irb-application-assistant

Assists researchers with Institutional Review Board (IRB) application tasks, including drafting informed consent documents, reviewing research protocols for compliance, generating application forms, and preparing submission checklists. Use when the user mentions IRB, Institutional Review Board, research ethics, human subjects research, protocol review, informed consent, or needs help preparing or reviewing an IRB application or submission.

Quality

67%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Academic Writing/irb-application-assistant/SKILL.md

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that clearly articulates specific capabilities, provides comprehensive trigger terms covering natural user language, and explicitly states both what the skill does and when to use it. The IRB/research ethics domain is well-defined and distinctive, minimizing conflict risk with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: drafting informed consent documents, reviewing research protocols for compliance, generating application forms, and preparing submission checklists.	3 / 3
Completeness	Clearly answers both 'what' (drafting consent documents, reviewing protocols, generating forms, preparing checklists) and 'when' with an explicit 'Use when...' clause listing specific trigger scenarios.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'IRB', 'Institutional Review Board', 'research ethics', 'human subjects research', 'protocol review', 'informed consent', 'IRB application', 'submission'. These are all terms a researcher would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche focused on IRB and research ethics compliance. The specific domain terminology (IRB, human subjects research, protocol review, informed consent) makes it very unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

35%

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

This skill has a solid domain-specific core in its 'Core Capabilities' and 'Recommended Workflow' sections, with concrete CLI commands and explicit validation checkpoints. However, it is severely undermined by extreme verbosity, heavy redundancy across overlapping sections, and extensive boilerplate that explains things Claude already knows. The skill would benefit enormously from consolidation — removing duplicate sections, cutting generic instructions, and trusting Claude's baseline competence.

Suggestions

Remove redundant sections: consolidate 'Workflow', 'Example Usage run plan', 'Quick Start', and 'Recommended Workflow' into a single workflow section. The 'Recommended Workflow' is the strongest — keep that and cut the others.

Delete boilerplate sections that describe Claude's default behavior: 'Output Requirements', 'Response Template', 'Input Validation', and 'Error Handling' add little that Claude doesn't already know how to do. Keep only domain-specific constraints.

Stop copy-pasting the skill description verbatim into 'When to Use' and 'Key Features' — replace with a brief trigger list (e.g., 'Trigger: user mentions IRB, informed consent, protocol review, human subjects research').

Define the expected schema or key fields for input files (protocol.json, study_config.json) so the commands are truly actionable rather than aspirational.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and repetitive. The skill description is copy-pasted verbatim into 'When to Use' and 'Key Features' sections. Multiple sections overlap heavily (Workflow, Recommended Workflow, Quick Start, Example Usage all cover similar ground). Boilerplate sections like 'Output Requirements', 'Response Template', 'Input Validation', and 'Error Handling' explain things Claude already knows how to do. The document could be cut by 60%+ without losing actionable content.	1 / 3
Actionability	The 'Core Capabilities' and 'Recommended Workflow' sections provide concrete CLI commands with specific flags and arguments, which is good. However, none of this is verifiably executable — there are no bundle files provided, no confirmation that scripts/main.py exists or accepts these flags, and the commands appear to be aspirational rather than tested. The protocol.json and study_config.json formats are never defined.	2 / 3
Workflow Clarity	The 'Recommended Workflow' section has a clear 6-step sequence with two explicit checkpoints (compliance check and submission validation) including feedback loops. This is well done. However, there are competing workflow sections ('Workflow', 'Example Usage run plan', 'Recommended Workflow') that create confusion about which to follow. The generic 'Workflow' section is vague and abstract, diluting the good specific workflow.	2 / 3
Progressive Disclosure	References to 'references/guide.md', 'references/examples/', and 'references/audit-reference.md' are present and clearly signaled. However, no bundle files are provided to verify these exist. The main document itself is monolithic with significant redundancy across sections rather than being a concise overview pointing to detailed materials. Content that could be in separate files (quality checklist, response template, error handling) is all inline.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: aipoch/medical-research-skills
Commit: d3c2c0f

Reviewed: about 6 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.