CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

histolab

Digital pathology image processing toolkit for whole slide images (WSI). Supports WSI formats (SVS, TIFF, NDPI), tile-based analysis, and histological image preprocessing workflows.

Quality

64%

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/histolab/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 skill body is highly actionable, with real API usage and well-signaled one-level-deep references that all exist in the bundle. Its main weaknesses are verbosity from duplicated content (the Resources section and redundant workflow examples) and a batch multi-slide workflow that lacks validation/verification steps, which caps workflow clarity.

Suggestions

Remove the '## Resources' section (or reduce it to a one-line-per-file list) — it duplicates the inline 'Reference:' blocks nearly verbatim.

Trim Workflows 1–3, which restate the Core Capabilities examples; keep the genuinely additive ones (multi-slide batch, custom filtering) or move workflow detail into the existing references.

Add validation to the batch Workflow 4: verify expected tile counts per slide, wrap per-slide processing in error handling, and report/flag failed slides instead of proceeding blindly.

DimensionReasoningScore

Conciseness

The body is noticeably padded: the '## Resources' section (~55 lines) repeats the per-capability 'Reference:' blocks nearly verbatim, Workflows 1–3 largely restate the Core Capabilities examples, and comments like '# Load slide' explain what Claude already knows. This fits 'several unnecessary explanations or padded sections' more than 'mostly efficient' (3), especially given ~700 lines for a file whose detail belongs in the provided references.

2 / 5

Actionability

Extensive concrete, parameterized, mostly copy-paste-ready code covering all common cases (random/grid/score tiling, masks, filter pipelines, visualization, reporting). It falls short of fully executable: e.g. `filtered_tile = tile.apply_filters(tissue_detection)` uses an undefined `tile` variable, a minor gap characteristic of score 4.

4 / 5

Workflow Clarity

Sequences are clear and preview checkpoints exist ('Always preview with locate_tiles() before extracting', 'Verify tissue is present using thumbnails'), but Workflow 4 is a batch multi-slide operation with no validation or verification step — no per-slide output check, no error handling, no failure recovery. Per the rubric's scoring notes, a missing feedback loop in a batch context caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Bundle structure is solid: all five referenced files exist, are cited inline with clearly signaled 'Reference:' blocks plus a Resources map, and are exactly one level deep with no nested references. However, the duplicated reference listings and the large amount of inline detail keep the main file from being the lean 'clear overview' of score 5 — this is 'good structure; minor organization gaps'.

4 / 5

Total

13

/

20

Passed

Description

61%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 names a distinct, well-bounded niche and includes useful format triggers (WSI, SVS, TIFF, NDPI), but it omits any 'when to use' trigger guidance and leans on generic phrasing ('image processing toolkit', 'preprocessing workflows') instead of the library's concrete capabilities like tile extraction and tissue segmentation. It is serviceable but sits below the strong-example bar.

Suggestions

Add an explicit trigger clause, e.g. 'Use when processing histopathology slides, extracting tiles from gigapixel WSIs, or segmenting tissue regions for computational pathology pipelines.'

Replace generic phrasing ('image processing toolkit', 'preprocessing workflows') with concrete actions the library performs, such as 'detects tissue regions, extracts tiles, applies filters, and builds tile datasets for deep learning'.

Include natural synonyms users would say — 'histopathology', 'H&E', 'IHC', 'tissue segmentation' — to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Concrete elements like 'tile-based analysis' and 'Supports WSI formats (SVS, TIFF, NDPI)' are present, but 'image processing toolkit' and 'histological image preprocessing workflows' are generic, and key actions (tissue detection, tile extraction, mask segmentation) are never named. This matches 'names domain and 1-2 concrete actions' rather than the 'several specific actions' of score 4.

3 / 5

Completeness

The 'what' is reasonably clear (toolkit supporting WSI formats, tile-based analysis, preprocessing), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Good natural coverage: 'whole slide images', 'WSI', 'digital pathology', plus concrete file formats 'SVS, TIFF, NDPI'. Common user phrases like 'histopathology', 'H&E', or 'tissue' are missing, so it falls short of the comprehensive synonym/extension coverage of score 5.

4 / 5

Distinctiveness Conflict Risk

Digital pathology / whole slide images is a clear niche with distinct format-level triggers, but 'image processing toolkit' and 'preprocessing workflows' phrasing leaves minor overlap risk with general image-processing or broader medical-imaging skills, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict profile of score 5.

4 / 5

Total

14

/

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (704 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Data Analysis/histolab/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.