google-slides
Use this skill any time the user wants to create a Google Slides deck from a template, mentions "Google Slides" with a template in mind, provides a Google Slides URL plus a content brief, or asks to "make slides", "build a deck", "generate a presentation", or "fill this template" in a Google Workspace context. Requires the Studio Google Slides + Google Drive MCP connectors. Do NOT use for PowerPoint (.pptx) creation (use the pptx skill), for editing without a template, or for authoring a new template (template authoring has its own skill).
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 strong description with excellent trigger terms, clear 'when to use' guidance, and outstanding distinctiveness through explicit negative boundaries. Its main weakness is that it focuses heavily on when to invoke the skill rather than detailing the concrete actions it performs (e.g., what specifically happens when filling a template). Adding a brief 'what it does' clause listing specific capabilities would elevate it further.
Suggestions
Add concrete action verbs describing what the skill does, e.g., 'Populates template slides with user-provided content, duplicates slide layouts, inserts text and images into placeholders, and exports the final deck.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Google Slides deck from a template) and mentions some actions like 'create', 'fill this template', but it doesn't list multiple concrete actions the skill performs (e.g., replacing placeholder text, inserting images, duplicating slides). It focuses more on when to use it than what it concretely does. | 2 / 3 |
Completeness | The description explicitly answers both 'when' (with a detailed 'Use this skill any time...' clause listing multiple trigger scenarios) and 'what' (creating Google Slides decks from templates). It also includes helpful negative boundaries (when NOT to use it), which strengthens the 'when' guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'Google Slides', 'make slides', 'build a deck', 'generate a presentation', 'fill this template', 'Google Slides URL', 'content brief', and 'Google Workspace context'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Very clearly distinguished from related skills: explicitly excludes PowerPoint creation (references a pptx skill), editing without a template, and template authoring (references a separate skill). The Google Slides + template niche is well-defined and unlikely to conflict. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides highly actionable guidance for a complex multi-step workflow. The tool inventory, numbered workflow, and failure modes table give Claude everything needed to execute confidently. Minor weaknesses include some unnecessary explanatory prose and a lengthy failure modes table that could be offloaded to a reference file for better progressive disclosure.
Suggestions
Remove or shorten the 'Why this shape?' paragraph — Claude doesn't need the API design rationale to execute the workflow.
Consider moving the failure modes table to a reference file (e.g., references/failure-modes.md) and keeping only the 2-3 most critical gotchas inline to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but includes some unnecessary framing (e.g., the 'Why this shape?' paragraph explains API design rationale Claude doesn't need). The failure modes table is valuable but some entries could be tighter. Overall reasonably lean for the complexity of the task. | 2 / 3 |
Actionability | Provides specific tool names, exact parameter names (requests_yaml, replacements_yaml), concrete workflow steps with named API calls, and a detailed failure modes table with specific symptoms, causes, and fixes. The guidance is highly concrete and executable — Claude knows exactly which tools to call and in what order. | 3 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced with specific tool calls at each step, includes validation (Step 9 QA loop with explicit 'loop until 0 findings'), recovery guidance in the failure modes table, and explicit checkpoints like user sign-off at step 4. The hiding-over-deleting rationale supports reversibility. References to workflow.md for detailed per-step verification are appropriate. | 3 / 3 |
Progressive Disclosure | The skill references several supporting files (references/workflow.md, references/pattern-selection.md, references/batch-update-recipes.yaml, references/filling-content.md, google-slides-review skill) which is good structure, but no bundle files were provided to verify these exist. The inline summary of the workflow is well-calibrated, but the failure modes table is quite long and could potentially live in a reference file, keeping the main skill leaner. | 2 / 3 |
Total | 10 / 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.
- Repository
- treasure-data/td-skills
- Commit
79bb9b8
- 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.