medication-adherence-message-gen
Use medication adherence message gen for academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries.
30
13%
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/medication-adherence-message-gen/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 is deeply problematic because it conflates two unrelated domains (medication adherence messaging and academic writing) without explaining what the skill actually does. It lacks concrete actions, natural trigger terms, and a coherent 'when to use' clause, making it nearly unusable for skill selection.
Suggestions
Clarify the actual purpose of the skill—decide whether it's about medication adherence messaging or academic writing, and describe concrete actions for that domain (e.g., 'Generates patient medication reminder messages' or 'Structures academic papers with explicit assumptions').
Add a clear 'Use when...' clause with natural trigger terms a user would actually say, such as 'Use when the user asks for medication reminders, adherence messages, or patient communication templates.'
Remove abstract filler phrases like 'structured execution', 'explicit assumptions', and 'clear output boundaries' and replace them with specific capabilities the skill performs.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'medication adherence message gen' and 'academic writing workflows' but does not list any concrete actions. Terms like 'structured execution', 'explicit assumptions', and 'clear output boundaries' are abstract and vague. | 1 / 3 |
Completeness | The 'what' is unclear—it conflates medication adherence messaging with academic writing. There is a 'Use when' equivalent ('for academic writing workflows that need...'), but the trigger condition is vague and the core capability is not explained. | 1 / 3 |
Trigger Term Quality | The keywords are confusing and contradictory—'medication adherence message gen' and 'academic writing workflows' are two unrelated domains mashed together. A user would not naturally say these terms together when seeking help with either task. | 1 / 3 |
Distinctiveness Conflict Risk | The description is internally contradictory, combining medication adherence and academic writing, which makes it impossible to distinguish from either domain-specific skill. It would cause confusion rather than clear selection. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with generic boilerplate sections (risk assessment, security checklist, lifecycle status, evaluation criteria, response templates) that consume significant tokens without adding skill-specific value. The core domain content—behavioral psychology message templates and generation logic—is paradoxically the thinnest part. The description mismatch (academic writing workflows vs. medication adherence messages) creates confusion about the skill's actual purpose.
Suggestions
Remove all generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template) that apply to any skill and don't teach Claude anything specific about medication adherence message generation.
Consolidate the redundant sections (Example Usage, Usage, Quick Check, Audit-Ready Commands) into a single concise Usage section with the CLI reference table and 2-3 examples.
Add actual message template examples for each psychological principle so Claude can understand the generation patterns, rather than just listing principle names in a table.
Resolve the identity crisis between 'academic writing workflows' (description) and 'medication adherence message generation' (actual content)—pick one purpose and remove references to the other.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. Contains massive amounts of boilerplate (security checklists, lifecycle status, evaluation criteria, risk assessments) that add no value for Claude. Multiple sections reference each other circularly ('See ## Prerequisites above', 'See ## Usage above'). The skill explains obvious concepts and includes generic templates that Claude already knows how to produce. | 1 / 3 |
Actionability | The CLI examples and Python API usage are concrete and executable, with specific flags and parameters documented in a table. However, much of the guidance is generic boilerplate ('confirm the user objective', 'validate that the request matches documented scope') rather than specific to medication adherence message generation. The actual behavioral psychology templates and message generation logic are not shown. | 2 / 3 |
Workflow Clarity | There is a numbered workflow with steps for confirming inputs, validating scope, executing, and handling failures. However, the workflow is generic and lacks specific validation checkpoints for this domain (e.g., no check that generated messages are medically appropriate, no validation of psychological principle application). The error handling section mentions fallbacks but doesn't specify concrete recovery steps. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with many redundant sections covering the same ground. Sections like 'Example Usage', 'Usage', 'Workflow', 'Implementation Details', and 'Quick Check' overlap significantly. The single reference to 'references/audit-reference.md' is buried at the bottom. Content that should be in separate files (security checklist, evaluation criteria, lifecycle status) is inlined, while the actual message templates are not shown at all. | 1 / 3 |
Total | 6 / 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
858c2e5
- 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.