CtrlK
BlogDocsLog inGet started
Tessl Logo

real-world-evidence-study-designer

Designs a structured real-world evidence study using EHR, claims, or registry data, with explicit handling of time zero, eligibility windows, exposure definitions, outcome windows, censoring, confounding control, and target-trial-emulation logic. Use this skill when the user needs study-type design and protocol framing for an observational clinical study based on routine-care data. Do not invent database fields, follow-up completeness, linkage, coding validity, or causal identifiability.

67

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 with excellent progressive disclosure via verified reference files and a prescriptive output structure, but it is held back by structural redundancy across its overview-style sections and the absence of a worked example and explicit self-review loop.

Suggestions

Consolidate the overlapping enumerations in Core Function, Workflow Standard, Mandatory Output Structure, and Quality Standard so each design dimension is defined once and cross-referenced, reducing token redundancy.

Add one short worked example (e.g. a skeleton blueprint for the GLP-1RA/kidney-outcome trigger) showing the expected A–L output to make the guidance copy-paste concrete.

Add an explicit self-review step at the end of the Workflow Standard (validate output against the Hard Rules and section completeness, fix gaps, re-check) to close the feedback-loop gap.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but the core design dimensions (time zero, exposure, confounding, censoring, target-trial emulation) are restated across Core Function, Workflow Standard, Mandatory Output Structure, Hard Rules, and Quality Standard, producing noticeable redundancy that could be tightened.

3 / 5

Actionability

Guidance is concrete and prescriptive — a fixed A–L section structure, a redirect-and-stop template, and ten numbered hard rules — but a worked example of a completed blueprint output is missing, leaving a minor gap below the fully-copy-paste-ready anchor.

4 / 5

Workflow Clarity

A clear 10-step Workflow Standard is present with checkpoints (out-of-scope redirect-and-stop, the 'incomplete if reference module not used' completeness gate, bias-review section), but there is no explicit self-review/fix-retry feedback loop, so it sits just below the top anchor.

4 / 5

Progressive Disclosure

A dedicated Reference Module Integration section maps each of nine real, one-level-deep reference files to a specific output section, with all referenced paths verified to exist, giving clear overview-with-signaled-references navigation.

5 / 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.

The description is concise, third-person, and explicitly pairs a comprehensive 'what' with a concrete 'when' trigger clause. It is distinctive and action-specific, with only minor room to add a few more natural synonyms.

DimensionReasoningScore

Specificity

The description lists multiple concrete design actions — 'time zero, eligibility windows, exposure definitions, outcome windows, censoring, confounding control, and target-trial-emulation logic' — giving comprehensive coverage of the domain, matching the top anchor rather than the 'several specific actions; minor gaps' anchor below.

5 / 5

Completeness

It explicitly answers both what ('Designs a structured real-world evidence study...') and when ('Use this skill when the user needs study-type design and protocol framing...') with concrete trigger phrases, and uses third-person voice, satisfying the top anchor with no missing-trigger cap.

5 / 5

Trigger Term Quality

Strong natural domain keywords appear ('EHR, claims, or registry data', 'observational clinical study', 'routine-care data', 'study-type design and protocol framing'), but a few common synonyms a user might say (e.g. 'comparative effectiveness', 'cohort study') are absent, so it sits just below the comprehensive-coverage anchor.

4 / 5

Distinctiveness Conflict Risk

The RWE study-design niche with EHR/claims/registry triggers is highly specific and unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

19

/

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.