short-video-script-generator

Generate popular science short video scripts based on topic, duration, and style. Invoke when the user needs to create scripts for short science videos.

Quality

48%

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/short-video-script-generator/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 body is dominated by generic template boilerplate and provides only abstract generation guidance with no concrete script templates or examples. Its sectioning and input options are clear, but actionable depth and token efficiency are weak.

Suggestions

Replace the generic wrapper sections with skill-specific content: per-style script templates, hook/opening patterns, and at least one full example script for a representative duration.

Make the workflow concrete by specifying what 'generate outline' and 'refine details' produce for each script type (Spoken vs Storyboard), with explicit acceptance checks before output.

Remove the boilerplate that restates general process discipline (When to Use, Implementation Details, Deterministic Output Rules) and keep only guidance specific to short science video scripts.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic boilerplate ('Use this skill when the request matches its documented task boundary', 'Execution model: validate the request, choose the packaged workflow') that restates process guidance Claude already knows, fitting the 'noticeably verbose; several unnecessary padded sections' anchor.	2 / 5
Actionability	While the Inputs section lists concrete options, the core workflow is only high-level hints ('Generate script outline for the specific type', 'Refine script details') with no templates, per-style examples, or executable guidance, matching the 'minimal concrete guidance; high-level hints' anchor.	2 / 5
Workflow Clarity	A four-step sequence is present and the Validation/Safety Rules plus Completion Checklist add some checkpoints, but the steps themselves are abstract with no explicit validation feedback loop between generate and output, fitting the 'steps listed but checkpoints implicit' anchor.	3 / 5
Progressive Disclosure	Content is organized into clear sections and the referenced scripts/validate_skill.py is a real file, but everything is inlined in one file and the only bundle script is a stub that does not offload real detail, matching the 'some structure but content that could be separate is inline' anchor.	3 / 5
	Total	10 / 20 Passed

Description

62%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 clearly answers both what the skill does and when to invoke it, with a reasonably distinct niche. It is let down by thin trigger-term coverage and a single stated action rather than comprehensive capabilities.

Suggestions

Add 2-3 natural trigger variations (e.g. 'science explainer videos', 'short-form science content', 'Reels/TikTok science scripts') to improve trigger-term coverage.

List additional concrete actions (e.g. structure hooks, draft voiceover/storyboard, fit duration pacing) to raise specificity beyond a single 'generate' verb.

Dimension	Reasoning	Score
Specificity	It names the domain ('popular science short video scripts') and concrete inputs ('topic, duration, and style') but offers only a single action (generate), matching the anchor that lists a domain plus 1-2 actions without comprehensive coverage.	3 / 5
Completeness	It explicitly states both what ('Generate popular science short video scripts based on topic, duration, and style') and when ('Invoke when the user needs to create scripts for short science videos'), but the trigger could list more concrete variations, so it sits just below the fully comprehensive anchor 5.	4 / 5
Trigger Term Quality	Phrases like 'short video scripts' and 'short science videos' are reasonably natural, but coverage lacks synonyms and common variations (e.g. 'science explainer', 'TikTok/Reels script'), fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The 'popular science short video scripts' niche is mostly distinct with only minor overlap risk against general video-script or copywriting skills, matching the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	14 / 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/short-video-script-generator/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.