CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

saudi-patient-testing

Test case execution guide for Saudi telehealth patients in Dr. Sophia AI. Covers 5 test cases (Ahmed, Fatima, Abdullah, Sara, Aisha), data separation principles (historical vs current symptoms), success criteria, critical safety validation. Use when testing Saudi patient consultations, running diagnostic accuracy tests, validating AI responses, or checking allergy/safety protocols.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, actionable test guide with concrete commands, complete test-case data, and clear pass/fail validation criteria. Main weaknesses are redundancy (safety checks and run instructions repeated), a script reference that doesn't match the bundle layout plus a machine-specific path inside the script, and no failure-handling guidance.

Suggestions

Deduplicate: remove the repeated safety-check statements (keep either the per-case 'Critical' lines or the 'Critical Safety Checks' section) and merge the 'Run Test Script' section into 'Running Tests', which already covers the same command.

Fix pathing: reference the script bundle-relative as 'scripts/run-test-suite.sh' instead of the assumed install location '.claude/skills/saudi-patient-testing/scripts/run-test-suite.sh', and remove the machine-specific absolute path ('/mnt/c/data/github/...') from the script itself.

Add a short failure-handling step: what to do when a test case falls below the 85% threshold or a critical safety check (penicillin allergy, no antibiotics for viral URTI, urgent appendicitis flag) fails.

DimensionReasoningScore

Conciseness

Mostly efficient data-oriented content, but the critical safety checks appear three times (per-case 'Critical' lines, the 'Critical Safety Checks' section, and the summary table), run instructions are duplicated ('Running Tests' and 'Run Test Script'), and time-sensitive status info ('Last Verified: October 2025', '87.5% success rate') is repeated in header and footer outside any deprecation section.

3 / 5

Actionability

Concrete executable guidance throughout: 'cd backend/tests; node test-saudi-ai-diagnostic-accuracy.js', a complete copy-paste curl example, and expected output blocks. Minor gaps: the script is referenced by installed path '.claude/skills/saudi-patient-testing/scripts/run-test-suite.sh' rather than bundle-relative 'scripts/run-test-suite.sh', and the script itself hardcodes a machine-specific absolute path ('/mnt/c/data/github/...').

4 / 5

Workflow Clarity

Clear sequence (principle → test cases → run → verify) with validation checkpoints: per-test expected outputs, pass thresholds (85% per case, 80% overall), and the explicit rule 'No critical safety failures allowed'. Falls short of 5 because there is no error-recovery guidance for what to do when a test or critical safety check fails.

4 / 5

Progressive Disclosure

Well-organized sections appropriate for a single-purpose test guide, with the one bundle file (scripts/run-test-suite.sh) referenced in its own clearly signaled section. Minor gap: the reference uses an assumed installation path instead of the actual bundle-relative path, so navigation from the skill as shipped is slightly broken.

4 / 5

Total

15

/

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 description: third-person voice, concrete what-and-when structure with explicit trigger phrases, and a distinct niche. Only minor gaps in action specificity and natural-term synonyms keep specificity and trigger_term_quality at 4.

DimensionReasoningScore

Specificity

Lists several concrete items — 5 named test cases, data separation principles, success criteria, safety validation — and concrete actions ('testing', 'running diagnostic accuracy tests', 'validating AI responses', 'checking allergy/safety protocols'), but 'Covers...' enumerates topics rather than fully comprehensive action coverage, leaving minor gaps.

4 / 5

Completeness

Explicitly answers both 'what' (test case execution guide covering 5 cases, data separation, success criteria, safety validation) and 'when' with concrete trigger phrases ('Use when testing Saudi patient consultations, running diagnostic accuracy tests, validating AI responses, or checking allergy/safety protocols').

5 / 5

Trigger Term Quality

Good natural-phrase coverage ('testing Saudi patient consultations', 'running diagnostic accuracy tests', 'validating AI responses', 'checking allergy/safety protocols') plus the product name 'Dr. Sophia AI'; a few natural synonyms (e.g., 'test suite', 'clinical decision validation') are missing.

4 / 5

Distinctiveness Conflict Risk

'Saudi telehealth patients in Dr. Sophia AI' with five named patients is a clear niche with distinct triggers; minimal risk of firing for the wrong skill.

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/examples/saudi-patient-testing/SKILL.md

Revision

93ed392

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill