expert-interview-generator

Generates a full expert interview article including introduction, Q&A body, and summary based on interview questions and expert background. Use when you have interview questions and an expert profile and need a polished article.

Quality

70%

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/Other/expert-interview-generator/SKILL.md

Quality

Content

53%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 skill has a solid, well-structured workflow with real, clearly-signaled reference files, but is dragged down by heavy generic boilerplate that pads the SKILL.md without adding domain-specific value and by missing explicit validation checkpoints between generation steps.

Suggestions

Remove the generic template sections (Key Features, Implementation Details, Output Contract, Failure Handling, Validation and Safety Rules) or collapse them into a few lines — 'Key Features' currently just restates the description verbatim.

Add explicit validation checkpoints between workflow steps (e.g., verify the generated intro/Q&A meets the word-count and format constraints before moving to the next step) to lift workflow_clarity.

Tighten 'When to Use', 'Required Inputs', and 'Example Usage run plan' to the few sentences that are actually specific to expert-interview generation rather than reusable process filler.

Dimension	Reasoning	Score
Conciseness	The body carries substantial generic boilerplate ('Key Features' restates the description verbatim, plus 'Output Contract', 'Failure Handling', 'Validation and Safety Rules', 'Required Inputs' template filler) that Claude already knows, fitting 'noticeably verbose; several unnecessary padded sections'.	2 / 5
Actionability	Provides a concrete 5-step workflow pointing to named prompts in references/prompts.md, real inputs per step, executable bash examples, and scripts/flow.py — 'mostly executable guidance with minor gaps'.	4 / 5
Workflow Clarity	Steps are clearly sequenced with branching (Path A/B on text1) and per-step inputs, but inter-step validation checkpoints are missing or only implicit, matching 'steps listed but validation gaps; checkpoints missing'.	3 / 5
Progressive Disclosure	Detailed prompts are correctly offloaded one level deep to references/prompts.md and clearly signaled by name, with the assembler in scripts/flow.py; the SKILL.md is an overview, though generic boilerplate sections could be trimmed for cleaner navigation.	4 / 5
	Total	13 / 20 Passed

Description

87%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 is strong: third-person voice, explicit what-and-when structure, concrete deliverable components, and a distinct niche. The only minor gap is trigger-term breadth (no synonyms or file extensions).

Dimension	Reasoning	Score
Specificity	Names the domain ('expert interview article') and three concrete deliverable parts ('introduction, Q&A body, and summary'), matching the anchor listing several specific actions with minor coverage gaps rather than the comprehensive 5-action anchor.	4 / 5
Completeness	Explicitly states both what it does ('Generates a full expert interview article including introduction, Q&A body, and summary') and when to use it ('Use when you have interview questions and an expert profile and need a polished article'), matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('interview questions', 'expert profile', 'polished article') but misses common synonyms and file extensions, fitting 'good keyword coverage; a few natural terms missing'.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche ('expert interview article' from 'interview questions and an expert profile') with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	18 / 20 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
Path: scientific-skills/Other/expert-interview-generator/SKILL.md
Commit: 63c61d3

Reviewed: 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.