scientific-slides

Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.

Quality

78%

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 ./skills/scientific-slides/SKILL.md

Quality

Content

61%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 content is highly actionable with excellent executable examples and good progressive disclosure to real bundle files, but it is padded with redundant overview/philosophy/summary sections and a duplicated Quick Start, and its batch slide-generation workflow lacks an explicit validation checkpoint.

Suggestions

Trim the Overview, CRITICAL DESIGN PHILOSOPHY, and Summary sections and remove the duplicate Quick Start that restates the Default Workflow steps, cutting content that explains concepts Claude already knows.

Wire the bundled `validate_presentation.py` / visual-review workflow into the main generation flow as an explicit validate -> fix -> regenerate checkpoint so the batch operation has a real feedback loop.

Deduplicate the reference listings: describe each reference file once (either in Core Capabilities prose or in the Reference Files index, not both) to tighten navigation.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: an overview paragraph explaining what scientific presentations are, a padded "CRITICAL DESIGN PHILOSOPHY" block, repeated "Remember: Boring = Forgotten" reminders, and a Quick Start that re-states the Default Workflow steps already detailed above, all re-explaining concepts Claude already knows.	2 / 5
Actionability	Provides concrete, copy-paste-ready bash commands with real flags (e.g. `python scripts/generate_slide_image.py "..." -o slides/01_title.png --attach slides/02_intro.png`), prompt templates, and varied examples covering title/content/results/methodology cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	A clear Plan -> Generate -> Combine-to-PDF sequence exists, but this batch operation lacks an explicit validation checkpoint in the main flow (the bundled `validate_presentation.py` and visual-review reference are not wired in as a validate/fix/retry step), which caps the score at 3 per the batch-operation guideline.	3 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to verified real files (`references/.md`, `assets/`) and a Reference Files index; held at 4 because several references (slide_capabilities, presentation_workflow, etc.) are listed twice — once in Core Capabilities prose and again in Reference Files — a minor organization gap.	4 / 5
	Total	14 / 20 Passed

Description

95%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: it concisely states concrete capabilities, provides comprehensive natural trigger terms, and explicitly covers both what and when. The only minor gap is that the capability list is slightly less exhaustive than the score-5 anchor's multiple-action pattern.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities ("Provides slide structure, design templates, timing guidance, and visual validation", "Works with PowerPoint and LaTeX Beamer") with only minor coverage gaps, matching the score-4 anchor rather than the more comprehensive score-5 list.	4 / 5
Completeness	Explicitly answers both what ("Build slide decks... Provides slide structure, design templates, timing guidance, and visual validation") and when ("Use this for making PowerPoint slides, conference presentations..."), matching the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and format names ("PowerPoint slides", "conference presentations", "seminar talks", "thesis defense slides", "research presentations", "scientific talk", "LaTeX Beamer"), fitting the score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear scientific/research-talk niche with distinct triggers ("thesis defense slides", "seminar talks", "scientific talk") and minimal conflict risk with generic slide skills, fitting the score-5 anchor.	5 / 5
	Total	19 / 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/scientific-slides/SKILL.md
Commit: 1e5eeff

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.