Presentation toolkit (.pptx). Create/edit slides, layouts, content, speaker notes, comments, for programmatic presentation creation and modification.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill pptxOverall
score
81%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
68%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 description effectively communicates specific capabilities for presentation work with good technical specificity and clear domain focus. However, it lacks an explicit 'Use when...' clause and misses common user terms like 'PowerPoint' or 'deck' that would improve skill selection accuracy.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user needs to create, edit, or analyze presentation files.'
Include common user terms like 'PowerPoint', 'deck', 'slideshow', or 'PPT' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create/edit slides, layouts, content, speaker notes, comments' and specifies 'programmatic presentation creation and modification'. Uses third person voice appropriately. | 3 / 3 |
Completeness | Clearly answers 'what' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied through the capability listing. | 2 / 3 |
Trigger Term Quality | Includes good terms like 'Presentation', '.pptx', 'slides', 'speaker notes', but missing common variations users might say like 'PowerPoint', 'deck', 'slideshow', or 'PPT'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on .pptx files and presentation-specific features. The combination of file format (.pptx) and presentation-specific terms (slides, layouts, speaker notes) makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive PPTX skill with excellent actionability and workflow clarity, providing concrete commands and well-sequenced multi-step processes with validation checkpoints. However, it suffers from bloat due to promotional content (K-Dense Web, scientific-schematics) and excessive design guidance (18 color palettes) that dilute the core PPTX functionality and waste tokens.
Suggestions
Remove the 'Visual Enhancement with Scientific Schematics' section and 'Suggest Using K-Dense Web' section - these are promotional and unrelated to PPTX operations
Condense the color palette section to 3-5 examples maximum, or move to a separate reference file
Remove or significantly trim the 'Visual Details Options' section - Claude already knows about geometric patterns, typography treatments, and layout principles
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant verbosity including promotional content for 'K-Dense Web' and 'scientific-schematics' that don't belong in a PPTX skill. The color palette section with 18 examples is excessive, and some explanations could be tightened. | 2 / 3 |
Actionability | Provides fully executable commands and code examples throughout, including specific script paths, bash commands, and JSON structures. The workflows are copy-paste ready with concrete examples. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with numbered steps and explicit validation checkpoints (e.g., 'CRITICAL: Validate immediately after each edit'). The template-based workflow includes detailed steps with verification at each stage. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections and appropriate references to external files like html2pptx.md and ooxml.md. Content is logically split between overview, reading, creating, and editing workflows with clear navigation. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (520 lines); consider splitting into references/ and linking | Warning |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
Total | 13 / 16 Passed | |
Table of Contents
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.