CtrlK
BlogDocsLog inGet started
Tessl Logo

shift-handover-summarizer

Generate structured shift handover summaries from EHR records, highlighting critical events, vital sign changes, and pending tasks for incoming clinical staff.

61

Quality

72%

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 ./scientific-skills/Other/shift-handover-summarizer/SKILL.md
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.

The body is well-structured, concise, and actionable with a real externalized script, concrete commands, explicit validation steps, and checklists for a clinical-safety context. Scores are consistently strong across all dimensions with only minor gaps.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's knowledge (no explanation of what EHR/vitals are), with a justified clinical disclaimer; matches anchor 4 (efficient, minor trimmable instances) due to small redundancy — Error Handling restates Workflow step 6, and Stress-Case Rules overlaps the Response Template. Not 5 because of that redundancy; not 3 because it is tighter than 'mostly efficient with some unnecessary explanation.'

4 / 5

Actionability

The Usage block is a complete copy-paste command, Quick Check is executable, the Parameters table matches the real scripts/main.py args, and the timezone step gives exact warning text to emit — matching anchor 4 (mostly executable, minor gaps). Not 5 because Workflow step 4 references an undefined 'manual extraction path'; not 3 because guidance is concrete and executable rather than pseudocode.

4 / 5

Workflow Clarity

A 6-step sequenced workflow with explicit validation checkpoints (validate records within shift range, timezone-offset warning), plus checklists (Stress-Case Rules, Response Template) and an error-recovery fallback, matches anchor 4. Not 5 because validation failures are handled generically in a separate section rather than as a closed validate→fix→retry loop within the flow; not 3 because checkpoints are present and explicit.

4 / 5

Progressive Disclosure

SKILL.md is a clear overview with well-organized sections, and the 539-line implementation is appropriately externalized into scripts/main.py as a well-signaled one-level-deep reference (verified as a real file whose args match the documented parameters), matching anchor 4. Not 5 because no detailed reference files are split out for the heavier frameworks, though they are concise enough inline; not 3 because structure and signaling are clear, not buried.

4 / 5

Total

16

/

20

Passed

Description

70%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.

The description is specific and distinct with good natural trigger terms, but it lacks an explicit 'Use when...' clause, which caps completeness and leaves the activation trigger implicit. Adding a concrete 'when to use' phrase would raise the weakest dimension.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when generating end-of-shift handover summaries from EHR records or when prioritizing patients by event severity for incoming staff.'

Add common synonyms such as 'handoff' and 'EMR' alongside 'handover' and 'EHR' to broaden natural trigger coverage.

Reframe the highlighted components (critical events, vital sign changes, pending tasks) as distinct actions (e.g. 'rank patients by priority, summarize vital-sign trends, list pending tasks') to strengthen specificity.

DimensionReasoningScore

Specificity

Quotes 'Generate structured shift handover summaries from EHR records, highlighting critical events, vital sign changes, and pending tasks' name the domain plus several concrete output components, matching anchor 4 (several specific actions, minor gaps); not 5 because the core action is a single 'generate' rather than multiple distinct actions, and not 3 because it goes well beyond naming the domain.

4 / 5

Completeness

It has a clear, detailed 'what' but no explicit 'Use when...' trigger clause, so per the judging guideline completeness is capped at anchor 3 ('clear what but when missing/weakly implied'); not 4 because there is no explicit 'when' guidance, and not 2 because the 'what' is specific rather than vague.

3 / 5

Trigger Term Quality

Natural clinical phrases ('shift handover summaries', 'EHR records', 'vital sign changes', 'pending tasks', 'clinical staff') give good keyword coverage matching anchor 4; not 5 because common synonyms (handoff, EMR) and any file extensions are absent, and not 3 because coverage is more than 'some' relevant keywords.

4 / 5

Distinctiveness Conflict Risk

The 'EHR records' + 'shift handover summaries' framing is a clear niche with distinct triggers and minimal overlap with other skills, matching anchor 5; not 4 because it is more specific than 'mostly distinct with minor overlap' examples.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
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.