treatment-plans

Generate concise (typically 1–4 pages) patient-centered medical treatment plans in LaTeX/PDF when a clinician needs an actionable plan with SMART goals, evidence-based interventions, monitoring, and HIPAA-aware documentation.

Quality

77%

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/Other/treatment-plans/SKILL.md

Quality

Content

63%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 is actionable and workflow-oriented with real commands and a compilable LaTeX pattern, but it is undermined by duplicated sections between Key Features and Implementation Details and by poor progressive disclosure: six reference guides exist in the bundle yet are never referenced from the body, and a referenced diagram script is missing. Fixing the cross-file navigation and de-duplicating the length/citation guidance would lift it substantially.

Suggestions

Replace the duplicated 'Key Features' / 'Implementation Details' content (length strategy, front-page summary, citation policy each appear twice) with a single authoritative section, keeping the body under ~120 lines.

Add a 'References' section linking each guide in references/ (e.g., goal_setting_frameworks.md, regulatory_compliance.md, specialty_specific_guidelines.md) and list templates with their assets/ paths so the existing bundle files are discoverable.

Either remove the generate_schematic.py example or note that it requires an external dependency, and align working directories across the example steps so commands are copy-paste runnable from one location.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and no beginner-concept padding, but several sections are duplicated: 'Concise formats by default' restates 'Document length strategy', the front-page executive summary pattern appears in both Key Features and Implementation Details, and 'minimal citations' vs 'Citation policy (minimalist)' repeats the same 0-3 citation rule. Not 4 because whole sections are restated rather than just having minor trimmable lines.	3 / 5
Actionability	Concrete bash commands, a usable LaTeX skeleton, and named scripts/templates make the guidance mostly executable. Not 5 because 'scripts/generate_schematic.py' is referenced but does not exist in the bundle, templates are named without their 'assets/' paths, and step 2's working directory is inconsistent with step 1's 'cd' into the scripts directory.	4 / 5
Workflow Clarity	Example Usage provides a clearly numbered sequence (generate -> optional diagram -> compile -> validate -> timeline) with explicit validation commands after compilation. Not 5 because no fix-and-revalidate feedback loop is stated and there is no guidance on what to do when check_completeness.py or validate_treatment_plan.py reports failures.	4 / 5
Progressive Disclosure	The bundle contains 6 reference guides, 4 scripts, and 10 asset files, but the body never links to any file in 'references/', gives no 'assets/' path for the templates it lists, and inlines content (core clinical sections, validation logic) that duplicates the orphaned reference guides. This fits the anchor of references present but not clearly signaled with content that should be separate kept inline.	3 / 5
	Total	14 / 20 Passed

Description

83%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.

A strong description: third-person voice, concrete action, explicit and specific when-to-use trigger, and a well-delineated clinical niche. The only improvements are broader synonym coverage (e.g., 'care plan') and mentioning the validation tooling that differentiates the skill.

Dimension	Reasoning	Score
Specificity	Concrete action ('Generate... treatment plans in LaTeX/PDF') plus specific content elements ('SMART goals', 'evidence-based interventions', 'monitoring', 'HIPAA-aware documentation') with only minor gaps (validation tooling unmentioned). Not 5 because it names one primary action rather than a list of multiple distinct concrete actions.	4 / 5
Completeness	Explicitly answers both 'what' (generate concise patient-centered medical treatment plans in LaTeX/PDF with the listed features) and 'when' ('when a clinician needs an actionable plan with SMART goals, evidence-based interventions, monitoring, and HIPAA-aware documentation'). The when-clause is concrete and trigger-shaped, matching the top anchor better than the level-4 example.	5 / 5
Trigger Term Quality	Contains natural phrases users would say: 'treatment plans', 'medical', 'patient-centered', 'SMART goals', 'clinician', 'LaTeX/PDF'. Not 5 because common synonyms like 'care plan' or 'clinical plan' are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (clinical treatment planning with LaTeX/PDF output) with distinct trigger terms; minor overlap risk with adjacent medical-documentation skills that also trade on 'medical' and 'HIPAA' terms. Not 5 because closely related clinical-writing skills could compete on those shared terms.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/treatment-plans/SKILL.md
Commit: 686e09d

Reviewed: 12 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.