CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

skill-builder-medical

Specialized guide for creating Claude Code skills for Dr. Sophia AI medical system. Includes healthcare integration patterns (FHIR/REST/EHR), medical compliance validation (HIPAA/PBS/TGA), botanical design integration, Railway deployment patterns, and proven examples from our 7 production skills. Use when creating skills specifically for Dr. Sophia AI, medical integration skills, healthcare compliance skills, EHR workflows, or adapting our proven skill patterns.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skill-builder-package/skill-builders/skill-builder-medical/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

47%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 functions as a well-organized index to seven existing skills rather than a standalone guide: it is lean and clearly structured, but delivers almost no executable pattern content, templates, or step-by-step process for actually building a skill. Workflow clarity is the biggest gap, followed by actionability.

Suggestions

Include the actual patterns inline (or in bundle reference files) instead of one-line deferrals — e.g., show the 'Two-phase FHIR/REST workflow' steps and a sanitized SOAP note template rather than 'See: medirecords-integration skill'.

Add a sequenced Quick Start workflow for creating a new skill (e.g., copy a proven template → adapt medical compliance rules → validate no PHI → test), with explicit validation checkpoints.

Remove the redundant scope restatements across Overview/When to Use/Quick Start and drop or relocate the time-sensitive trailer metadata ('Version: 1.0', 'Last Updated: October 25, 2025').

DimensionReasoningScore

Conciseness

The body is mostly lean bullets with no explanation of concepts Claude already knows, but the Overview, When to Use, and Quick Start sections restate the same scope three times, and the trailer carries time-sensitive metadata ('Version: 1.0', 'Last Updated: October 25, 2025') outside any deprecated/old-patterns section. Redundant framing keeps it from 4.

3 / 5

Actionability

The Medical-Specific Requirements section gives some concrete rules ('No PHI in examples', 'Template credentials', 'Use #00B368 green spectrum', 'Frontend: npm run build required'), but the four pattern sections are one-line deferrals ('See: medirecords-integration skill', 'Two-phase FHIR/REST workflow') with no templates, code, or steps included. Concrete but incomplete guidance matches anchor 3 rather than 4.

3 / 5

Workflow Clarity

Despite the skill's purpose of guiding skill creation, no sequenced process is given: Quick Start is a single pointer ('use skill-builder-generic first'), the pattern sections are an unordered catalog, and there are no validation or verification checkpoints anywhere. This is rough structure with major gaps, matching anchor 2 rather than the fully missing steps of anchor 1.

2 / 5

Progressive Disclosure

No bundle files exist, and the ~85-line body is organized into clean sections with clearly signaled, one-level-deep pointers ('See: botanical-design skill', 'All in: .claude/skills/'). Structure is good with minor gaps — the referenced skills live outside this bundle so navigation cannot be verified and inline content is thin.

4 / 5

Total

12

/

20

Passed

Description

87%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, niche-scoped description in third person that explicitly states both what the skill includes and when to use it, with good natural trigger terms. The only weakness is that the enumerated capabilities read as topic areas rather than concrete actions, and a few natural synonym triggers are absent.

DimensionReasoningScore

Specificity

Names the domain ('creating Claude Code skills for Dr. Sophia AI medical system') and lists several concrete capability areas ('healthcare integration patterns (FHIR/REST/EHR)', 'medical compliance validation (HIPAA/PBS/TGA)', 'Railway deployment patterns'). The listed items are topical areas rather than discrete actions, so it falls just short of the comprehensive action coverage of a 5.

4 / 5

Completeness

Clearly answers 'what' (a specialized guide including named pattern areas) and explicitly answers 'when' with the clause 'Use when creating skills specifically for Dr. Sophia AI, medical integration skills, healthcare compliance skills, EHR workflows, or adapting our proven skill patterns', matching the anchor for both concrete what and when.

5 / 5

Trigger Term Quality

The 'Use when' clause covers natural phrases users would say ('medical integration skills, healthcare compliance skills, EHR workflows') plus domain acronyms (FHIR/REST/EHR, HIPAA). A few common variations are missing (e.g., 'build a skill', 'healthcare app'), so it does not reach comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Scoped to a named niche ('Dr. Sophia AI medical system') with distinct triggers (FHIR/REST/EHR, HIPAA/PBS/TGA, Railway, botanical design) that no generic skill-builder description would share, giving minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

fernandezbaptiste/Skrillz

Path

skill-builder-package/skill-builders/skill-builder-medical/SKILL.md

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.