odyssey4me/google-slides
Create and edit Google Slides presentations. Add or delete slides, insert text, shapes, and images. Use when asked to build a deck, create a slideshow, update a Google presentation, or edit slides.
75
94%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
100%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 strong skill description that clearly communicates specific capabilities, includes natural trigger terms users would use, and explicitly states both what the skill does and when to use it. The Google Slides focus provides clear distinctiveness from other presentation-related skills. The description is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create and edit Google Slides presentations', 'Add or delete slides', 'insert text, shapes, and images'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create/edit presentations, add/delete slides, insert text/shapes/images) and 'when' with an explicit 'Use when...' clause listing trigger scenarios like building a deck, creating a slideshow, or updating a Google presentation. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'deck', 'slideshow', 'Google presentation', 'edit slides', 'Google Slides'. These cover common variations of how users refer to presentation tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Google Slides specifically, which distinguishes it from generic presentation skills or PowerPoint/.pptx skills. The 'Google Slides' and 'Google presentation' terms create a distinct niche unlikely to conflict with other presentation tools. | 3 / 3 |
Total | 12 / 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 well-structured skill with strong actionability and workflow clarity, featuring explicit verification steps after each operation and clear error handling boundaries. The progressive disclosure is excellent with appropriate references to supporting files. The main weakness is moderate verbosity—the three examples are somewhat repetitive and some explanatory content (setup verification details, URL parsing) could be trimmed.
Suggestions
Consolidate the three examples into one comprehensive example and one simpler one, reducing repetition of the create-verify-insert-verify pattern.
Remove the 'Cannot find presentation' troubleshooting section—extracting an ID from a URL is basic knowledge Claude already has.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary verbosity. The setup verification section explains what the check command does in detail that Claude doesn't need. The troubleshooting section explains how to extract a presentation ID from a URL, which is basic knowledge. The three examples are somewhat repetitive (all follow the same create-verify-insert-verify pattern) and could be consolidated. | 2 / 3 |
Actionability | The skill provides fully executable bash commands with specific flags and arguments throughout. The examples are copy-paste ready with concrete values for coordinates, layout types, and shape types. The command reference covers all major operations with clear syntax. | 3 / 3 |
Workflow Clarity | Multi-step workflows include explicit verification checkpoints after each mutation (e.g., 'Verify creation and get the default slide ID', 'Verify content was inserted correctly'). Error handling clearly distinguishes retryable vs non-retryable errors with specific guidance to stop and inform the user for auth errors, which is an important safety boundary. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled references to deeper content: permissions.md for read/write classification, command-reference.md for full argument details, layouts-guide.md, shapes-guide.md, and external OAuth setup guides. References are one level deep and clearly labeled with their purpose. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents