clinical-research

Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging), estimating sample size and power for two-arm designs (means / proportions / survival), or scoring a study plan for feasibility and a GO / GO-WITH-CONDITIONS / REDESIGN / NO-GO phase-gate decision. Every output is an ESTIMATE plus a named human owner (clinician / biostatistician / regulatory owner) — never clinical fact, never a finished protocol. Distinct from ra-qm-team, which handles the regulatory/QM submission (ISO 13485, EU MDR, FDA 510(k)/PMA/QSR), not the study design.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

86%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 highly actionable with real, executable scripts and a well-structured one-level-deep bundle. Conciseness and workflow_clarity sit at 4 due to minor Purpose/Scripts redundancy and the absence of an explicit error-recovery loop rather than any substantive gap.

Suggestions

Collapse the per-tool descriptions so each tool is described once (e.g., keep detail in the Scripts table and shorten the Purpose list to a one-line role each) to remove the Purpose/Scripts redundancy.

Add an explicit feedback loop after step 4: if phase_gate_scorer returns REDESIGN or NO-GO, state which earlier step (endpoint or sample size) to revisit before re-scoring.

Surface a couple of trigger synonyms in the description (e.g., 'clinical trial', 'protocol synopsis') to lift trigger-term coverage from 4 to 5.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no basic-concept padding, guidelines cited by name), but the three-tool description in 'Purpose' repeats in the 'Scripts' table, a minor over-explanation that could be trimmed — fitting level 4 rather than the lean level 5.	4 / 5
Actionability	Fully executable, copy-paste-ready commands are given throughout ('sample_size_estimator.py --design proportions --p1 0.30 --p2 0.45 --dropout 0.15', '--profile {drug\|device\|biologic\|diagnostic\|digital-therapeutic}', '--phase {1\|2\|3\|4}') with a 'Quick examples' block covering the common cases, matching the level-5 anchor.	5 / 5
Workflow Clarity	A clear 5-step sequence (Draft synopsis → Select endpoint → Estimate sample size → Score feasibility → Route for sign-off) carries checkpoints ('If >1 primary, plan multiplicity control', 'Trace the effect ... to a published or anchor-based source; inflate for dropout'), but no explicit validate→fix→retry recovery loop, so it lands at level 4 rather than 5; the destructive/batch cap does not apply since outputs are estimates/recommendations.	4 / 5
Progressive Disclosure	SKILL.md is a clean overview with one-level-deep, clearly labeled references (study_design_canon.md, endpoint_and_power.md, trial_operations.md each with a one-line contents description), a scripts table, and an asset template — all verified to exist — matching the level-5 anchor for well-signaled navigation.	5 / 5
	Total	18 / 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 specific, trigger-led, and clearly bounded against sibling skills, with concrete actions and an explicit 'Use when' clause. The only soft spot is trigger-term synonym coverage, which keeps trigger_term_quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging)', 'estimating sample size and power for two-arm designs (means / proportions / survival)', 'scoring a study plan for feasibility and a GO / GO-WITH-CONDITIONS / REDESIGN / NO-GO phase-gate decision' — with comprehensive coverage, matching the score-5 anchor rather than the minor-gaps level 4.	5 / 5
Completeness	An explicit 'Use when designing a prospective clinical study before submission' trigger pairs with a concrete 'what' (endpoint selection/classification, sample-size/power estimation, feasibility scoring), clearly answering both questions per the level-5 anchor.	5 / 5
Trigger Term Quality	Natural domain terms a clinical R&D user would say are present ('sample size and power', 'endpoints', 'feasibility', 'phase-gate', 'prospective clinical study'), but common synonyms like 'clinical trial', 'protocol', or 'study design' are not surfaced, so it sits just below the comprehensive level-5 anchor.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (prospective study design) and explicitly bounds the sibling — 'Distinct from ra-qm-team, which handles the regulatory/QM submission ... not the study design' — minimizing wrong-skill triggering per the level-5 anchor.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: research-ops/skills/clinical-research/SKILL.md
Commit: 19392f7

Reviewed: ~1 hour ago

Table of Contents

Discovery Implementation Validation

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.