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.
33
Quality
17%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/ehr-semantic-compressor/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description fails on all dimensions. It reads like internal procedural notes rather than a skill description, containing no concrete capabilities, no domain specificity, no trigger terms, and no guidance on when to use it. The text also appears truncated ('unsupported as.').
Suggestions
Completely rewrite to specify WHAT domain or task this skill handles (e.g., 'Validates API requests', 'Reviews project requirements', 'Scopes technical tasks').
Add a 'Use when...' clause with natural trigger terms users would actually say when they need this skill.
Replace procedural language with concrete action verbs describing capabilities (e.g., 'Analyzes requirements, identifies missing inputs, flags scope conflicts').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'user objective', 'required inputs', 'non-negotiable constraints', and 'detailed work' without specifying any concrete actions or domain. No specific capabilities are listed. | 1 / 3 |
Completeness | Fails to answer 'what does this do' in any meaningful way and completely lacks a 'when should Claude use it' clause. The description reads like internal process steps rather than a skill description. | 1 / 3 |
Trigger Term Quality | Contains no natural keywords users would say. Terms like 'non-negotiable constraints', 'documented scope', and 'unsupported as' (appears truncated) are technical jargon that users wouldn't naturally use when requesting help. | 1 / 3 |
Distinctiveness Conflict Risk | Extremely generic - 'confirm objectives' and 'validate requests' could apply to virtually any skill. No domain or niche is established, creating high conflict risk with any other skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from severe redundancy and poor organization - the same workflow steps and scope description appear verbatim in 4+ different sections. While it provides useful concrete elements (CLI commands, JSON schemas, parameter tables), the excessive boilerplate (security checklists, lifecycle status, evaluation criteria) and repetition make it difficult to quickly extract actionable guidance. The content would be significantly improved by consolidating to ~30% of its current length.
Suggestions
Consolidate the workflow into a single authoritative section - remove duplicate workflow descriptions from 'When to Use', 'Key Features', and 'Implementation Details'
Remove boilerplate sections that don't add actionable value (Lifecycle Status, Evaluation Criteria, Security Checklist, Risk Assessment) or move them to a separate reference file
Merge 'Overview' and 'Core Features' into a single brief introduction, and combine 'Usage' with 'Example Usage' to eliminate redundancy
Remove the truncated/malformed description text that appears in 'When to Use' and 'Key Features' sections
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with significant redundancy - the same workflow steps appear in multiple sections (When to Use, Key Features, Workflow, Implementation Details). Contains unnecessary boilerplate like lifecycle status, evaluation criteria, and security checklists that don't add actionable value for Claude. | 1 / 3 |
Actionability | Provides concrete CLI commands and JSON input/output formats which are helpful, but the actual script implementation details are missing. The commands reference scripts/main.py but don't show what the script actually does internally, making it unclear how to modify or extend behavior. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly listed and includes validation/fallback steps, but the same workflow appears fragmented across multiple sections (When to Use, Key Features, Workflow, Implementation Details) creating confusion. Validation checkpoints exist but are scattered rather than integrated into a single clear sequence. | 2 / 3 |
Progressive Disclosure | References external files appropriately (references/, scripts/main.py) but the main document itself is poorly organized with redundant sections. Content that should be consolidated is spread across Overview, Core Features, Usage, Implementation Details, and Workflow sections with significant overlap. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
4a48721
- Reviewed
Table of Contents
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.