medication-adherence-message-gen
Use medication adherence message gen for academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries.
24
13%
Does it follow best practices?
Impact
—
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: it conflates two unrelated domains (medication adherence messaging and academic writing) without explaining the connection, lists no concrete actions, and uses abstract jargon instead of natural user language. It would be nearly impossible for Claude to correctly determine when to select this skill.
Suggestions
Clarify the actual purpose of the skill — decide whether it's about medication adherence message generation or academic writing, and describe concrete actions (e.g., 'Generates patient-facing medication reminder messages' or 'Structures academic papers with explicit methodology sections').
Add a clear 'Use when...' clause with natural trigger terms that match what users would actually say (e.g., 'Use when the user asks to create medication reminder texts, adherence notifications, or patient communication messages').
Remove vague filler phrases like 'structured execution', 'explicit assumptions', and 'clear output boundaries' and replace them with specific capabilities and outputs.
| 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 description fails to clearly answer 'what does this do' — it's unclear whether this generates medication messages or helps with academic writing. The 'when' clause ('Use... for academic writing workflows') is present but contradicts the skill name, making it incoherent. | 1 / 3 |
Trigger Term Quality | The description combines two unrelated domains ('medication adherence' and 'academic writing') in a confusing way. The keywords are unlikely to match what a user would naturally say, and the jargon ('structured execution', 'output boundaries') is not user-facing language. | 1 / 3 |
Distinctiveness Conflict Risk | The description is confusing and contradictory, mixing medication adherence and academic writing. This would likely cause incorrect triggering for both medication-related and academic writing-related queries, creating conflicts with skills in either domain. | 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 suffers from severe verbosity and poor organization. It mixes genuinely useful content (CLI options, Python API, output format examples) with extensive boilerplate (security checklists, lifecycle status, evaluation criteria, risk assessment) and circular self-references that waste tokens. The description is repeated multiple times, and the 'When to Use' section awkwardly pastes the skill description as a bullet point. The core medication adherence message generation content is solid but buried under layers of generic process scaffolding.
Suggestions
Remove all boilerplate sections that don't provide skill-specific guidance (Security Checklist, Risk Assessment, Lifecycle Status, Evaluation Criteria) or move them to a separate reference file.
Eliminate circular cross-references ('See ## Prerequisites above', 'See ## Usage above') and consolidate duplicated content (the skill description appears 3+ times, py_compile appears 3 times).
Move the psychological principles table, detailed output format examples, and response template to separate reference files, keeping only a concise quick-start with the most common usage pattern in the main SKILL.md.
Add a concrete validation step after message generation (e.g., verify JSON output schema, check message length constraints for SMS) to improve workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. Multiple sections reference each other circularly ('See ## Prerequisites above', 'See ## Usage above', 'See ## Workflow above'). The skill explains basic concepts Claude already knows, includes boilerplate sections (Lifecycle Status, Security Checklist, Evaluation Criteria) that add no actionable value, and repeats the same commands (py_compile, --help) in multiple places. The description of the skill's purpose is repeated at least 3 times verbatim. | 1 / 3 |
Actionability | The skill does provide concrete CLI examples, a Python API snippet, and specific command-line options with a parameter table. However, much of the 'workflow' content is generic process guidance rather than executable instructions specific to this tool. The code examples appear functional but the overall actionability is diluted by the volume of non-actionable boilerplate surrounding them. | 2 / 3 |
Workflow Clarity | There is a numbered workflow (steps 1-5) and an 'Example run plan' (steps 1-4), but they are generic and lack specific validation checkpoints. The error handling section mentions fallback paths but doesn't provide concrete commands for verification beyond py_compile. No feedback loop for validating generated message quality or correctness is provided. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with 20+ sections all inline. Sections like the full psychological principles table, output format examples, security checklist, evaluation criteria, lifecycle status, and risk assessment could all be in separate reference files. The circular cross-references ('See ## Prerequisites above') add confusion rather than navigation clarity. Only one external reference is mentioned (references/audit-reference.md) but no bundle files were provided to verify it. | 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
73f6514
- 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.