acronym-unpacker

Intelligent medical abbreviation disambiguation tool that resolves ambiguous acronyms using clinical context, specialty-specific knowledge, and document-level semantic analysis.

Quality

57%

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/acronym-unpacker/SKILL.md

Quality

Content

56%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 is actionable with concrete commands and a real script, but it is padded with repeated descriptions and governance boilerplate, has duplicated References sections and broken cross-references, and inlines content that would be better split into reference files.

Suggestions

Remove the verbatim description restatements (header, When to Use, Key Features, references file) so the value proposition appears once; this is the biggest conciseness win.

Collapse the duplicated `## References` sections and replace vague non-file entries ('Medical abbreviation standards') with the real audit-reference.md link already present.

Fix or remove the broken 'See `## Features`/`## Usage`/`## Workflow` above' pointers, which reference sections that appear later in the document.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the description is restated verbatim three or more times, and large templated governance blocks (Implementation Details, Output Requirements, Response Template, risk/security tables, Lifecycle Status) pad the document. It is not a 3 because the repetition and boilerplate exceed 'some unnecessary explanation,' and not a 1 because genuine useful content (usage, params, acronym table) is present.	2 / 5
Actionability	It provides concrete, copy-paste-ready commands (`python scripts/main.py PID`, `--context`, `--list`, `py_compile`, `--help`), a parameters table, and a real output example covering common cases. It is not a 5 because batch/document processing is described as a feature but no command is shown, leaving a minor gap.	4 / 5
Workflow Clarity	A sequenced 5-step Workflow with an explicit fallback path plus a `py_compile` Quick Check checkpoint gives a clear sequence with most checkpoints present. It is not a 5 because the validate->fix->retry feedback loop is weak and several cross-references ('See `## Workflow` above') point to sections that appear below them.	4 / 5
Progressive Disclosure	A real bundle exists (scripts/main.py, references/audit-reference.md) with a working one-level link, but governance/process boilerplate is inlined rather than split out and the References section is duplicated with vague entries that do not correspond to actual files. It is not a 4 due to the inlined boilerplate and noisy/buried references, and not a 2 because structure and a working reference link are present.	3 / 5
	Total	13 / 20 Passed

Description

58%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, specific capability for medical-acronym disambiguation but omits any explicit "Use when..." trigger guidance, which caps completeness. Trigger-term coverage is adequate but lacks natural user phrasings.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when expanding or disambiguating medical acronyms/abbreviations in clinical notes or research text.'

Include natural user-facing synonyms such as 'expand,' 'decode,' and 'spell out' alongside 'acronym' and 'abbreviation' to improve trigger-term quality.

Clarify when this skill is preferred over a general medical-text skill to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	Names the medical-acronym domain plus several concrete mechanisms — "resolves ambiguous acronyms," "clinical context," "specialty-specific knowledge," "document-level semantic analysis" — which is several specific actions with only minor coverage gaps. It stops short of 5 because it presents one composite capability rather than a list of distinct, separately-executable actions.	4 / 5
Completeness	It gives a clear "what" (resolving ambiguous medical acronyms) but no "Use when..." clause or equivalent trigger guidance; the rubric caps completeness at 3 for a missing explicit trigger clause. It is not a 2 because the "what" is clear rather than vague.	3 / 5
Trigger Term Quality	It includes real relevant terms ("acronym," "abbreviation," "medical") but is missing common natural synonyms users would actually say ("expand," "decode," "spell out") and leans on technical jargon ("disambiguation"). Coverage is present but thin on natural user phrasings, so it is not a 4.	3 / 5
Distinctiveness Conflict Risk	It targets a clear medical-acronym niche and is unlikely to trigger for unrelated skills, with only minor overlap risk against broader medical-text skills. It is not a 5 because context-based "disambiguation" is somewhat broad within medical NLP.	4 / 5
	Total	14 / 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/acronym-unpacker/SKILL.md
Commit: 63c61d3

Reviewed: 2 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.