ehr-semantic-compressor

1. Confirm the user objective, required inputs, and non-negotiable constraints before doing detailed work. 2. Validate that the request matches the documented scope and stop early if the task would require unsupported as.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is genuinely actionable with executable commands, a parameters table, and concrete I/O examples backed by real bundle files, but it is weighed down by repetitive boilerplate and generic template sections. Workflow guidance lacks skill-specific validation checkpoints despite being a code-execution skill.

Suggestions

Trim the generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) and move the duplicated scope-validation preamble out of 'When to Use' and 'Key Features' to remove the repeated truncated text.

Integrate the py_compile validation into the Workflow as an explicit validate-then-run checkpoint with a fix-retry feedback loop, rather than isolating it in 'Quick Check'.

Fix the circular 'See `## Usage` above' and 'See `## Workflow` above' cross-references in 'Example Usage' and 'Implementation Details', which point readers in loops instead of giving guidance.

Dimension	Reasoning	Score
Conciseness	The body contains actionable detail (parameters table, JSON I/O examples, commands) but is padded with generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) and repeats the same truncated preamble verbatim in 'When to Use', 'Key Features', and 'Workflow'.	2 / 3
Actionability	It provides executable commands ('python scripts/main.py --input ehr_document.txt --output summary.json', 'python -m py_compile scripts/main.py'), a concrete parameters table, and complete input/output JSON examples that are copy-paste ready against the bundled main.py.	3 / 3
Workflow Clarity	A 5-step Workflow is sequenced, but the steps are generic scaffolding ('Confirm the user objective', 'switch to the fallback path') with no integrated validation checkpoint or validate-fix-retry feedback loop for the script-execution task; py_compile lives in a separate 'Quick Check' section rather than the workflow.	2 / 3
Progressive Disclosure	References to references/requirements.txt, guidelines.md, sample_input.json, sample_output.json and scripts/main.py are real, one level deep, and clearly signaled, but the SKILL.md itself is a ~280-line monolithic file with much content (risk/security/evaluation boilerplate) that could be split out.	2 / 3
	Total	9 / 12 Passed

Description

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 frontmatter description is a truncated, generic scope-checking preamble that fails to convey what the skill (EHR semantic compression) actually does or when to use it. It lacks any domain-specific capability or trigger language.

Suggestions

Rewrite the description to state the concrete capability, e.g. 'Summarizes lengthy Electronic Health Record (EHR) documents into structured, clinically accurate bullet-point summaries extracting allergies, medications, diagnoses, and other key clinical information.'

Add an explicit trigger clause such as 'Use when processing or summarizing long EHR/medical records, or when the user asks to extract clinical information from patient notes.'

Remove the numbered scope-validation preamble from the description field; it belongs in the body's workflow guidance, not as the skill's identity.

Dimension	Reasoning	Score
Specificity	The description lists generic process actions ('Confirm the user objective, required inputs, and non-negotiable constraints', 'Validate that the request matches the documented scope') that describe a scope-checking preamble rather than any concrete capability of the skill; no EHR/summarization actions are named.	1 / 3
Completeness	It answers neither 'what does this do' (the actual EHR summarization capability is absent) nor 'when should Claude use it' (no 'Use when...' trigger), and the text is truncated mid-sentence at 'unsupported as.'.	1 / 3
Trigger Term Quality	It contains no natural keywords a user would say to invoke this skill — no 'EHR', 'medical records', 'summarize', or 'clinical' — only generic workflow jargon, so it would not be triggered by real requests.	1 / 3
Distinctiveness Conflict Risk	The text is a generic scope-validation preamble that could apply to virtually any skill, so it is indistinguishable from many others and would conflict broadly.	1 / 3
	Total	4 / 12 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
Commit: d924410

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.