residency-interview-prep
Mock interview preparation tool for residency Match interviews. Generates.
26
17%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/residency-interview-prep/SKILL.mdQuality
Discovery
22%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 description is incomplete — the sentence cuts off after 'Generates.' leaving the reader with no understanding of what the skill actually produces. It lacks a 'Use when...' clause and fails to specify concrete actions. The residency Match interview domain provides some distinctiveness, but the truncated description severely undermines its utility for skill selection.
Suggestions
Complete the truncated sentence to specify what the skill generates (e.g., 'Generates practice interview questions, sample answers, and feedback for residency Match interviews').
Add an explicit 'Use when...' clause with trigger terms like 'mock interview', 'residency interview prep', 'Match interview practice', 'ERAS', or 'interview questions'.
List 2-3 specific concrete actions the skill performs (e.g., 'Generates specialty-specific questions, provides feedback on responses, simulates panel interview scenarios').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'mock interview preparation' and 'generates' but the sentence is incomplete — it cuts off after 'Generates.' without specifying what it generates. This leaves the capabilities extremely vague. | 1 / 3 |
Completeness | The 'what' is incomplete (sentence cuts off at 'Generates.') and there is no 'when' clause or explicit trigger guidance whatsoever. Both components are weak or missing. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'mock interview', 'residency', and 'Match interviews' that users in this domain would naturally use, but the incomplete sentence limits coverage and misses variations like 'ERAS', 'practice questions', 'interview prep', or specific specialties. | 2 / 3 |
Distinctiveness Conflict Risk | The niche of 'residency Match interviews' is fairly specific and unlikely to conflict with most other skills, but the incomplete description and vague 'Generates.' could cause confusion with other interview prep or medical education skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a generic boilerplate template with minimal domain-specific content about residency interview preparation. The vast majority of the content is reusable template filler (risk assessment, security checklist, lifecycle status, response templates) that provides no value for the stated task. The few domain-relevant sections (Features, Input Parameters, Output Format) are buried and lack concrete examples of actual interview questions, STAR format guidance, or feedback mechanisms.
Suggestions
Remove all generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Input Validation template text) and focus on domain-specific interview prep content—example questions, STAR format templates, specialty-specific guidance.
Add concrete, executable examples: show 2-3 sample behavioral questions with model STAR-format responses and specific feedback annotations rather than just referencing a script.
Eliminate circular self-references ('See ## Features above') and either inline the content where first needed or remove the duplicate references entirely.
Provide actual content from the 'references/' directory and 'scripts/main.py' or remove references to files that don't exist in the bundle—the skill should be self-contained if no bundle is provided.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded with boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) that add no actionable value. Multiple self-referential 'See above' links that are circular. The actual domain-specific content (interview prep features, input parameters, output format) is buried under generic template filler that Claude doesn't need. | 1 / 3 |
Actionability | No concrete examples of how to actually generate interview questions or provide feedback. The 'Example Usage' just shows how to run a Python script with --help. There's no executable code for the core task (generating behavioral questions, providing STAR format feedback), and the workflow steps are entirely generic and abstract. | 1 / 3 |
Workflow Clarity | There is a numbered workflow and an example run plan with sequential steps, but the steps are generic boilerplate ('Confirm the user objective', 'Validate that the request matches') with no domain-specific validation checkpoints. The error handling section exists but is also generic. No feedback loops specific to interview prep quality. | 2 / 3 |
Progressive Disclosure | Contains circular self-references ('See ## Features above', 'See ## Prerequisites above', 'See ## Workflow above') that point to sections within the same document. No bundle files are provided despite references to 'references/' directory and 'scripts/main.py'. The document is a monolithic wall of mostly boilerplate sections with poor organization—domain-specific content (Features, Input Parameters, Output Format) appears late after pages of generic template. | 1 / 3 |
Total | 5 / 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
73f6514
- 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.