with concrete actions, but there is no explicit "Use when..." clause; "Complements Scanpy/scVI-tools for trajectory inference" describes ecosystem positioning rather than explicit trigger guidance, so per the judging guidelines completeness is capped at 3. It fits the clear-what/weakly-implied-when anchor exactly — not 4 because the when-guidance is not actionable trigger phrasing, not 2 because the what is concrete and specific.

Trigger Term Quality

Good natural keyword coverage: "RNA velocity", "scVelo", "single-cell RNA-seq", "cell state transitions", "trajectory", "driver genes", "latent time" — terms users of this domain would actually say. A few natural variations are missing (e.g., "pseudotime", "scRNA-seq", mention of unspliced/spliced loom/h5ad inputs), which keeps it below the comprehensive-with-synonyms anchor at 5.

Distinctiveness Conflict Risk

"RNA velocity analysis with scVelo" names a specific tool and a specific analysis — a clear niche with distinct triggers and minimal conflict risk (only adjacent tools like velocyto/dynamo could overlap, and the explicit scVelo naming disambiguates). Matches the clear-niche anchor; not lower because nothing in the description is generic enough to collide with unrelated skills.