CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

medical-imaging-review

Write comprehensive literature reviews for medical imaging AI research. Use when writing survey papers, systematic reviews, or literature analyses on topics like segmentation, detection, classification in CT, MRI, X-ray, ultrasound, or pathology imaging. Triggers on requests f...

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/medical-imaging-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A well-structured instruction-only skill body: lean, template-driven, with excellent bundle organization and real validation/error-handling guidance. Its remaining gaps are the deferred workflow detail and slight boilerplate around input validation.

Suggestions

Add a one-line ordered list of the 7 phase names in the body so the core sequence is visible without opening WORKFLOW.md, strengthening workflow clarity.

Compress the Input Validation refusal block into a single sentence (or merge it into Error Handling) to trim the last padded section.

DimensionReasoningScore

Conciseness

The body is dense tables, checklists, and templates with no explanation of concepts Claude already knows — hedging rules, metric formats ("Dice (0.XXX), HD95 (X.XX mm)"), and citation patterns are all skill-specific. Only minor trimmable padding remains (the boilerplate Input Validation block and the source-attribution line), so it sits at 'efficient; minor instances of over-explanation'.

4 / 5

Actionability

Concrete, copy-adaptable guidance throughout: a full review-structure markdown skeleton, a method-description template with literal fill-in slots ("Achieves Dice of X.XX on [dataset]"), citation pattern examples, named MCP tools (`search_papers`, `pubmed_search_articles`, `zotero_search_items`), and exact reference-count targets (80–120). Not 5 because the core 7-phase sequence is deferred to WORKFLOW.md and the Quick Start's initialization steps don't state what to put in each file (pointed to TEMPLATES.md instead).

4 / 5

Workflow Clarity

Quick Start gives a clear 3-step initialization sequence, and the Input Validation and Error Handling sections act as explicit checkpoints (state missing fields, stop on out-of-scope, report failure with manual fallback), reinforced by the QUALITY_CHECKLIST.md pre-submission reference. Not 5 because no inline validate→fix→retry loop exists and the actual phase-by-phase sequencing lives in the referenced WORKFLOW.md rather than the body.

4 / 5

Progressive Disclosure

The body is a genuine overview and all five bundle files (WORKFLOW.md, TEMPLATES.md, DOMAINS.md, MCP_SETUP.md, QUALITY_CHECKLIST.md) exist on disk, are each referenced exactly once-level-deep from the body, and are indexed in a purpose table — clear navigation and an appropriate content split with no orphaned or nested references.

5 / 5

Total

17

/

20

Passed

Description

75%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.

A well-formed description with a clear what/when pair, strong domain keywords, and a defensible niche. Its main defect is that it is physically truncated mid-sentence ("Triggers on requests f..."), which cuts off the explicit trigger phrases and makes the skill look unfinished.

Suggestions

Repair the truncation: the description ends mid-sentence at 'Triggers on requests f...' — restore or rewrite the full closing clause so the trigger guidance is not visibly cut off.

Complete the trigger clause with concrete user phrasings, e.g., 'Use when the user asks for a literature review, survey, or systematic review of medical imaging AI methods (segmentation, detection, classification).'

Add common synonyms such as 'review paper' or 'state-of-the-art survey' to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

"Write comprehensive literature reviews for medical imaging AI research. Use when writing survey papers, systematic reviews, or literature analyses" names several concrete deliverables plus specific tasks (segmentation, detection, classification) and modalities (CT, MRI, X-ray, ultrasound, pathology), matching the anchor 'Lists several specific actions; minor gaps in coverage'. Not a 5 because the final trigger clause is cut off mid-sentence ("Triggers on requests f..."), leaving coverage visibly incomplete.

4 / 5

Completeness

Both parts are explicitly answered: a clear 'what' ("Write comprehensive literature reviews for medical imaging AI research") and an explicit 'when' ("Use when writing survey papers, systematic reviews, or literature analyses..."). Not 5 because the description terminates mid-sentence, leaving the intended trigger guidance incomplete rather than concrete and fully explicit.

4 / 5

Trigger Term Quality

Natural user phrasings are present — "survey papers", "systematic reviews", "literature analyses", "medical imaging" — plus task and modality keywords, matching the 'good keyword coverage; a few natural terms missing' anchor. Not 5 because common synonyms (e.g., "review paper", "literature search") are absent and the truncated closing sentence drops the concrete trigger phrasings it presumably contained.

4 / 5

Distinctiveness Conflict Risk

The "medical imaging AI" domain qualifier plus named modalities and tasks carve a clear niche with minimal conflict risk, but generic deliverable terms like "survey papers" and "systematic reviews" could also match a general academic-writing or clinical systematic-review skill, matching 'mostly distinct; minor overlap risk with closely related skills'.

4 / 5

Total

16

/

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/Academic Writing/medical-imaging-review/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.