residency-interview-prep

Mock interview preparation tool for residency Match interviews. Generates.

Quality

50%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/residency-interview-prep/SKILL.md

Quality

Content

50%

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

The body has a genuine executable script and correctly signaled one-level-deep references, but it is padded with generic process boilerplate and offers only soft validation rather than concrete, residency-specific actionable workflows.

Suggestions

Trim generic template sections (Lifecycle Status, Evaluation Criteria, Response Template, Output Requirements) that are not residency-specific, or move them to a reference file, to improve token efficiency.

Replace the soft workflow validation step with a concrete checkpoint, e.g. 'Run `python -m py_compile scripts/main.py` and confirm the question_type is one of behavioral/clinical/program/ethical before generating output.'

Add a short residency-specific usage example in the body showing an actual command with a real question_type and the expected output, rather than only generic process guidance.

Dimension	Reasoning	Score
Conciseness	The body is structured and does not explain basic concepts Claude already knows, but it carries substantial generic templated boilerplate (Security Checklist, Risk Assessment, Lifecycle Status, Evaluation Criteria, Output Requirements, Response Template) that is largely process-template padding rather than residency-specific guidance and could be tightened — not level 1 (no concept tutorials) but not the lean level 3 either.	2 / 3
Actionability	There are concrete executable commands ('python -m py_compile scripts/main.py', 'python scripts/main.py demo'), a real working script, an input parameters table, and an output JSON schema, but the body's core instructional guidance is generic process direction ('validate the request, choose the packaged workflow') rather than specific steps for interview prep, so it is incomplete rather than fully copy-paste ready.	2 / 3
Workflow Clarity	A 5-step Workflow and an Error Handling/fallback path are present and the Quick Check provides one concrete py_compile checkpoint, but the main validation step ('Validate that the request matches the documented scope') is soft and implicit rather than a concrete technical checkpoint, leaving sequence gaps — not level 1 (sequence exists) but not the explicit validated level 3.	2 / 3
Progressive Disclosure	Bundle files exist and are real and one level deep (references/guidelines.md and scripts/main.py), both clearly signaled in the body, but the body itself is a fairly monolithic run of generic boilerplate that could be trimmed or split, so organization is adequate but not the cleanly compartmentalized level 3.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 targets a clear niche (residency Match interview prep) but is undermined by a truncated sentence ending in 'Generates.', giving only a partial statement of what the skill does and no explicit 'when to use' trigger.

Suggestions

Complete the truncated sentence: replace 'Generates.' with the concrete outputs, e.g. 'Generates behavioral, clinical, program, and ethical interview questions with STAR-structured guidance and feedback.'

Add an explicit trigger clause: 'Use when a user is preparing for residency or NRMP Match interviews, needs mock interview practice, or wants interview question examples and response feedback.'

Include natural variations users would actually say (e.g., 'residency interview questions', 'practice interview', 'NRMP Match') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('residency Match interviews') and a class of action ('Mock interview preparation tool') but the sentence is literally truncated at 'Generates.', so it does not list multiple concrete actions and is not comprehensive — not level 3, and not level 1 because a real action and domain are named.	2 / 3
Completeness	It states a partial 'what' (mock interview preparation) but the sentence is truncated and there is no 'Use when...' clause or equivalent trigger guidance, so per the judging guidelines 'when' is missing and completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes some natural terms a user would say ('interview', 'Match', 'residency', 'Mock interview') but misses common variations like 'residency interview questions', 'practice interview', or 'NRMP', so coverage is partial rather than strong.	2 / 3
Distinctiveness Conflict Risk	'residency Match interviews' is a fairly distinct niche, but the truncated 'Generates.' leaves the skill's full behavior underspecified, so it is only somewhat specific rather than a cleanly defined niche that clearly avoids overlap.	2 / 3
	Total	8 / 12 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: aipoch/medical-research-skills
Commit: 7cc5680

Reviewed: 3 days 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.