patient-consent-simplifier

Simplifies informed consent documents into patient-friendly language while maintaining regulatory compliance. Readability assessment targeting 6th-8th grade level, risk/benefit clarification in table format, and FDA 21CFR50/ICH-GCP/HIPAA compliance validation.

Quality

60%

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/Other/patient-consent-simplifier/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 skill has a well-structured workflow with checkpoints and feedback loops, but its code examples are largely non-executable against the provided bundle and reference a fictitious API/module. Reconciling the documented API with scripts/main.py would most improve actionability and progressive disclosure.

Suggestions

Align all code examples with the actual bundle: import from scripts.main and use only the methods that exist (simplify(text), calculate_grade_level(text)), or extend main.py to implement simplify_section, clarify_risks, assess_readability, and check_compliance.

Fix the referenced file path: the CLI examples invoke scripts/consent_simplifier.py but the bundled file is scripts/main.py.

Split the detailed capability API, the compliance checklist, and the response template into reference files so the SKILL.md body stays a lean overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the overlapping 'Quick Check' and 'Audit-Ready Commands' sections and generic boilerplate (Output Requirements, Response Template, Error Handling) add length that could be trimmed.	3 / 5
Actionability	The audit CLI commands (py_compile, --help, --text) are executable, but the Core Capabilities code references a non-existent module (scripts/consent_simplifier) and methods (simplify_section, clarify_risks, assess_readability, check_compliance) that do not exist in the bundled scripts/main.py, so the primary examples are not executable against the real bundle.	3 / 5
Workflow Clarity	A clear 10-step sequence includes two explicit checkpoints, a readability feedback loop, a compliance check, a fallback, and a required-elements checklist, though several validation steps rely on user confirmation rather than concrete automated checks.	4 / 5
Progressive Disclosure	Sections are clearly labeled, but the ~200-line body is monolithic with no reference files for content that could be split out, and it references a non-existent scripts/consent_simplifier.py instead of the real scripts/main.py, producing an inaccurate reference path.	3 / 5
	Total	13 / 20 Passed

Description

63%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 is specific and well-scoped to a clear regulatory niche, but it omits any explicit trigger guidance and leans on technical jargon over the natural phrases a user would say. Adding a 'Use when…' clause with layperson trigger terms would lift the completeness and trigger-term dimensions.

Suggestions

Add an explicit 'Use when…' clause with trigger phrases such as 'simplify consent', 'plain language consent form', or 'patient-friendly consent form'.

Replace or supplement regulatory jargon (FDA 21CFR50/ICH-GCP/HIPAA) with natural synonyms a patient-facing user would actually say.

Keep the concrete capability list but trim the acronym-heavy tail so the description reads as triggers rather than a compliance spec.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — simplification of consent documents, readability assessment at a target grade level, risk/benefit clarification in table format, and FDA/ICH-GCP/HIPAA compliance validation — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Clearly states what the skill does but provides no 'Use when…' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Contains some natural terms ('informed consent documents', 'patient-friendly language') but is heavy on regulatory jargon (FDA 21CFR50/ICH-GCP/HIPAA) and omits common variations users would say such as 'simplify consent' or 'plain language consent'.	3 / 5
Distinctiveness Conflict Risk	Targets a narrow niche (consent simplification with regulatory compliance) that is mostly distinct, though it could overlap with general medical plain-language skills and lacks explicit distinct trigger phrases.	4 / 5
	Total	15 / 20 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
Path: scientific-skills/Other/patient-consent-simplifier/SKILL.md
Commit: 63c61d3

Reviewed: 10 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.