clinic-research-design

Generates a structured prompt framework for clinical study protocols. Supports Diagnostic, Efficacy, Etiology, and Prognosis studies. Calculates sample size and provides logic guides for LLMs.

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Protocol Design/clinic-research-design/SKILL.md

Quality

Content

52%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 content contains a useful concrete command and a clear workflow, but it is heavily padded with generic templated boilerplate and references script files that are absent from the bundle. Trimming the boilerplate and either shipping or removing the script references would meaningfully improve conciseness and progressive disclosure.

Suggestions

Remove the generic templated sections (When to Use, Dependencies, Implementation Details, Validation/Safety Rules, Failure Handling, Completion Checklist) or replace them with skill-specific content; they currently restate what Claude already knows.

Either include the referenced scripts (scripts/main.py, scripts/calculators/sample_size.py, and the 4 additional scripts) in a scripts/ bundle or drop the references and validation-shortcut commands that depend on them.

Consolidate the duplicated "Validation Shortcut" and "Quick Validation" blocks (both run `python scripts/main.py --help`) into a single verification step to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is padded with large blocks of generic templated boilerplate ("When to Use", "Dependencies", "Implementation Details", "Validation and Safety Rules", "Failure Handling", "Completion Checklist") that restate things Claude already knows and add little skill-specific value. It is not a 3 because the unnecessary explanation is pervasive rather than isolated, and not a 1 because there is some concrete skill-specific content embedded.	2 / 5
Actionability	Provides a concrete, copy-paste-ready command ("python scripts/main.py --type efficacy --P 'Type 2 Diabetes' ...") and an explicit argument list covering the common case. It is not a 5 because the referenced scripts are not actually present in the bundle, so the guidance is only conditionally executable.	4 / 5
Workflow Clarity	A clear sequenced workflow exists (call the skill, read the output, execute the LLM instructions) plus a "Recommended Workflow" and "Completion Checklist" with validation checkpoints. It is not a 5 because the validation/feedback loop is generic rather than tied to a concrete re-run-and-retry step for the script.	4 / 5
Progressive Disclosure	No bundle files exist, yet the body references packaged scripts ("scripts/main.py", "scripts/calculators/sample_size.py", "4 additional script(s)") that are not present, and large amounts of generic content that belong elsewhere are inlined into a single monolithic file. It is not a 3 because the missing referenced files and inlined boilerplate undermine navigation, and not a 1 because section headers do provide some structure.	2 / 5
	Total	12 / 20 Passed

Description

66%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 clearly communicates a focused clinical-protocol capability with several concrete actions, but it omits any explicit "Use when..." trigger guidance, which caps its completeness. Adding concrete trigger phrases would lift the completeness and distinctiveness scores.

Suggestions

Add an explicit 'Use when...' clause naming the situations or user phrasings that should trigger this skill (e.g., 'Use when designing a clinical study protocol or calculating sample size for a diagnostic, efficacy, etiology, or prognosis study').

Include common user-facing synonyms and terms (e.g., 'clinical trial', 'RCT', 'study design', 'PICO') to improve trigger-term coverage.

Tighten the action list so each capability is a distinct, concrete verb phrase rather than grouping logic guides under one generic action.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Generates a structured prompt framework", "Calculates sample size", "provides logic guides" — across four named study types, with only minor coverage gaps. It is not a 5 because the actions are not as comprehensively enumerated as the top anchor.	4 / 5
Completeness	The "what" is clearly stated but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. It is not a 4 because the "when" is entirely missing rather than weakly present.	3 / 5
Trigger Term Quality	Includes fairly natural domain terms a user would say ("clinical study protocols", "sample size", "Diagnostic/Efficacy/Etiology/Prognosis"), but lacks common synonyms or file/extension variants that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	The clinical-protocol/PICO niche with four specific study types is mostly distinct with only minor overlap risk against other medical-research skills. It is not a 5 because trigger coverage is not comprehensive enough to guarantee minimal conflict.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 8 missing, 2 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Protocol Design/clinic-research-design/SKILL.md
Commit: 63c61d3

Reviewed: 3 hours 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.