science-popularization-article

Generates science popularization articles with titles and outlines based on medical topics and style preferences. Invoke when user needs to create medical/science popular content for public education.

Quality

52%

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/science-popularization-article/SKILL.md

Quality

Content

35%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 presents a recognizable workflow but is undermined by generic boilerplate, broken value placeholders, contradictory validation guidance, and a lack of concrete prompts or examples. The packaged validation script is a stub that does not actually validate output.

Suggestions

Replace the broken '****' placeholders in Input Requirements and Style Guidelines with the actual parameter names and style values.

Cut the duplicated generic boilerplate (When to Use / When Not to Use, Recommended Workflow / Output Contract / Deterministic Output Rules) and keep only skill-specific guidance.

Add a concrete example: a sample topic, the 3 candidate titles it would produce, and a skeleton outline, so the workflow is executable rather than descriptive.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic boilerplate ('When to Use', 'Dependencies', 'Implementation Details', 'Deterministic Output Rules', 'Completion Checklist') that restates process discipline Claude already applies, and duplicates guidance across overlapping sections.	2 / 5
Actionability	Workflow steps are high-level hints ('Creates 3 style-appropriate titles', 'Chooses the most engaging title') with no concrete prompts, templates, or title/outline examples, and the Input Requirements and Style Guidelines contain broken '****' placeholders where values should be.	2 / 5
Workflow Clarity	A five-step sequence is listed with a Quality Control step and a completion checklist, but checkpoints are mostly implicit and two validation sections contradict each other (a 'Validation Shortcut' referencing a script vs. 'No local script validation step is required').	3 / 5
Progressive Disclosure	Section headers provide some structure and the referenced scripts/validate_skill.py is a real one-level file, but the bulk of generic guidance is inlined in a single monolithic file rather than split out, and the referenced script is only a stub.	3 / 5
	Total	10 / 20 Passed

Description

70%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 cleanly states both what the skill does and when to invoke it, with concrete trigger language for a well-scoped niche. It is held back from the top band by limited action enumeration and a single trigger clause rather than varied synonyms.

Suggestions

Add 2-3 more concrete actions (e.g., 'drafts ~2500-word articles', 'applies easy-to-understand or professional style') to lift specificity.

Expand the trigger clause with synonyms users naturally say (e.g., 'health articles', 'patient education materials', 'science communication').

Dimension	Reasoning	Score
Specificity	Names the domain ('science popularization articles') and 1-2 concrete actions ('titles and outlines') but does not enumerate comprehensive capabilities like content drafting or quality control.	3 / 5
Completeness	Both 'what' (generates articles with titles and outlines) and 'when' (Invoke when user needs to create medical/science popular content) are present; the 'when' is explicit but could list more varied trigger phrasings to reach a 5.	4 / 5
Trigger Term Quality	Good natural keyword coverage ('medical topics', 'style preferences', 'science popular content', 'public education') with a clear 'Invoke when' clause, though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	The medical/science popularization niche is mostly distinct with specific triggers, with only minor overlap risk against general writing or content-generation skills.	4 / 5
	Total	15 / 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/science-popularization-article/SKILL.md
Commit: 63c61d3

Reviewed: 5 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.