tone-adjuster

Use when converting medical text between academic and patient-friendly tones, translating medical jargon for patients, adapting research papers for public audiences, or rewriting clinical notes for patient handouts. Maintains medical accuracy while adjusting readability level.

Quality

75%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/tone-adjuster/SKILL.md

Quality

Content

50%

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, fairly concise skill content (term tables, conversion rules, reading-level guidance), but it is undermined by code/CLI examples that contradict the bundled scripts/main.py and by substantial generic boilerplate unrelated to medical tone adjustment. Organization is adequate but references are weakly signaled and one script path is wrong.

Suggestions

Reconcile all code and CLI examples with the actual scripts/main.py surface: replace the non-existent methods (to_patient_friendly, to_academic, assess_reading_level, translate_jargon, convert), the scripts.tone_adjuster import path, and the --input/--direction/--assess flags with the real adjust(text, target_tone, level) API and positional argv usage so examples are copy-paste executable.

Remove the generic process boilerplate (Output Requirements, Error Handling, Input Validation, Response Template, and the verbatim description repeats in "When to Use"/"Key Features") that restates discipline Claude already applies; keep only the tone-conversion-specific guidance.

Signal references/guidelines.md by name from the body and move the inline jargon dictionary plus detailed worked examples there, leaving SKILL.md as a lean overview; also fix the scripts/tone_adjuster.py path to scripts/main.py.

Dimension	Reasoning	Score
Conciseness	The skill-specific sections (conversion rules, term tables, reading levels, jargon dictionary) are reasonably lean, but large generic boilerplate blocks (Output Requirements, Error Handling, Input Validation, Response Template, Workflow, Implementation Details) and a verbatim re-quote of the description in "When to Use"/"Key Features" pad the body with content Claude already knows.	2 / 3
Actionability	Code and CLI blocks are concrete in form, but they do not match the bundled script: documented methods (to_patient_friendly, to_academic, assess_reading_level, translate_jargon, convert), the import path scripts.tone_adjuster, and CLI flags (--input, --direction) are absent from scripts/main.py, which exposes adjust(text, target_tone, level) with positional args, so the examples are not copy-paste executable.	2 / 3
Workflow Clarity	A sequenced Workflow and an "Audit-Ready Commands" block exist (including a py_compile validation step), but the steps are generic process discipline rather than tone-conversion-specific checkpoints, and there is no validation of the converted output's medical accuracy or reading level.	2 / 3
Progressive Disclosure	A one-level-deep references/ directory exists, but the body only gestures at "references/" generically rather than naming references/guidelines.md, references a non-existent scripts/tone_adjuster.py, and keeps large reference-style content (jargon dictionary, detailed examples) inline instead of split out.	2 / 3
	Total	8 / 12 Passed

Description

100%

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 is well-constructed: it opens with an explicit "Use when..." trigger, enumerates several concrete capabilities in third-person imperative form, and carves out a distinct medical-tone niche. It closely matches the rubric's good examples and shows no vagueness or over-claiming.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "converting medical text between academic and patient-friendly tones", "translating medical jargon", "adapting research papers", "rewriting clinical notes" — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what (converts/tones/translates/adapts) and when via a leading "Use when..." trigger clause, matching the full what+when anchor.	3 / 3
Trigger Term Quality	Uses natural terms a user would say ("medical text", "medical jargon for patients", "research papers", "clinical notes", "patient handouts", "readability level") with good coverage of variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear medical-tone-adjustment niche with distinct triggers (jargon translation, patient handouts, readability) unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Commit: 7cc5680

Reviewed: 3 days 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.