CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pseudotime-trajectory-viz

Analyze data with `pseudotime-trajectory-viz` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.

Quality

51%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/pseudotime-trajectory-viz/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 delivers strong domain-specific actionability — complete CLI examples, a thorough parameter table, explicit input/output contracts, and executable preprocessing code — wrapped in a heavily padded shell of duplicated governance boilerplate. Progressive disclosure is underused: a real reference file exists but is never named, while reference-worthy material (methods detail, security checklists) is inlined.

Suggestions

Cut the redundant meta-sections (Key Features, Implementation Details, Output Requirements, Output Contract, Inputs to Collect, Input Validation, Validation and Safety Rules, Error Handling, Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) down to one consolidated workflow/safety section — they restate the same rules ~5 times across ~150 lines.

Replace the generic 'references/ contains supporting rules' pointer with a named link, e.g. '**Runtime rules**: See [references/runtime_checklist.md](references/runtime_checklist.md)', and move the Methods detail and Security/Risk boilerplate there.

Fix the inconsistent audit example: 'python scripts/main.py --input "Audit validation sample..." --format json' passes a prose string where the documented contract requires a .h5ad path — replace it with a real minimal .h5ad example or the --help smoke check only.

DimensionReasoningScore

Conciseness

Roughly 150 lines are redundant boilerplate: 'Key Features' restates the description, 'See `## Usage` above for related details' and 'See `## Workflow` above for related details' are filler, and 'Output Requirements', 'Output Contract', 'Inputs to Collect', 'Input Validation', 'Error Handling', 'Validation and Safety Rules', 'Risk Assessment', 'Security Checklist', 'Evaluation Criteria', and 'Lifecycle Status' repeatedly restate the same scope/validation/output-discipline rules. This is several padded sections beyond the 'some unnecessary explanation' of anchor 3; it is not 1 because the domain sections (Usage, Parameters, Methods, Input/Output formats) are dense and non-padding.

2 / 5

Actionability

Mostly executable guidance: complete CLI examples ('python scripts/main.py --input data.h5ad --start-cell stem_cell_cluster --method diffusion --output ./results'), a full 17-row parameter table with defaults, a concrete output file tree, and a runnable scanpy preprocessing snippet. Minor gap: the audit command passes a prose sentence as --input where the documented input contract requires a .h5ad AnnData path, so it would not run as written; this keeps it below anchor 5.

4 / 5

Workflow Clarity

A clear sequenced workflow exists ('1. Confirm the user objective... 2. Validate that the request matches the documented scope and stop early... 5. If execution fails... switch to the fallback path') with an explicit pre-execution smoke check ('python -m py_compile scripts/main.py') and a stated recovery path on failure. Not anchor 5 because validation guidance is scattered across many redundant sections rather than one explicit validate→fix→retry loop with checkpoints, leaving minor validation gaps.

4 / 5

Progressive Disclosure

The bundle has one reference file (references/runtime_checklist.md), but the body only says 'references/ contains supporting rules, prompts, or checklists' — never naming or linking the actual file, so the reference is present but not clearly signaled. Meanwhile content that belongs in references (four Methods subsections, Risk Assessment, Security Checklist) is inlined in a ~400-line body. This matches anchor 3; it is not 4 because key content is not appropriately split out and the reference is buried.

3 / 5

Total

13

/

20

Passed

Description

25%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 generic boilerplate that fails to convey the skill's actual domain (single-cell pseudotime trajectory analysis) or when to invoke it. It names no concrete domain capabilities, includes no natural trigger phrases, and provides no 'Use when' guidance, making it indistinguishable from any other data-analysis skill except by its embedded name.

Suggestions

State the concrete domain actions, e.g. 'Infer developmental trajectories from single-cell RNA-seq data, compute diffusion/slingshot/palantir pseudotime, plot lineage branching trees, and overlay gene expression dynamics along trajectories.'

Add an explicit trigger clause with natural user terms: 'Use when analyzing single-cell RNA-seq (scRNA-seq) data, .h5ad AnnData files, differentiation trajectories, lineage branching, or pseudotime ordering.'

Remove the process boilerplate ('reproducible workflow, explicit validation, structured outputs, review-ready interpretation') — it adds no domain signal and reads as filler.

DimensionReasoningScore

Specificity

The only stated action is the generic "Analyze data"; "reproducible workflow, explicit validation, and structured outputs" are process attributes, not capabilities, and no domain actions (pseudotime computation, trajectory plotting, lineage analysis) are named. It is not 1 because a concrete verb and the skill's domain name are present, and not 3 because no 1-2 concrete domain-specific actions are listed.

2 / 5

Completeness

The 'what' is vague ("Analyze data with `pseudotime-trajectory-viz` using a reproducible workflow...") and the 'when' is entirely absent — no 'Use when...' clause or equivalent trigger guidance exists, matching anchor 2 exactly and triggering the completeness cap. It is not 3 because the 'what' itself is not clear about what the skill actually does.

2 / 5

Trigger Term Quality

Keywords are limited to generic meta-terms ("data", "workflow", "validation", "outputs", "review-ready interpretation") that users would not naturally say; the natural domain phrases (single-cell, scRNA-seq, differentiation, trajectory, lineage) appear only inside the embedded skill name. Anchor 2 fits — one or two generic keywords while missing the natural phrases users actually use.

2 / 5

Distinctiveness Conflict Risk

The boilerplate template "Analyze data with X using a reproducible workflow, explicit validation, and structured outputs" would match virtually any data-analysis skill; only the embedded skill name provides any distinction. Very broad with high overlap risk against many similar analysis skills fits anchor 2; it is not 3 because the description language itself gives no niche beyond the skill name.

2 / 5

Total

8

/

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.

Validation — 15 / 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

Path

scientific-skills/Data Analysis/pseudotime-trajectory-viz/SKILL.md

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.