pptx-posters
Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual integration.
80
76%
Does it follow best practices?
Impact
83%
1.48xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/pptx-posters/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that excels at completeness and distinctiveness by explicitly defining when to use this skill versus the alternative (latex-posters). Trigger terms are well-covered with natural keywords like 'PowerPoint', 'PPTX', and 'research posters'. The main weakness is that the specificity of concrete actions could be stronger — the last sentence about 'modern web-based poster design with responsive layouts' reads as marketing fluff rather than actionable capability description.
Suggestions
Replace the vague closing sentence ('modern web-based poster design with responsive layouts and easy visual integration') with specific concrete actions, e.g., 'Supports custom layouts, image placement, charts, and multi-column designs.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (research posters) and mentions HTML/CSS creation with export to PDF/PPTX, but doesn't list multiple specific concrete actions beyond 'create' and 'export'. Phrases like 'modern web-based poster design with responsive layouts and easy visual integration' are somewhat vague/fluffy. | 2 / 3 |
Completeness | Clearly answers both 'what' (create research posters using HTML/CSS exportable to PDF/PPTX) and 'when' (explicitly states 'Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format' and differentiates from latex-posters). The explicit trigger guidance is well-defined. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'research posters', 'HTML/CSS', 'PDF', 'PPTX', 'PowerPoint', 'poster format', 'web-based poster'. These cover terms users would naturally use when requesting this type of work. | 3 / 3 |
Distinctiveness Conflict Risk | Excellent distinctiveness — explicitly differentiates itself from the latex-posters skill, specifies the exact trigger condition (PPTX/PowerPoint poster format), and carves out a clear niche for HTML/CSS-based poster creation vs LaTeX-based. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels in actionability with concrete, executable examples and has excellent workflow clarity with explicit validation checkpoints and feedback loops. However, it suffers significantly from verbosity and repetition—the same rules about element counts, font sizes, and simplification are restated 3-4 times across different sections. The content would benefit greatly from deduplication and moving detailed checklists/guidelines to referenced files.
Suggestions
Deduplicate the repeated graphic simplification rules (3-4 elements max, 50% white space, font sizes) into a single authoritative section, and reference it from other sections instead of restating it.
Move the detailed quality checklist and common pitfalls sections to a separate referenced file (e.g., the already-mentioned poster_quality_checklist.md in assets/), keeping only a brief summary with a link in the main skill.
Remove the 'When to Use / When Not to Use' section or reduce it to 1-2 lines—the YAML description already handles routing, and Claude doesn't need 12 bullet points to understand format selection.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines with significant repetition. The font size requirements, content overflow rules, and simplification guidelines are repeated multiple times across sections (e.g., the '3-4 elements max' rule appears in at least 4 places). The 'When to Use' section is overly detailed for routing logic Claude can handle. Many sections explain obvious concepts. | 1 / 3 |
Actionability | The skill provides fully executable code examples throughout: bash commands for generating schematics, Chrome headless PDF export commands, python-pptx code for direct PPTX creation, and concrete HTML/CSS snippets. The template path, directory structure, and specific commands are all copy-paste ready. | 3 / 3 |
Workflow Clarity | The 5-stage workflow (Planning → Generate Visuals → Create HTML → Export PDF → Convert PPTX) is clearly sequenced with explicit validation checkpoints. The quality checklist includes mandatory pre-generation review, post-generation review with pass/fail criteria, and post-export verification. Feedback loops for regeneration are explicitly defined. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (template in assets/, references/ directory with design guides) but the main SKILL.md itself is a monolithic wall of content. Much of the detailed graphic generation guidelines, quality checklists, and common pitfalls could be split into separate reference files, keeping the main skill leaner with clear pointers. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
25e1c0f
- Reviewed
Table of Contents
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.