bio-ontology-mapper

Map unstructured biomedical text to standardized ontologies (SNOMED CT.

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/bio-ontology-mapper/SKILL.md

Quality

Content

38%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 genuinely useful, specific material (ontology table, code examples, pitfalls, quality checklist), but it is padded with redundant sections and mismatched template boilerplate, and its file references are largely fabricated against the actual bundle. The code examples cannot run against the provided scripts.

Suggestions

Reconcile the References and Scripts sections with the actual bundle: describe mesh_sample.json, snomed_sample.json, and synonyms.json, and remove the nonexistent .md and .py files.

Make the code examples executable against the bundle or clearly label them as illustrative API sketches distinct from the shipped `scripts/main.py` CLI.

Remove the redundant Quick Check / Audit-Ready Commands / Example Usage duplication (one compile-check command is enough) and delete the stub 'Implementation Details' section that only points back to Workflow.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: multiple redundant sections repeat the same content (`python -m py_compile scripts/main.py` appears in Quick Check, Audit-Ready Commands, and Example Usage), the 'When to Use' bullets restate the truncated description verbatim, and the 'Implementation Details' section is a stub pointing back to '## Workflow above'.	2 / 5
Actionability	Concrete code examples (map_text, cross_map, batch_map, score_mapping), a parameters table, and CLI commands are present, but the flagship examples import `from scripts.mapper import BioOntologyMapper` and `mapper.py` is not in the bundle, so they are not executable as written.	3 / 5
Workflow Clarity	A numbered Workflow and a compile-check checkpoint exist, but the batch-normalization operation lacks an output validation step; per the rubric, missing validation for batch operations caps workflow clarity at 3.	3 / 5
Progressive Disclosure	The body lists 6 reference .md files and 8 script .py files that do not exist in the bundle, while the actual references/ (mesh_sample.json, snomed_sample.json, synonyms.json) are never mentioned and scripts/ contains only main.py — navigation is broken.	2 / 5
	Total	10 / 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 establishes a clear, distinct niche (biomedical text to standardized ontologies) but is malformed — an unclosed parenthesis truncates the ontology list and the 'when to use' trigger guidance is entirely missing. It reads as a cut-off sentence rather than a complete description.

Suggestions

Close the malformed sentence and complete the ontology list, e.g. 'Map unstructured biomedical text to standardized ontologies (SNOMED CT, MeSH, ICD-10, LOINC, RxNorm).'

Add an explicit 'Use when...' trigger clause naming natural user phrases such as 'normalize clinical terms', 'map to SNOMED', or 'crosswalk ontologies'.

Include natural synonyms and file extensions users might say (e.g. 'clinical text', 'terminology normalization', '.csv', '.json') to raise trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('unstructured biomedical text', 'standardized ontologies') and one concrete action ('Map ... to standardized ontologies'), but the ontology list is cut off after SNOMED CT so coverage is not comprehensive.	3 / 5
Completeness	A clear 'what' is stated ('Map unstructured biomedical text to standardized ontologies') but there is no 'Use when...' or equivalent trigger clause, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Relevant natural terms like 'biomedical text' and 'SNOMED CT' are present, but the truncated list omits common synonyms (clinical text, MeSH, ICD-10, LOINC, RxNorm) and any file extensions.	3 / 5
Distinctiveness Conflict Risk	The biomedical ontology-mapping niche is fairly distinct with low overlap risk; the only weakness is the truncated trigger list that limits how specifically it can be distinguished.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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/bio-ontology-mapper/SKILL.md
Commit: 63c61d3

Reviewed: 6 hours ago

Table of Contents

Discovery Implementation Validation

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.