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).

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary skill body: concise, highly actionable, with a well-sequenced workflow carrying explicit validation checkpoints, and clean one-level-deep progressive disclosure to verified reference files. No significant weaknesses.

Dimension	Reasoning	Score
Conciseness	Lean and dense with no padding: it never explains what Google Slides is, and the terse "Why this shape?" justifies the architecture without bloat, matching the top anchor.	3 / 3
Actionability	Concrete tool names, exact parameter forms (`uc?id=`, `role: reader`, `type: anyone`), placeholder object IDs, and a copy-paste YAML recipe library make the guidance fully executable.	3 / 3
Workflow Clarity	The numbered 10-step workflow includes explicit validation checkpoints (connector confirmation at step 1, user sign-off at step 4, an independent QA sub-agent loop "until 0 findings" at step 9), satisfying the feedback-loop anchor.	3 / 3
Progressive Disclosure	SKILL.md is a genuine overview that links four real, clearly-signaled one-level-deep reference files (workflow.md, pattern-selection.md, filling-content.md, batch-update-recipes.yaml), each verified to exist and appropriately split from the body.	3 / 3
	Total	12 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, complete description with excellent natural trigger coverage and clear negative-scope conflict avoidance. Its only weakness is the second-person "Use this skill" framing rather than third-person voice, which the rubric penalizes on specificity.

Suggestions

Rewrite the opening in third person (e.g., "Creates a Google Slides deck from a template by...") to satisfy the third-person voice guideline and recover the specificity point.

Lead with the concrete capabilities (pick pattern slides, duplicate, fill via style-preserving replacement, hide originals) before the trigger list so the "what" is enumerated as actions, not just trigger phrases.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ("create a Google Slides deck from a template", "fill this template") plus required connectors, but the second-person framing ("Use this skill any time the user wants...") departs from third-person voice, triggering the rubric's specificity penalty.	2 / 3
Completeness	Clearly answers both what (template-driven deck creation via pattern duplication and filling) and when (explicit trigger clauses plus negative scope), satisfying the top anchor.	3 / 3
Trigger Term Quality	Excellent natural coverage of phrases users would actually say ("make slides", "build a deck", "generate a presentation", "fill this template", "Google Slides", "template", "Google Workspace"), matching the top anchor.	3 / 3
Distinctiveness Conflict Risk	The explicit "Do NOT use for PowerPoint (.pptx) creation (use the pptx skill)" carve-out and required MCP connectors give it a distinct niche unlikely to trigger the wrong skill.	3 / 3
	Total	11 / 12 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: treasure-data/td-skills
Commit: 50d5a57

Reviewed: 8 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.