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.
73
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/irb-application-assistant/SKILL.mdQuality
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 defines its scope with multiple concrete actions, provides comprehensive trigger terms covering both acronyms and full phrases a researcher would use, and explicitly states when to activate. It occupies a distinct niche that is unlikely to overlap 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 suffers significantly from verbosity and redundancy—the same information is repeated across multiple sections (scope description appears 3 times, workflow appears twice, audit commands appear twice). The IRB-specific content in the 'Recommended Workflow,' 'Core Capabilities,' and 'Quality Checklist' sections is genuinely useful and well-structured, but it's buried under layers of generic boilerplate about error handling, input validation, and response templates that don't add IRB-specific value. The skill would be dramatically improved by removing duplicate sections and generic scaffolding.
Suggestions
Remove duplicate content: consolidate the two workflow sections into one, merge the two reference sections, and eliminate the repeated verbatim skill description from 'When to Use' and 'Key Features'.
Remove generic boilerplate sections (Output Requirements, Response Template, Input Validation, Error Handling) that don't contain IRB-specific guidance—Claude already knows how to handle missing inputs and structure responses.
Move the 'Core Capabilities' detailed command examples into a separate reference file and keep only a summary table in the main SKILL.md to improve progressive disclosure.
Add concrete examples of what study_config.json and protocol.json should contain (even a minimal schema) to make the commands truly actionable rather than dependent on undocumented file formats.
| 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 repeat the same information (e.g., 'Quick Check' and 'Audit-Ready Commands' are nearly identical, 'Workflow' and 'Recommended Workflow' overlap significantly). Generic boilerplate about output requirements, error handling, input validation, and response templates pad the content heavily without adding IRB-specific value. | 1 / 3 |
Actionability | The skill provides concrete CLI commands with specific flags (--task consent, --task compliance-check, etc.) which is good, but these commands reference a script (scripts/main.py) whose actual implementation and capabilities are unknown. The commands appear plausible but there's no way to verify they're executable as shown. The workflow steps are concrete but rely entirely on this opaque script rather than providing actionable guidance Claude could use directly. | 2 / 3 |
Workflow Clarity | The 'Recommended Workflow' section has a clear 6-step sequence with two explicit checkpoints (steps 2 and 5) including feedback loops for error recovery, which is strong. However, there are two competing workflow sections ('Workflow' with generic steps and 'Recommended Workflow' with specific steps) creating confusion. The generic 'Workflow' section is vague and abstract, diluting the quality of the specific one. The quality checklist is a nice addition. | 2 / 3 |
Progressive Disclosure | References to external files (references/guide.md, references/examples/, references/audit-reference.md) are present and clearly signaled. However, the SKILL.md itself is monolithic and bloated with sections that could be consolidated or removed. Content is poorly organized with redundant sections (two workflow sections, two reference sections, repeated scope descriptions) making navigation difficult. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%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
8277276
- 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.