google-slides

Google Slides work for finding, reading, summarizing, creating, importing, template following, visual cleanup, source-deck adaptation, structural repair, and content edits in native Slides decks.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/google-drive/skills/google-slides/SKILL.md

Quality

Content

70%Weight 40%Scale 1-3

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

The skill has excellent workflow clarity and progressive disclosure, with strong validation checkpoints and a clean one-level reference structure. Its weaknesses are verbosity (repetition plus general presentation-design guidance Claude already knows) and actionability that defers executable specifics to references while leaning on abstract policy.

Suggestions

Tighten the body by deduplicating the recurring "for net-new Google Slides without a provided native Slides template or reference deck" phrasing and moving general presentation-design guidance (font sizes, overlap, title-slide minimalism) into a reference file.

Reduce abstract do-not policy in the body and surface a minimal copy-paste example (e.g., one batchUpdate request shape or import call) so the main file is actionable without forcing every reference read.

Consolidate the overlapping Release-Blocker Checklist and Non-Negotiable Output Invariant sections to cut repetition while preserving the validation checkpoints.

Dimension	Reasoning	Score
Conciseness	The runtime/routing/safety content is efficient and novel, but the body is padded with repetition (the "for net-new Google Slides without a provided native Slides template or reference deck" phrasing recurs several times) and a "Slides" subsection re-explains general presentation-design knowledge (font sizes, overlap, title-slide minimalism) Claude already knows.	2 / 3
Actionability	Concrete specifics exist (tool names like mcp__codex_apps__google_drive_import_presentation, upload_mode: "native_google_slides", the Task-to-Reference map), but executable write/recipe details are deliberately deferred to references and much of the body is abstract policy and do-nots rather than copy-paste guidance.	2 / 3
Workflow Clarity	Clear sequenced workflows with explicit validation checkpoints: the Canonical Workflow Bias 7-step sequence, the 19-item Release-Blocker Checklist with readback/thumbnail verification, "API success is not completion... You MUST curl the image", and the Required Read Order provide strong feedback loops.	3 / 3
Progressive Disclosure	The body is an overview that routes to 15 verified one-level-deep reference files via a well-signaled Task-to-Reference Map, with assets in ./assets/; navigation is easy and content is appropriately split across files.	3 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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

The description is specific and distinctive, enumerating many concrete Google Slides actions within a clear niche. Its main weakness is the absence of an explicit "Use when..." trigger clause and somewhat unnatural trigger phrasing.

Suggestions

Add an explicit "Use when..." clause naming natural user triggers (e.g., "Use when creating or editing Google Slides presentations, importing decks, or cleaning up slide layouts").

Include common user-facing terms like "presentations" and "slide deck" alongside "Slides decks" for better trigger coverage.

Rephrase the opening so it reads as a natural capability statement rather than the "Google Slides work for..." noun phrase.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ("finding, reading, summarizing, creating, importing, template following, visual cleanup, source-deck adaptation, structural repair, and content edits"), matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly answers "what" via the enumerated actions, but provides no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 2 per the guidelines.	2 / 3
Trigger Term Quality	Contains relevant terms ("Google Slides", "Slides decks") but the awkward noun-phrase construction ("Google Slides work for finding...") is not natural user phrasing and omits common variations like "presentations" or "slide deck".	2 / 3
Distinctiveness Conflict Risk	Scoped to "native Slides decks" with a clear Google Slides niche and distinct triggers, making conflict with other skills unlikely.	3 / 3
	Total	10 / 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: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/google-drive/skills/google-slides/SKILL.md
Commit: 11c74d6

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.