CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

medical-unit-converter

Convert medical laboratory values between units (mg/dL to mmol/L, etc.) with formula transparency and clinical reference ranges. Supports glucose, cholesterol, creatinine, and hemoglobin conversions.

Quality

70%

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/Other/medical-unit-converter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 delivers genuinely actionable reference material — exact conversion factors, CLI contract, output schema, and verification commands — but dilutes it with generic workflow/response boilerplate and developer-facing implementation notes. The bundle compounds this: references/guidelines.md is orphaned and empty, and batch conversion is advertised without any operational support.

Suggestions

Replace the generic 5-step Workflow with the actual operational sequence (validate inputs → run scripts/main.py with the documented flags → check output against the reference-range table → fall back to the manual factor from the conversion table on failure), including an explicit verification checkpoint for batch table conversions.

Either link and populate references/guidelines.md (real SI-conversion standards content) or delete it; also drop or drastically trim the "Implementation Notes (for script developer)" section since the script already exists in the bundle.

Cut the abstract Response Template and Workflow boilerplate ("non-negotiable constraints", "Assumptions/Risks/Next Checks") down to the fields actually used, and add a one-line example of how a batch table conversion is performed.

DimensionReasoningScore

Conciseness

Mostly efficient — the conversion table, input parameters, output JSON, and Quick Check are dense and earn their tokens — but several sections are generic padding: the "Workflow" steps ("Confirm the user objective, required inputs, and non-negotiable constraints"), the abstract "Response Template" (Objective/Inputs/Assumptions/Workflow/Deliverable/Risks/Next Checks), and "Implementation Notes (for script developer)" that re-specifies how to write a script that already exists in the bundle. Not a 4 because these three sections contain noticeably more boilerplate than the anchor's "minor instances of over-explanation".

3 / 5

Actionability

Strong concrete guidance: an exact factor table for all 8 conversion pairs, executable CLI parameters, a copy-paste Quick Check ("python scripts/main.py --value 100 --from-unit mg_dl --to-unit mmol_l --analyte glucose"), a concrete output JSON example, and specific error messages ("Error: --value must be a numeric value."). Not a 5 because the Workflow's "Use the packaged script path or the documented reasoning path" is vague hand-waving rather than a concrete invocation, and the batch-conversion use case has no example of how to actually perform it.

4 / 5

Workflow Clarity

The 5-step Workflow is present but written as generic boilerplate ("Confirm the user objective... Return a structured result that separates assumptions, deliverables, risks") rather than a concrete operational sequence with commands; validation checkpoints are implicit (left to the separate Error Handling section). It is also capped at 3 per the rubric: "Batch-converting lab result tables" is an advertised use case, yet no validation/verification step exists for batch operations. Not a 2 because Error Handling and the Fallback Template do supply explicit recovery paths for missing inputs, unsupported pairs, and script failure.

3 / 5

Progressive Disclosure

The body is well-sectioned and correctly points to the real bundle script (scripts/main.py in Quick Check and Error Handling), but the actual bundle structure undercuts it: references/guidelines.md exists yet is never referenced or linked anywhere in the body, and its content is two empty bullet headings ("SI Unit Conversions", "Clinical Laboratory Standards") with no substance. Per the rubric guideline to score against the actual bundle, this is "some structure but could be better organized; references present but not clearly signaled." Not a 4 because an orphaned, contentless reference file is more than a minor organization gap.

3 / 5

Total

13

/

20

Passed

Description

70%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 specific, well-scoped third-person description that clearly conveys what the skill does and which analytes it covers. Its main weakness is the complete absence of a "Use when..." trigger clause, which caps completeness and leaves the description dependent on keyword luck for invocation.

Suggestions

Add an explicit trigger clause, e.g. "Use when converting or verifying lab values such as glucose, cholesterol, creatinine, or hemoglobin between mg/dL, mmol/L, or g/L units."

Include common synonyms users would naturally say — "lab results", "SI units", "clinical chemistry" — to broaden trigger coverage.

Mention the batch table conversion capability the body advertises ("Batch-converting lab result tables") so the description's coverage matches the skill.

DimensionReasoningScore

Specificity

"Convert medical laboratory values between units (mg/dL to mmol/L, etc.) with formula transparency and clinical reference ranges. Supports glucose, cholesterol, creatinine, and hemoglobin conversions" names the domain, a concrete action (unit conversion with example units), and two supporting capabilities (formula transparency, reference ranges) plus the four supported analytes. Not a 5 because the only real action is "convert" — no mention of batch conversion or verification that the body claims — leaving minor coverage gaps.

4 / 5

Completeness

The "what" is clear and concrete (convert lab values between units with formula transparency and reference ranges for the four named analytes), but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description. Per the rubric guidelines, a missing explicit trigger clause caps completeness at 3; it is not a 4 because the "when" is entirely absent rather than merely weakly implied.

3 / 5

Trigger Term Quality

Good natural keyword coverage: users would say "convert glucose", "mg/dL to mmol/L", "lab values", "cholesterol", "creatinine", "hemoglobin", "reference ranges". Not a 5 because common synonyms like "lab results", "SI units", "unit conversion", or "clinical chemistry" are absent, so a few natural phrasings would not match.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — medical laboratory unit conversion for specific named analytes with clinical reference ranges — with distinct triggers (mg/dL, mmol/L, glucose, creatinine, etc.). A generic unit-conversion or general-medical skill would rarely be selected over it, so conflict risk is minimal; it is not below 5 because the trigger terms are unambiguous for this domain.

5 / 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/Other/medical-unit-converter/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.