CtrlK
BlogDocsLog inGet started
Tessl Logo

healthcare-eval-harness

Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures. Use when a healthcare deployment must be gated on patient-safety tests for CDSS accuracy, PHI exposure, and workflow integrity.

69

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is tdg-personal/healthcare-eval-harness

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 highly actionable, well-structured skill body with executable commands, a clear gated workflow, and validation checkpoints. The main weakness is token redundancy from duplicating the clinical/integration threshold logic between the standalone examples and the CI/CD YAML.

Suggestions

De-duplicate the clinical and integration pass-rate shell logic: present it once in the CI/CD YAML and reference it from the standalone examples (or vice versa) to recover ~30 lines of tokens.

In the CI/CD YAML HIGH-gate steps, fail the step (exit non-zero) when the pass rate is below 95% if blocking is intended, or make the 'WARN, allow with review' decision explicit so the gating behavior matches the Pass/Fail matrix.

Move the full CI/CD workflow YAML into a references/ file (e.g. CI-CD.md) and keep only a minimal inline excerpt, improving both conciseness and progressive_disclosure.

DimensionReasoningScore

Conciseness

Largely lean and assumes Claude's knowledge of CDSS/PHI/HL7/FHIR, but the clinical and integration pass-rate shell logic is duplicated verbatim across the standalone examples and the CI/CD YAML block, adding avoidable tokens.

3 / 5

Actionability

Fully executable guidance throughout — concrete `npx jest` invocations, jq/bc pipelines, a complete GitHub Actions YAML, and three worked examples that are copy-paste ready and cover the common cases.

5 / 5

Workflow Clarity

Clear sequencing of five ordered eval categories with CRITICAL/HIGH gating, a pass/fail matrix, and explicit zero-test and pass-rate validation checkpoints; the HIGH-gate YAML only warns rather than failing, leaving a minor checkpoint gap relative to fully enforced gating.

4 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers and no nested references, though the full inlined CI/CD YAML could plausibly live in a separate reference file; no bundle files are present to offload to.

4 / 5

Total

16

/

20

Passed

Description

92%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, concrete description with an explicit 'Use when' trigger and comprehensive coverage of the four test categories plus deployment-blocking behavior. The only minor gap is a lack of synonym-level keyword variation, which keeps trigger term quality at 4 rather than 5.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the domain — 'Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance' plus 'Blocks deployments on safety failures' — matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both what (automated test suites across four categories that block deployments) and when via a concrete 'Use when a healthcare deployment must be gated on patient-safety tests...' trigger clause.

5 / 5

Trigger Term Quality

Strong domain-natural terms ('healthcare deployment', 'patient-safety tests', 'CDSS accuracy', 'PHI exposure', 'workflow integrity') but lacks synonyms or layperson variations, sitting just below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (healthcare patient-safety deployment gating) with distinct, specialized triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
affaan-m/ECC
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.