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

30%

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/ehr-semantic-compressor/SKILL.md

Quality

Content

60%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 guidance backed by a real script and properly signaled reference files, but is undermined by heavy duplication of generic process boilerplate and template scaffold filler that inflates length without adding skill-specific value. Structure and actionability are solid; conciseness is the weakest dimension.

Suggestions

Eliminate the duplicated generic process boilerplate — keep one canonical Workflow section and remove the repeated 'Confirm the user objective / validate scope' text from 'When to Use', 'Key Features', and 'Implementation Details'.

Move or remove scaffold filler ('Lifecycle Status', 'Risk Assessment', 'Security Checklist', 'Evaluation Criteria') that does not advance the EHR summarization task, or relocate it to a reference file.

Add one fully runnable end-to-end example that uses the existing references/sample_input.json so the Usage section is copy-paste complete.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the same generic process boilerplate ('Confirm the user objective...', 'Validate that the request matches the documented scope') is repeated verbatim across 'When to Use', 'Key Features', 'Workflow', 'Implementation Details', 'Output Requirements', 'Input Validation', and 'Response Template', and scaffold filler ('Lifecycle Status', 'Risk Assessment', 'Security Checklist', 'Evaluation Criteria' test cases) pads the document; it is not a 1 because the technical sections themselves do not extensively explain concepts Claude already knows.	2 / 5
Actionability	Guidance is mostly executable: real commands ('python scripts/main.py --input ehr_document.txt --output summary.json', 'python -m py_compile scripts/main.py'), a Parameters table with defaults, concrete Audit-Ready Commands with a sample input string, and a genuine 14KB scripts/main.py with referenced sample_input.json/sample_output.json; it is not 5 because examples use placeholder file paths and never wire the existing sample_input.json into a fully runnable end-to-end command.	4 / 5
Workflow Clarity	A clear 5-step Workflow and 4-step 'Example run plan' are sequenced with explicit checkpoints (Quick Check 'python -m py_compile', step-2 scope validation with stop-early, and an Error Handling fallback path); it is not 5 because the checkpoints are partly generic rather than concrete output-validation (e.g., no 'verify summary_length within 200-300' step).	4 / 5
Progressive Disclosure	Structure is good with a clearly signaled one-level-deep References section pointing to real files (guidelines.md, requirements.txt, sample_input.json, sample_output.json, scripts/main.py, all verified present); it is not 5 because substantial content that could live in separate files (Parameters, Technical Details, Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) is inlined, making the SKILL.md more monolith than lean overview.	4 / 5
	Total	14 / 20 Passed

Description

0%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 a truncated, generic process instruction duplicated from the body rather than a capability statement; it fails to convey what the skill does or when to trigger it. This is a severe quality failure across all dimensions.

Suggestions

Rewrite the description to state the concrete capability in third person, e.g. 'Summarizes lengthy Electronic Health Record (EHR) documents into structured bullet-point clinical summaries and extracts allergies, medications, diagnoses, family history, procedures, and vitals.'

Add an explicit trigger clause: 'Use when the user needs to condense or extract structured clinical information from long medical records or EHR text.'

Remove the duplicated numbered process boilerplate and the truncated 'unsupported as' fragment from the description field.

Dimension	Reasoning	Score
Specificity	The description lists only generic process steps ('Confirm the user objective, required inputs, and non-negotiable constraints', 'Validate that the request matches the documented scope') and names no skill domain or concrete capability, matching the 'Entirely vague; no concrete actions; pure abstract language' anchor; it cannot score 2 because no domain is named.	1 / 5
Completeness	It answers neither 'what does this skill do' (no capability described) nor 'when should Claude use it' (no 'Use when...' clause), and is also truncated mid-sentence at 'unsupported as', fitting the 'Missing both what and when, or both are extremely vague' anchor.	1 / 5
Trigger Term Quality	It contains zero natural trigger terms a user would say for EHR summarization (no 'EHR', 'medical records', 'clinical summary'); the language is entirely generic process jargon, matching anchor 1 rather than 2 which requires at least one or two generic skill-relevant keywords.	1 / 5
Distinctiveness Conflict Risk	The generic 'confirm objective / validate scope' boilerplate would apply to virtually any skill and provides no distinguishing trigger, matching the 'Entirely generic; would conflict with virtually any skill' anchor exactly.	1 / 5
	Total	4 / 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/ehr-semantic-compressor/SKILL.md
Commit: 63c61d3

Reviewed: 6 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.