CtrlK
BlogDocsLog inGet started
Tessl Logo

treatment-plans

Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.

65

1.44x
Quality

47%

Does it follow best practices?

Impact

75%

1.44x

Average score across 6 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/treatment-plans/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

67%

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 excels at specificity and distinctiveness, clearly carving out a unique niche for medical treatment plan generation with detailed capability enumeration. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Trigger terms are adequate but could better cover natural user language variations.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for a treatment plan, care plan, clinical plan, or medical protocol for a patient.'

Include more natural user-facing trigger terms such as 'care plan', 'patient plan', 'clinical protocol', or 'medical plan' to improve matching against common user requests.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and domains: generating treatment plans in LaTeX/PDF, supporting rehabilitation therapy, mental health care, chronic disease management, perioperative care, pain management, SMART goal frameworks, evidence-based interventions, HIPAA compliance, and professional formatting.

3 / 3

Completeness

Clearly answers 'what does this do' with detailed capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the nature of the described capabilities, which caps this at 2 per the rubric guidelines.

2 / 3

Trigger Term Quality

Contains relevant clinical keywords like 'treatment plans', 'rehabilitation therapy', 'mental health care', 'chronic disease management', 'HIPAA', 'LaTeX/PDF', but misses common user-facing variations (e.g., 'patient plan', 'care plan', 'clinical plan', 'treatment protocol'). Some terms like 'SMART goal frameworks' and 'perioperative care' are more professional jargon than natural user language.

2 / 3

Distinctiveness Conflict Risk

Highly distinctive niche combining medical treatment plans with LaTeX/PDF output, specific clinical specialties, and regulatory compliance. Unlikely to conflict with generic document or medical skills due to the very specific combination of domain, format, and purpose.

3 / 3

Total

10

/

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 extreme verbosity, containing extensive clinical knowledge that Claude already possesses (SMART goal definitions, lists of medical conditions, standard treatment plan components) while ironically emphasizing brevity as its core principle. The actionable elements (LaTeX commands, validation scripts, template selection) are buried within hundreds of lines of descriptive content that should either be in separate reference files or omitted entirely. The skill would benefit enormously from being reduced to ~100 lines covering template selection, the validation workflow, the custom LaTeX style package usage, and pointers to detailed reference files.

Suggestions

Reduce the main skill to ~100-150 lines: template selection table, compilation commands, validation workflow, and style package quick-reference, with all clinical specialty details moved to separate reference files (e.g., SPECIALTIES.md, LATEX_STYLING.md)

Remove all explanations of clinical concepts Claude already knows (SMART goals, what rehabilitation is, lists of medical conditions, standard treatment plan components) and focus only on project-specific conventions and templates

Move the entire 'Professional Document Styling' section (~300 lines) to a separate STYLING_GUIDE.md and reference it with a single line

Consolidate the repeated emphasis on brevity/conciseness into a single brief directive rather than restating it in 5+ different sections throughout the document

DimensionReasoningScore

Conciseness

This is an extremely verbose document (~1000+ lines) that extensively explains concepts Claude already knows (SMART goals, HIPAA, what treatment plans are, what rehabilitation therapy involves, standard medical terminology). Massive sections enumerate standard clinical components (e.g., listing every type of rehabilitation, every mental health condition) that add no novel instruction. The irony is palpable: a skill that repeatedly emphasizes 'brevity and conciseness' is itself enormously bloated.

1 / 3

Actionability

The skill provides some concrete LaTeX code examples, bash commands for compilation and validation scripts, and specific template file names. However, much of the content is descriptive rather than instructive (e.g., long lists of 'what to include' in treatment plans rather than executable templates), and the LaTeX snippets are fragments/pseudocode rather than complete compilable documents. The validation workflow has concrete commands but references scripts that may not exist.

2 / 3

Workflow Clarity

The validation workflow section (create → check completeness → validate quality → review checklist → generate PDF → review → implement) is clearly sequenced with specific commands. However, validation checkpoints are listed but lack explicit feedback loops (e.g., what to do if validation fails is not detailed), and the overall document structure makes it hard to find the actual workflow amidst the massive amount of descriptive content.

2 / 3

Progressive Disclosure

This is a monolithic wall of text with hundreds of lines of detailed content that should be split into separate files (e.g., LaTeX styling guide, clinical specialty details, box environment reference, template usage guide). While it references some external files (quality_checklist.md, templates, scientific-schematics skill), the vast majority of content that belongs in reference files is inlined, making the skill extremely difficult to navigate.

1 / 3

Total

6

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1581 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

Total

9

/

11

Passed

Repository
K-Dense-AI/claude-scientific-skills
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.