CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rare-disease-hpo-mapper

Map patient symptoms to Human Phenotype Ontology terms for gene diagnosis.

Quality

56%

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/Evidence Insight/rare-disease-hpo-mapper/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%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 contains a sound core (parameters, returns, an example mapping, error handling, a real script) but buries it under organizational boilerplate and broken cross-references. The documented parameters diverge from the actual script interface, and no runnable example with real symptom input is given.

Suggestions

Cut the generic filler sections (Key Features, Implementation Details, Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) or move them to a reference file; they consume the context window without task value.

Add a copy-paste-ready invocation with real input, e.g. `python scripts/main.py --symptoms "wide-set eyes,seizures,ataxia"`, and align the documented Parameters section with the script's actual CLI flags.

Fix the broken cross-references — 'See ## Prerequisites above' and 'See ## Workflow above' point to sections located below those callouts — and give references/audit-reference.md distinct content instead of duplicating the body.

DimensionReasoningScore

Conciseness

The ~190-line body is dominated by generic filler ("Scope-focused workflow aligned to...", "Structured execution path designed to keep outputs consistent and reviewable") and boilerplate audit sections (Risk Assessment, Security Checklist, Lifecycle Status) that teach nothing about the task. This matches 'Noticeably verbose; several unnecessary explanations or padded sections' rather than 3, where padding would be occasional rather than the majority of the body.

2 / 5

Actionability

It provides real executable commands ("python -m py_compile scripts/main.py", "python scripts/main.py --help") and a real example mapping, but no copy-paste invocation with actual symptom input, and the documented parameters (age_onset, inheritance_pattern) do not match the script's actual CLI (--symptoms only). This fits 'Some concrete guidance but incomplete; missing key details' — more than minor gaps for a 4, but genuinely executable for a 3.

3 / 5

Workflow Clarity

The Workflow section lists a coherent 5-step sequence with a fallback path and a compile Quick Check, but output validation is only implicit, and two internal cross-references are broken: "See `## Prerequisites` above" and "See `## Workflow` above" point to sections that appear below those callouts. This matches 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit' rather than 4, where gaps must be minor.

3 / 5

Progressive Disclosure

Both bundle files exist (scripts/main.py, references/audit-reference.md) and the reference is one level deep, clearly signaled in a References section. However, the reference merely duplicates body content (audit commands, fallback wording) instead of extending it, and meta content that belongs in separate files or nowhere (Key Features, Implementation Details, Lifecycle Status) is inlined, matching 'Some structure but could be better organized... content that should be separate is inline' rather than 4's 'minor organization gaps'.

3 / 5

Total

11

/

20

Passed

Description

53%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 states a clear, domain-specific capability but is a single bare sentence. It answers 'what' well yet provides no explicit 'when to use' trigger guidance and omits natural trigger terms like the HPO acronym and 'rare disease'.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when the user mentions HPO terms, rare disease diagnosis, phenotype mapping, or symptom-to-gene matching.'

Include natural synonyms and the acronym users would actually type: 'HPO', 'Human Phenotype Ontology', 'rare disease', 'phenotype standardization'.

Mention the additional concrete actions the skill performs (returns confidence scores, differential diagnosis genes, literature links) to lift specificity and completeness.

DimensionReasoningScore

Specificity

The description names the domain ("Human Phenotype Ontology... for gene diagnosis") and one concrete action ("Map patient symptoms to Human Phenotype Ontology terms"), matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It stays at 3 because the skill's other documented capabilities (confidence scores, differential diagnosis genes, literature links) are absent, and it is not 2 since the stated action is concrete rather than generic.

3 / 5

Completeness

The 'what' is clear (map symptoms to HPO terms), but there is no 'Use when...' clause or equivalent trigger guidance; 'for gene diagnosis' only weakly implies when to use it. Per the rubric guideline, a missing 'Use when...' clause caps completeness at 3, and it is not 2 because the 'what' is explicit.

3 / 5

Trigger Term Quality

It contains relevant keywords ("patient symptoms", "Human Phenotype Ontology", "gene diagnosis") but misses common variations users would naturally type: the acronym "HPO", "rare disease", and "phenotype". This fits 'Some relevant keywords but missing common variations or synonyms' rather than 4, since more than a few natural terms are missing.

3 / 5

Distinctiveness Conflict Risk

HPO term mapping for gene diagnosis is a clear niche with domain-specific terminology, giving 'mostly distinct; minor overlap risk' with closely related medical/bioinformatics skills. It does not reach 5 because the score-5 anchor expects explicit distinct trigger phrases, which this description lacks.

4 / 5

Total

13

/

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/Evidence Insight/rare-disease-hpo-mapper/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.