CtrlK
BlogDocsLog inGet started
Tessl Logo

pathml

Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.

69

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 is well-structured with strong progressive disclosure and a working quick-start example, but the multi-step workflows lack explicit validation/feedback loops and the reference navigation is restated across sections.

Suggestions

Add explicit validation checkpoints to the numbered workflows (e.g., verify segmentation quality on a sample tile before running across the whole slide; assert held-out metrics meet a threshold before deployment).

Provide a short executable snippet for the CODEX and ML-training workflows to match the actionability of the H&E quick-start example.

Consolidate the 'References to Detailed Documentation' and 'Resources' sections into one to remove duplicate navigation and tighten conciseness.

DimensionReasoningScore

Conciseness

Efficient overview with a focused code example, but the 'Resources' and 'References to Detailed Documentation' sections partly restate the per-section 'See' pointers, adding minor padding.

4 / 5

Actionability

Provides one complete, executable H&E pipeline example and names key transforms/models, but the numbered Common Workflows for CODEX and ML training are high-level hints without accompanying code.

4 / 5

Workflow Clarity

Three numbered workflows are sequenced, but they involve batch/ML-training operations with only implicit validation checkpoints (e.g., 'Evaluate on held-out test sets') and no explicit validate-fix-retry feedback loops.

3 / 5

Progressive Disclosure

Clear overview with well-signaled, one-level-deep references to six real, organized reference files; navigation is easy and content is appropriately split out of the main file.

5 / 5

Total

16

/

20

Passed

Description

100%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 concise yet comprehensive, naming concrete capabilities, natural trigger terms, and an explicit use-when clause while also carving out a distinct niche against a neighboring tool.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (multiplexed immunofluorescence, nucleus segmentation, tissue graph construction, ML model training) with comprehensive coverage of the pathology toolkit's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (full-featured computational pathology toolkit with listed capabilities) and 'when' via a concrete 'Use for...' clause enumerating trigger scenarios.

5 / 5

Trigger Term Quality

Rich natural terms users would say (WSI, CODEX, Vectra, immunofluorescence, nucleus segmentation, H&E, histolab) including platform synonyms and modality names.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear computational-pathology niche and explicitly distinguishes itself from histolab for simple tile extraction, minimizing wrong-skill triggering.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
synthetic-sciences/openscience
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.