medical-scribe-dictation

Convert physician verbal dictation into structured SOAP notes. Trigger.

Quality

53%

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/Academic Writing/medical-scribe-dictation/SKILL.md

Quality

Content

53%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 concrete, executable usage guidance and well-signaled references, but is bloated with templated governance boilerplate and weak validation checkpoints that drag down conciseness and workflow clarity.

Suggestions

Remove generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Output Requirements, Response Template) that restate what Claude already knows, and deduplicate the `--help` commands.

Replace the abstract Workflow steps with concrete validation checkpoints tied to the skill (e.g., verify SOAP section completeness, confirm terminology normalization, flag missing required elements) instead of only `py_compile`/`--help`.

Move the inline SOAP Output Structure and Technical Architecture detail into the existing references (soap-templates.md) so SKILL.md stays a lean overview pointing one level deep.

Dimension	Reasoning	Score
Conciseness	The body is heavily padded with generic governance boilerplate (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Output Requirements, Response Template) that Claude already knows, plus a duplicated `--help` command and a mismatched "academic writing" trigger line, matching the level-2 anchor of noticeably verbose padded sections.	2 / 5
Actionability	Concrete executable commands (`python scripts/main.py --input … --output-format soap`, `--audio consultation.wav`), a copy-paste Python API example, and a Parameters table provide mostly executable guidance with only minor gaps such as the odd hardcoded `cd` path.	4 / 5
Workflow Clarity	A sequenced Workflow and fallback path exist, but validation checkpoints are generic (`py_compile`, `--help`) rather than real output validation, matching the level-3 anchor of steps listed with missing/implicit checkpoints.	3 / 5
Progressive Disclosure	The References section clearly signals real one-level-deep bundle files (soap-templates.md, medical-abbreviations.json, terminology-sources.md, example-cases.md, scripts/main.py), but the SKILL.md itself inlines content (SOAP structure, technical architecture) that could live in those references, a minor organization gap.	4 / 5
	Total	13 / 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 purpose and niche but lacks an explicit "Use when…" trigger clause and relies on a stray "Trigger." token, leaving completeness and trigger-term quality at the midpoint.

Suggestions

Replace the bare "Trigger." token with an explicit "Use when…" clause listing concrete scenarios (e.g., transcribing physician dictation, generating SOAP/clinical notes from audio or text).

Add natural trigger synonyms users would actually say, such as "transcribe", "medical notes", "clinical notes", and "SOAP note", to broaden keyword coverage.

Enumerate 2-3 specific actions (transcribe audio, normalize medical terminology, assemble SOAP sections, run clinical quality checks) to lift specificity from one action to comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Convert physician verbal dictation into structured SOAP notes" names the domain plus one concrete action (convert into structured SOAP notes), but does not enumerate several specific actions, matching the level-3 anchor rather than level 4's multi-action coverage.	3 / 5
Completeness	The "what" is clear, but there is no explicit "Use when…" clause; the trailing "Trigger." is not equivalent trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	"physician verbal dictation" and "structured SOAP notes" supply a couple of relevant natural terms, but common synonyms (transcribe, medical/clinical notes) are missing, and the bare token "Trigger." is a templating artifact rather than a usable keyword.	3 / 5
Distinctiveness Conflict Risk	The medical-scribe/SOAP-note niche is distinct with low conflict risk, but the thin set of trigger phrases keeps it just below the level-5 anchor's clear, well-populated distinct triggers.	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/Academic Writing/medical-scribe-dictation/SKILL.md
Commit: 63c61d3

Reviewed: 13 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.