tooluniverse-spatial-transcriptomics

Analyze spatial transcriptomics data to map gene expression in tissue architecture. Supports 10x Visium, MERFISH, seqFISH, Slide-seq, and imaging-based platforms. Performs spatial clustering, domain identification, cell-cell proximity analysis, spatial gene expression patterns, tissue architecture mapping, and integration with single-cell data. Use when analyzing spatial transcriptomics datasets, studying tissue organization, identifying spatial expression patterns, mapping cell-cell interactions in tissue context, characterizing tumor microenvironment spatial structure, or integrating spatial and single-cell RNA-seq data for comprehensive tissue analysis.

Quality

75%

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/bio/tooluniverse-spatial-transcriptomics/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured with an explicit 8-phase workflow and real library calls, but it is over-long, includes undefined placeholder functions, lacks validation feedback loops beyond QC, and keeps everything inline rather than splitting detail into reference files.

Suggestions

Move the ~100-line sample report (lines 591-698) and per-phase code detail into reference files under ./references/ and link to them one level deep, leaving SKILL.md a lean overview.

Replace or implement undefined helpers ('detect_pattern_type', 'extract_signatures') and verify cell2location/scanpy API calls so the code is copy-paste executable rather than pseudocode.

Add explicit validate→fix→retry checkpoints to the clustering and deconvolution phases, mirroring the QC feedback loop, and trim duplicated trigger/capability lists that restate the description.

Dimension	Reasoning	Score
Conciseness	Mostly executable but padded: a ~100-line fully-fleshed sample report (lines 591-698), trigger/capability lists that duplicate the description, and docstrings explaining concepts Claude already knows (Moran's I semantics). Not a 3 because not every token earns its place; not a 1 because the code is concrete rather than abstract padding.	2 / 3
Actionability	Provides real scanpy/squidpy/cell2location calls, but several functions call undefined placeholders ('detect_pattern_type', 'extract_signatures') and use questionable API calls ('mod.get_cell_type_fractions()', passing a Series to sc.pl.spatial color=), leaving guidance incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	The 8-phase workflow is clearly sequenced with an ASCII diagram and per-phase objectives, but explicit validate→fix→retry feedback loops appear only in Phase 1 QC; later heavy steps (clustering, deconvolution) lack checkpoints, capping clarity at 2.	2 / 3
Progressive Disclosure	No bundle files exist and SKILL.md is a monolithic 789-line document; the full sample report and detailed phase code that belong in separate reference files are inline. It is well-sectioned (not poorly organized), so it sits at 2 rather than 1.	2 / 3
	Total	8 / 12 Passed

Description

100%

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 strong, specific description in third-person voice that clearly enumerates capabilities and provides explicit 'Use when' triggers covering the major spatial transcriptomics use cases.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'spatial clustering, domain identification, cell-cell proximity analysis, spatial gene expression patterns, tissue architecture mapping, and integration with single-cell data' — matching the score-3 anchor.	3 / 3
Completeness	Explicitly states what it does and includes a 'Use when analyzing...' clause with concrete triggers, answering both what and when.	3 / 3
Trigger Term Quality	Uses natural terms users would say ('spatial transcriptomics datasets, tissue organization, tumor microenvironment, cell-cell interactions, single-cell RNA-seq') in third-person voice ('Analyze', 'Supports', 'Performs'), with no first/second person.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (spatial transcriptomics across named platforms) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (789 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/tooluniverse-spatial-transcriptomics/SKILL.md
Commit: df37802

Reviewed: 2 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.