spatial-transcriptomics-mapper

Map spatial transcriptomics data from 10x Genomics Visium/Xenium onto.

Quality

60%

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 ./scientific-skills/Data Analysis/spatial-transcriptomics-mapper/SKILL.md

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 content is highly actionable and well-structured for the core task, with accurate parameters and examples against the real script, but it is padded with generic boilerplate, repeats validation commands, contains broken cross-references, and documents non-existent scripts and flags.

Suggestions

Remove or collapse the generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) that are not specific to spatial transcriptomics, or move them into a separate reference file.

Fix broken references: delete the "Quick Start - Test Data" block (generate_test_data.py does not exist), remove the absent requirements.txt pointer, and drop the non-existent --hires/--downsample notes from the Notes section.

Correct the "See `## X` above" pointers in Key Features, Dependencies, Example Usage, and Implementation Details, since those target sections appear later in the file, not above.

Dimension	Reasoning	Score
Conciseness	The 415-line body carries substantial generic templated boilerplate (Risk Assessment table, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template, Input Validation) plus repeated py_compile/--help commands across Quick Check, Audit-Ready Commands, and Example Usage, matching the "noticeably verbose; several unnecessary padded sections" anchor rather than the mostly-efficient 3.	2 / 5
Actionability	Usage, Parameters, Examples, Input File Structure, and API Usage give concrete, copy-pasteable commands and code that match the real main.py interface, but "Quick Start - Test Data" invokes a non-existent generate_test_data.py and Notes reference phantom --hires/--downsample flags, which are minor gaps keeping it just below fully-executable 5.	4 / 5
Workflow Clarity	The Workflow section lists a clear 5-step sequence with an explicit scope-validation gate (step 2) and a fallback path on failure (step 5), plus a py_compile Quick Check; it is not 5 because per-data validation checkpoints are implicit rather than concrete commands.	4 / 5
Progressive Disclosure	The body is well-sectioned but monolithic at ~415 lines with no separate reference files (none exist under references/ or assets/), and several "See `## X` above" pointers (Key Features, Dependencies, Example Usage, Implementation Details) point to sections that are actually below them, matching the "some structure but poorly signaled references, content that should be separate is inline" anchor.	3 / 5
	Total	13 / 20 Passed

Description

65%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 targets a specific, distinctive niche but is grammatically truncated ("...onto.") and omits any explicit "Use when..." trigger clause, capping completeness. It is recognizable and low-conflict but not fully actionable as a trigger description.

Suggestions

Complete the sentence and name the target, e.g. "Map spatial transcriptomics data from 10x Genomics Visium/Xenium onto tissue section images to visualize gene-expression distribution."

Add an explicit trigger clause such as "Use when working with Visium or Xenium output, spatial gene-expression mapping, or tissue-coordinate clustering."

List 1-2 more concrete actions (e.g. spatial clustering visualization, multi-gene overlay) to lift specificity from 3 toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain ("spatial transcriptomics data from 10x Genomics Visium/Xenium") and one concrete action ("Map ... onto"), matching the anchor that names a domain plus 1-2 concrete actions but is not comprehensive; the action is also grammatically truncated at "onto".	3 / 5
Completeness	It states a clear "what" (map spatial transcriptomics data) but provides no "when" / "Use when..." trigger guidance, so per the judging guideline completeness is capped at 3; it is not 4 because the "when" is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	Includes strong natural domain keywords a user would say ("spatial transcriptomics", "10x Genomics", "Visium", "Xenium") with platform synonyms, but lacks file-extension-level terms, so it sits at good-but-not-comprehensive coverage rather than 5.	4 / 5
Distinctiveness Conflict Risk	The Visium/Xenium spatial transcriptomics niche is highly specific with distinct triggers and minimal overlap with other skills; the truncation does not undermine its distinctiveness, so it lands on the clear-niche anchor rather than the 4 anchor.	5 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/spatial-transcriptomics-mapper/SKILL.md
Commit: f5ef65b

Reviewed: ~9 hours 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.