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.

63

Quality

76%

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 ./skills/healthcare-eval-harness/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a clear, well-validated workflow and clean single-file organization; its main weakness is redundant repetition of the pass-rate computation across the category sections, the CI yaml, and the examples.

Suggestions

De-duplicate the jq pass-rate snippet: show the pattern once and reference it from the CI yaml and examples rather than repeating it three times.

Remove the duplicated comment line '# HIGH gates — 95%+ required' in the CI yaml block.

DimensionReasoningScore

Conciseness

The body is mostly lean and command-driven without explaining concepts Claude already knows, but the jq pass-rate computation appears three times (per-category sections, the CI yaml, and Example 2) and the full CI yaml restates logic already shown, so it could be tightened; it is not a 3 because of this redundancy, and not a 1 because it is not padded with conceptual explanation.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands (exact `npx jest` flags, `--bail`, `--coverage` thresholds), complete jq pipelines with zero-test guards, a full GitHub Actions workflow, and a concrete example with expected output; it is not a 2 because nothing is pseudocode or missing key details.

3 / 3

Workflow Clarity

Sequences five gates in order, separates CRITICAL (100%, bail) from HIGH (95%+) with an explicit pass/fail matrix, and includes validation checkpoints (`--bail`, coverage thresholds, zero-test `exit 1` guards) plus feedback loops (warn/review below threshold); it is not a 2 because checkpoints and error handling are explicit, not implicit.

3 / 3

Progressive Disclosure

As a single-file skill with no bundle files, it is well-organized into clear sections (When to Use, How It Works, Eval Categories, Pass/Fail Matrix, CI/CD, Anti-Patterns, Examples) with no nested references; per the simple-skills note this merits a 3, and it is not a 2 because organization is clear and content is not a monolithic wall.

3 / 3

Total

11

/

12

Passed

Description

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 is specific and occupies a distinct, low-conflict niche, but it omits an explicit 'Use when...' trigger and leans on technical jargon, leaving trigger guidance implied rather than stated.

Suggestions

Add an explicit 'Use when...' clause naming concrete deployment scenarios (e.g., 'Use before deploying EMR/EHR apps or after modifying CDSS logic, PHI handling, or clinical workflows').

Soften specialized jargon or pair it with natural phrasings users would actually say (e.g., 'drug interaction and dose checks' alongside 'CDSS accuracy').

Confirm the description answers 'when should Claude use it' as explicitly as it answers 'what it does'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance' and 'Blocks deployments on safety failures' — rather than vague language, matching the anchor for listing several specific concrete actions; it is not a 2 because it goes beyond naming a domain plus a few actions.

3 / 3

Completeness

It clearly states what the skill does but only implies when to use it with no explicit 'Use when...' trigger clause, so per the guideline a missing explicit trigger caps completeness at 2; it is not a 1 because the 'what' is clearly and fully stated.

2 / 3

Trigger Term Quality

It includes some natural terms a healthcare engineer would say ('patient safety', 'healthcare', 'deployments') but leans on specialized jargon ('CDSS accuracy', 'PHI exposure', 'clinical workflow integrity') and misses common variations; it is not a 3 because the keyword coverage is not broad and natural enough.

2 / 3

Distinctiveness Conflict Risk

It occupies a clear niche — healthcare deployment patient-safety gating with distinct triggers (CDSS, PHI, clinical workflow, healthcare deployments) — making it unlikely to fire for the wrong skill; it is not a 2 because the domain and triggers are specific enough to avoid overlap.

3 / 3

Total

10

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

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.